llama-stack-mirror/client-sdks/stainless/openapi.yml
Sébastien Han 357be98279
wip2
Signed-off-by: Sébastien Han <seb@redhat.com>
2025-11-04 10:23:07 +01:00

18859 lines
571 KiB
YAML

openapi: 3.1.0
info:
title: Llama Stack API - Stable & Experimental APIs
description: "A comprehensive API for building and deploying AI applications\n\n**🔗 COMBINED**: This specification includes both stable production-ready APIs and experimental pre-release APIs. Use stable APIs for production deployments and experimental APIs for testing new features."
version: 1.0.0
servers:
- url: https://api.llamastack.com
description: Production server
- url: https://staging-api.llamastack.com
description: Staging server
paths:
/v1/batches:
get:
responses:
'200':
description: A list of batch objects.
content:
application/json:
schema:
$ref: '#/components/schemas/ListBatchesResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Batches
summary: List all batches for the current user.
description: List all batches for the current user.
parameters:
- name: after
in: query
description: >-
A cursor for pagination; returns batches after this batch ID.
required: false
schema:
type: string
- name: limit
in: query
description: >-
Number of batches to return (default 20, max 100).
required: true
schema:
type: integer
deprecated: false
post:
responses:
'200':
description: The created batch object.
content:
application/json:
schema:
$ref: '#/components/schemas/Batch'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Batches
summary: >-
Create a new batch for processing multiple API requests.
description: >-
Create a new batch for processing multiple API requests.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CreateBatchRequest'
required: true
deprecated: false
/v1/batches/{batch_id}:
get:
responses:
'200':
description: The batch object.
content:
application/json:
schema:
$ref: '#/components/schemas/Batch'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Batches
summary: >-
Retrieve information about a specific batch.
description: >-
Retrieve information about a specific batch.
parameters:
- name: batch_id
in: path
description: The ID of the batch to retrieve.
required: true
schema:
type: string
deprecated: false
/v1/batches/{batch_id}/cancel:
post:
responses:
'200':
description: The updated batch object.
content:
application/json:
schema:
$ref: '#/components/schemas/Batch'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Batches
summary: Cancel a batch that is in progress.
description: Cancel a batch that is in progress.
parameters:
- name: batch_id
in: path
description: The ID of the batch to cancel.
required: true
schema:
type: string
deprecated: false
/v1/chat/completions:
get:
responses:
'200':
description: A ListOpenAIChatCompletionResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListOpenAIChatCompletionResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inference
summary: List chat completions.
description: >-
List chat completions.
:param after: The ID of the last chat completion to return.
:param limit: The maximum number of chat completions to return.
:param model: The model to filter by.
:param order: The order to sort the chat completions by: "asc" or
"desc". Defaults to "desc".
:returns: A ListOpenAIChatCompletionResponse.
parameters:
- name: after
description: >-
The ID of the last chat completion to return.
required: false
schema:
type: string
in: query
- name: limit
description: >-
The maximum number of chat completions to return.
required: false
schema:
type: integer
in: query
- name: model
description: The model to filter by.
required: false
schema:
type: string
in: query
- name: order
description: >-
The order to sort the chat completions by: "asc" or "desc". Defaults to
"desc".
required: false
schema:
$ref: '#/components/schemas/Order'
in: query
deprecated: false
post:
responses:
'200':
description: An OpenAIChatCompletion.
content:
application/json:
schema:
$ref: '#/components/schemas/llama_stack.apis.inference.inference.OpenAIChatCompletion
| collections.abc.AsyncIterator[llama_stack.apis.inference.inference.OpenAIChatCompletionChunk]'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inference
summary: Create chat completions.
description: >-
Create chat completions.
Generate an OpenAI-compatible chat completion for the given messages using
the specified model.
:returns: An OpenAIChatCompletion.
parameters: []
requestBody:
content:
application/json:
schema:
id: Annotated
required: true
deprecated: false
/v1/chat/completions/{completion_id}:
get:
responses:
'200':
description: A OpenAICompletionWithInputMessages.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAICompletionWithInputMessages'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inference
summary: Get chat completion.
description: >-
Get chat completion.
Describe a chat completion by its ID.
:param completion_id: ID of the chat completion.
:returns: A OpenAICompletionWithInputMessages.
parameters:
- name: completion_id
description: ID of the chat completion.
required: true
schema:
type: string
in: path
deprecated: false
/v1/completions:
post:
responses:
'200':
description: An OpenAICompletion.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAICompletion'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inference
summary: Create completion.
description: >-
Create completion.
Generate an OpenAI-compatible completion for the given prompt using the specified
model.
:returns: An OpenAICompletion.
parameters: []
requestBody:
content:
application/json:
schema:
id: Annotated
required: true
deprecated: false
/v1/conversations:
post:
responses:
'200':
description: The created conversation object.
content:
application/json:
schema:
$ref: '#/components/schemas/Conversation'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Conversations
summary: Create a conversation.
description: >-
Create a conversation.
Create a conversation.
:param items: Initial items to include in the conversation context.
:param metadata: Set of key-value pairs that can be attached to an
object.
:returns: The created conversation object.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CreateConversationRequest'
required: true
deprecated: false
/v1/conversations/{conversation_id}:
get:
responses:
'200':
description: The conversation object.
content:
application/json:
schema:
$ref: '#/components/schemas/Conversation'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Conversations
summary: Retrieve a conversation.
description: >-
Retrieve a conversation.
Get a conversation with the given ID.
:param conversation_id: The conversation identifier.
:returns: The conversation object.
parameters:
- name: conversation_id
description: The conversation identifier.
required: true
schema:
type: string
in: path
deprecated: false
post:
responses:
'200':
description: The updated conversation object.
content:
application/json:
schema:
$ref: '#/components/schemas/Conversation'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Conversations
summary: Update a conversation.
description: >-
Update a conversation.
Update a conversation's metadata with the given ID.
:param conversation_id: The conversation identifier.
:param metadata: Set of key-value pairs that can be attached to an
object.
:returns: The updated conversation object.
parameters:
- name: conversation_id
description: The conversation identifier.
required: true
schema:
type: string
in: path
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/UpdateConversationRequest'
required: true
deprecated: false
delete:
responses:
'200':
description: The deleted conversation resource.
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationDeletedResource'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Conversations
summary: Delete a conversation.
description: >-
Delete a conversation.
Delete a conversation with the given ID.
:param conversation_id: The conversation identifier.
:returns: The deleted conversation resource.
parameters:
- name: conversation_id
description: The conversation identifier.
required: true
schema:
type: string
in: path
deprecated: false
/v1/conversations/{conversation_id}/items:
get:
responses:
'200':
description: List of conversation items.
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationItemList'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Conversations
summary: List items.
description: >-
List items.
List items in the conversation.
:param conversation_id: The conversation identifier.
:param after: An item ID to list items after, used in pagination.
:param include: Specify additional output data to include in the response.
:param limit: A limit on the number of objects to be returned (1-100,
default 20).
:param order: The order to return items in (asc or desc, default desc).
:returns: List of conversation items.
parameters:
- name: conversation_id
description: The conversation identifier.
required: true
schema:
type: string
in: path
- name: after
description: >-
An item ID to list items after, used in pagination.
required: false
schema:
type: string
in: query
- name: include
description: >-
Specify additional output data to include in the response.
required: false
schema:
$ref: '#/components/schemas/list'
in: query
- name: limit
description: >-
A limit on the number of objects to be returned (1-100, default 20).
required: false
schema:
type: integer
in: query
- name: order
description: >-
The order to return items in (asc or desc, default desc).
required: false
schema:
$ref: '#/components/schemas/Literal'
in: query
deprecated: false
post:
responses:
'200':
description: List of created items.
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationItemList'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Conversations
summary: Create items.
description: >-
Create items.
Create items in the conversation.
:param conversation_id: The conversation identifier.
:param items: Items to include in the conversation context.
:returns: List of created items.
parameters:
- name: conversation_id
description: The conversation identifier.
required: true
schema:
type: string
in: path
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/AddItemsRequest'
required: true
deprecated: false
/v1/conversations/{conversation_id}/items/{item_id}:
get:
responses:
'200':
description: The conversation item.
content:
application/json:
schema:
id: Annotated
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Conversations
summary: Retrieve an item.
description: >-
Retrieve an item.
Retrieve a conversation item.
:param conversation_id: The conversation identifier.
:param item_id: The item identifier.
:returns: The conversation item.
parameters:
- name: conversation_id
description: The conversation identifier.
required: true
schema:
type: string
in: path
- name: item_id
description: The item identifier.
required: true
schema:
type: string
in: path
deprecated: false
delete:
responses:
'200':
description: The deleted item resource.
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationItemDeletedResource'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Conversations
summary: Delete an item.
description: >-
Delete an item.
Delete a conversation item.
:param conversation_id: The conversation identifier.
:param item_id: The item identifier.
:returns: The deleted item resource.
parameters:
- name: conversation_id
description: The conversation identifier.
required: true
schema:
type: string
in: path
- name: item_id
description: The item identifier.
required: true
schema:
type: string
in: path
deprecated: false
/v1/embeddings:
post:
responses:
'200':
description: >-
An OpenAIEmbeddingsResponse containing the embeddings.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIEmbeddingsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inference
summary: Create embeddings.
description: >-
Create embeddings.
Generate OpenAI-compatible embeddings for the given input using the specified
model.
:returns: An OpenAIEmbeddingsResponse containing the embeddings.
parameters: []
requestBody:
content:
application/json:
schema:
id: Annotated
required: true
deprecated: false
/v1/files:
get:
responses:
'200':
description: >-
An ListOpenAIFileResponse containing the list of files.
content:
application/json:
schema:
$ref: '#/components/schemas/ListOpenAIFileResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Files
summary: List files.
description: >-
List files.
Returns a list of files that belong to the user's organization.
:param after: A cursor for use in pagination. `after` is an object
ID that defines your place in the list. For instance, if you make a list request
and receive 100 objects, ending with obj_foo, your subsequent call can include
after=obj_foo in order to fetch the next page of the list.
:param limit: A limit on the number of objects to be returned. Limit
can range between 1 and 10,000, and the default is 10,000.
:param order: Sort order by the `created_at` timestamp of the objects.
`asc` for ascending order and `desc` for descending order.
:param purpose: Only return files with the given purpose.
:returns: An ListOpenAIFileResponse containing the list of files.
parameters:
- name: after
description: >-
A cursor for use in pagination. `after` is an object ID that defines your
place in the list. For instance, if you make a list request and receive
100 objects, ending with obj_foo, your subsequent call can include after=obj_foo
in order to fetch the next page of the list.
required: false
schema:
type: string
in: query
- name: limit
description: >-
A limit on the number of objects to be returned. Limit can range between
1 and 10,000, and the default is 10,000.
required: false
schema:
type: integer
in: query
- name: order
description: >-
Sort order by the `created_at` timestamp of the objects. `asc` for ascending
order and `desc` for descending order.
required: false
schema:
$ref: '#/components/schemas/Order'
in: query
- name: purpose
description: >-
Only return files with the given purpose.
required: false
schema:
$ref: '#/components/schemas/OpenAIFilePurpose'
in: query
deprecated: false
post:
responses:
'200':
description: >-
An OpenAIFileObject representing the uploaded file.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIFileObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Files
summary: Upload file.
description: >-
Upload file.
Upload a file that can be used across various endpoints.
The file upload should be a multipart form request with:
- file: The File object (not file name) to be uploaded.
- purpose: The intended purpose of the uploaded file.
- expires_after: Optional form values describing expiration for the
file.
:param file: The uploaded file object containing content and metadata
(filename, content_type, etc.).
:param purpose: The intended purpose of the uploaded file (e.g., "assistants",
"fine-tune").
:param expires_after: Optional form values describing expiration for
the file.
:returns: An OpenAIFileObject representing the uploaded file.
parameters: []
requestBody:
content:
multipart/form-data:
schema:
type: object
properties:
file:
type: string
format: binary
purpose:
$ref: '#/components/schemas/OpenAIFilePurpose'
expires_after:
$ref: '#/components/schemas/ExpiresAfter'
required:
- file
- purpose
required: true
deprecated: false
/v1/files/{file_id}:
get:
responses:
'200':
description: >-
An OpenAIFileObject containing file information.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIFileObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Files
summary: Retrieve file.
description: >-
Retrieve file.
Returns information about a specific file.
:param file_id: The ID of the file to use for this request.
:returns: An OpenAIFileObject containing file information.
parameters:
- name: file_id
description: >-
The ID of the file to use for this request.
required: true
schema:
type: string
in: path
deprecated: false
delete:
responses:
'200':
description: >-
An OpenAIFileDeleteResponse indicating successful deletion.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIFileDeleteResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Files
summary: Delete file.
description: >-
Delete file.
:param file_id: The ID of the file to use for this request.
:returns: An OpenAIFileDeleteResponse indicating successful deletion.
parameters:
- name: file_id
description: >-
The ID of the file to use for this request.
required: true
schema:
type: string
in: path
deprecated: false
/v1/files/{file_id}/content:
get:
responses:
'200':
description: >-
The raw file content as a binary response.
content:
application/json:
schema:
$ref: '#/components/schemas/Response'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Files
summary: Retrieve file content.
description: >-
Retrieve file content.
Returns the contents of the specified file.
:param file_id: The ID of the file to use for this request.
:returns: The raw file content as a binary response.
parameters:
- name: file_id
description: >-
The ID of the file to use for this request.
required: true
schema:
type: string
in: path
deprecated: false
/v1/health:
get:
responses:
'200':
description: >-
Health information indicating if the service is operational.
content:
application/json:
schema:
$ref: '#/components/schemas/HealthInfo'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inspect
summary: Get health status.
description: >-
Get health status.
Get the current health status of the service.
:returns: Health information indicating if the service is operational.
parameters: []
deprecated: false
/v1/inspect/routes:
get:
responses:
'200':
description: >-
Response containing information about all available routes.
content:
application/json:
schema:
$ref: '#/components/schemas/ListRoutesResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inspect
summary: List routes.
description: >-
List routes.
List all available API routes with their methods and implementing providers.
parameters:
- name: api_filter
in: query
description: >-
Optional filter to control which routes are returned. Can be an API level
('v1', 'v1alpha', 'v1beta') to show non-deprecated routes at that level,
or 'deprecated' to show deprecated routes across all levels. If not specified,
returns only non-deprecated v1 routes.
required: false
schema:
type: string
enum:
- v1
- v1alpha
- v1beta
- deprecated
deprecated: false
/v1/models:
get:
responses:
'200':
description: A OpenAIListModelsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIListModelsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Models
summary: List models using the OpenAI API.
description: List models using the OpenAI API.
parameters: []
deprecated: false
post:
responses:
'200':
description: A Model.
content:
application/json:
schema:
$ref: '#/components/schemas/Model'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Models
summary: Register model.
description: >-
Register model.
Register a model.
:param model_id: The identifier of the model to register.
:param provider_model_id: The identifier of the model in the provider.
:param provider_id: The identifier of the provider.
:param metadata: Any additional metadata for this model.
:param model_type: The type of model to register.
:returns: A Model.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RegisterModelRequest'
required: true
deprecated: false
/v1/models/{model_id}:
get:
responses:
'200':
description: A Model.
content:
application/json:
schema:
$ref: '#/components/schemas/Model'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Models
summary: Get model.
description: >-
Get model.
Get a model by its identifier.
:param model_id: The identifier of the model to get.
:returns: A Model.
parameters:
- name: model_id
description: The identifier of the model to get.
required: true
schema:
type: string
in: path
deprecated: false
delete:
responses:
'200':
description: OK
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Models
summary: Unregister model.
description: >-
Unregister model.
Unregister a model.
:param model_id: The identifier of the model to unregister.
parameters:
- name: model_id
description: >-
The identifier of the model to unregister.
required: true
schema:
type: string
in: path
deprecated: false
/v1/moderations:
post:
responses:
'200':
description: A moderation object.
content:
application/json:
schema:
$ref: '#/components/schemas/ModerationObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Safety
summary: Create moderation.
description: >-
Create moderation.
Classifies if text and/or image inputs are potentially harmful.
:param input: Input (or inputs) to classify.
Can be a single string, an array of strings, or an array of multi-modal
input objects similar to other models.
:param model: (Optional) The content moderation model you would like
to use.
:returns: A moderation object.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RunModerationRequest'
required: true
deprecated: false
/v1/prompts:
get:
responses:
'200':
description: >-
A ListPromptsResponse containing all prompts.
content:
application/json:
schema:
$ref: '#/components/schemas/ListPromptsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Prompts
summary: List all prompts.
description: >-
List all prompts.
:returns: A ListPromptsResponse containing all prompts.
parameters: []
deprecated: false
post:
responses:
'200':
description: The created Prompt resource.
content:
application/json:
schema:
$ref: '#/components/schemas/Prompt'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Prompts
summary: Create prompt.
description: >-
Create prompt.
Create a new prompt.
:param prompt: The prompt text content with variable placeholders.
:param variables: List of variable names that can be used in the prompt
template.
:returns: The created Prompt resource.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CreatePromptRequest'
required: true
deprecated: false
/v1/prompts/{prompt_id}:
get:
responses:
'200':
description: A Prompt resource.
content:
application/json:
schema:
$ref: '#/components/schemas/Prompt'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Prompts
summary: Get prompt.
description: >-
Get prompt.
Get a prompt by its identifier and optional version.
:param prompt_id: The identifier of the prompt to get.
:param version: The version of the prompt to get (defaults to latest).
:returns: A Prompt resource.
parameters:
- name: prompt_id
description: The identifier of the prompt to get.
required: true
schema:
type: string
in: path
- name: version
description: >-
The version of the prompt to get (defaults to latest).
required: false
schema:
type: integer
in: query
deprecated: false
post:
responses:
'200':
description: >-
The updated Prompt resource with incremented version.
content:
application/json:
schema:
$ref: '#/components/schemas/Prompt'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Prompts
summary: Update prompt.
description: >-
Update prompt.
Update an existing prompt (increments version).
:param prompt_id: The identifier of the prompt to update.
:param prompt: The updated prompt text content.
:param version: The current version of the prompt being updated.
:param variables: Updated list of variable names that can be used
in the prompt template.
:param set_as_default: Set the new version as the default (default=True).
:returns: The updated Prompt resource with incremented version.
parameters:
- name: prompt_id
description: The identifier of the prompt to update.
required: true
schema:
type: string
in: path
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/UpdatePromptRequest'
required: true
deprecated: false
delete:
responses:
'200':
description: OK
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Prompts
summary: Delete prompt.
description: >-
Delete prompt.
Delete a prompt.
:param prompt_id: The identifier of the prompt to delete.
parameters:
- name: prompt_id
description: The identifier of the prompt to delete.
required: true
schema:
type: string
in: path
deprecated: false
/v1/prompts/{prompt_id}/set-default-version:
post:
responses:
'200':
description: >-
The prompt with the specified version now set as default.
content:
application/json:
schema:
$ref: '#/components/schemas/Prompt'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Prompts
summary: Set prompt version.
description: >-
Set prompt version.
Set which version of a prompt should be the default in get_prompt (latest).
:param prompt_id: The identifier of the prompt.
:param version: The version to set as default.
:returns: The prompt with the specified version now set as default.
parameters:
- name: prompt_id
description: The identifier of the prompt.
required: true
schema:
type: string
in: path
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/SetDefaultVersionRequest'
required: true
deprecated: false
/v1/prompts/{prompt_id}/versions:
get:
responses:
'200':
description: >-
A ListPromptsResponse containing all versions of the prompt.
content:
application/json:
schema:
$ref: '#/components/schemas/ListPromptsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Prompts
summary: List prompt versions.
description: >-
List prompt versions.
List all versions of a specific prompt.
:param prompt_id: The identifier of the prompt to list versions for.
:returns: A ListPromptsResponse containing all versions of the prompt.
parameters:
- name: prompt_id
description: >-
The identifier of the prompt to list versions for.
required: true
schema:
type: string
in: path
deprecated: false
/v1/providers:
get:
responses:
'200':
description: >-
A ListProvidersResponse containing information about all providers.
content:
application/json:
schema:
$ref: '#/components/schemas/ListProvidersResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Providers
summary: List providers.
description: >-
List providers.
List all available providers.
:returns: A ListProvidersResponse containing information about all
providers.
parameters: []
deprecated: false
/v1/providers/{provider_id}:
get:
responses:
'200':
description: >-
A ProviderInfo object containing the provider's details.
content:
application/json:
schema:
$ref: '#/components/schemas/ProviderInfo'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Providers
summary: Get provider.
description: >-
Get provider.
Get detailed information about a specific provider.
:param provider_id: The ID of the provider to inspect.
:returns: A ProviderInfo object containing the provider's details.
parameters:
- name: provider_id
description: The ID of the provider to inspect.
required: true
schema:
type: string
in: path
deprecated: false
/v1/responses:
get:
responses:
'200':
description: A ListOpenAIResponseObject.
content:
application/json:
schema:
$ref: '#/components/schemas/ListOpenAIResponseObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
summary: List all responses.
description: >-
List all responses.
:param after: The ID of the last response to return.
:param limit: The number of responses to return.
:param model: The model to filter responses by.
:param order: The order to sort responses by when sorted by created_at
('asc' or 'desc').
:returns: A ListOpenAIResponseObject.
parameters:
- name: after
description: The ID of the last response to return.
required: false
schema:
type: string
in: query
- name: limit
description: The number of responses to return.
required: false
schema:
type: integer
in: query
- name: model
description: The model to filter responses by.
required: false
schema:
type: string
in: query
- name: order
description: >-
The order to sort responses by when sorted by created_at ('asc' or 'desc').
required: false
schema:
$ref: '#/components/schemas/Order'
in: query
deprecated: false
post:
responses:
'200':
description: An OpenAIResponseObject.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIResponseObject'
text/event-stream:
schema:
$ref: '#/components/schemas/AsyncIterator'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
summary: Create a model response.
description: >-
Create a model response.
:param input: Input message(s) to create the response.
:param model: The underlying LLM used for completions.
:param previous_response_id: (Optional) if specified, the new response
will be a continuation of the previous response. This can be used to easily
fork-off new responses from existing responses.
:param conversation: (Optional) The ID of a conversation to add the
response to. Must begin with 'conv_'. Input and output messages will be automatically
added to the conversation.
:param include: (Optional) Additional fields to include in the response.
:param guardrails: (Optional) List of guardrails to apply during response
generation. Can be guardrail IDs (strings) or guardrail specifications.
:returns: An OpenAIResponseObject.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CreateOpenaiResponseRequest'
required: true
deprecated: false
x-llama-stack-extra-body-params:
- name: guardrails
schema:
id: Annotated
description: >-
List of guardrails to apply during response generation. Guardrails provide
safety and content moderation.
required: true
/v1/responses/{response_id}:
get:
responses:
'200':
description: An OpenAIResponseObject.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIResponseObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
summary: Get a model response.
description: >-
Get a model response.
:param response_id: The ID of the OpenAI response to retrieve.
:returns: An OpenAIResponseObject.
parameters:
- name: response_id
description: >-
The ID of the OpenAI response to retrieve.
required: true
schema:
type: string
in: path
deprecated: false
delete:
responses:
'200':
description: An OpenAIDeleteResponseObject
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIDeleteResponseObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
summary: Delete a response.
description: >-
Delete a response.
:param response_id: The ID of the OpenAI response to delete.
:returns: An OpenAIDeleteResponseObject
parameters:
- name: response_id
description: The ID of the OpenAI response to delete.
required: true
schema:
type: string
in: path
deprecated: false
/v1/responses/{response_id}/input_items:
get:
responses:
'200':
description: An ListOpenAIResponseInputItem.
content:
application/json:
schema:
$ref: '#/components/schemas/ListOpenAIResponseInputItem'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
summary: List input items.
description: >-
List input items.
:param response_id: The ID of the response to retrieve input items for.
:param after: An item ID to list items after, used for pagination.
:param before: An item ID to list items before, used for pagination.
:param include: Additional fields to include in the response.
:param limit: A limit on the number of objects to be returned. Limit
can range between 1 and 100, and the default is 20.
:param order: The order to return the input items in. Default is desc.
:returns: An ListOpenAIResponseInputItem.
parameters:
- name: response_id
description: >-
The ID of the response to retrieve input items for.
required: true
schema:
type: string
in: path
- name: after
description: >-
An item ID to list items after, used for pagination.
required: false
schema:
type: string
in: query
- name: before
description: >-
An item ID to list items before, used for pagination.
required: false
schema:
type: string
in: query
- name: include
description: >-
Additional fields to include in the response.
required: false
schema:
$ref: '#/components/schemas/list'
in: query
- name: limit
description: >-
A limit on the number of objects to be returned. Limit can range between
1 and 100, and the default is 20.
required: false
schema:
type: integer
in: query
- name: order
description: >-
The order to return the input items in. Default is desc.
required: false
schema:
$ref: '#/components/schemas/Order'
in: query
deprecated: false
/v1/safety/run-shield:
post:
responses:
'200':
description: A RunShieldResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/RunShieldResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Safety
summary: Run shield.
description: >-
Run shield.
Run a shield.
:param shield_id: The identifier of the shield to run.
:param messages: The messages to run the shield on.
:param params: The parameters of the shield.
:returns: A RunShieldResponse.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RunShieldRequest'
required: true
deprecated: false
/v1/scoring-functions:
get:
responses:
'200':
description: A ListScoringFunctionsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListScoringFunctionsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ScoringFunctions
summary: List all scoring functions.
description: >-
List all scoring functions.
:returns: A ListScoringFunctionsResponse.
parameters: []
deprecated: false
post:
responses:
'200':
description: OK
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ScoringFunctions
summary: Register a scoring function.
description: >-
Register a scoring function.
:param scoring_fn_id: The ID of the scoring function to register.
:param description: The description of the scoring function.
:param return_type: The return type of the scoring function.
:param provider_scoring_fn_id: The ID of the provider scoring function
to use for the scoring function.
:param provider_id: The ID of the provider to use for the scoring
function.
:param params: The parameters for the scoring function for benchmark
eval, these can be overridden for app eval.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RegisterScoringFunctionRequest'
required: true
deprecated: false
/v1/scoring-functions/{scoring_fn_id}:
get:
responses:
'200':
description: A ScoringFn.
content:
application/json:
schema:
$ref: '#/components/schemas/ScoringFn'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ScoringFunctions
summary: Get a scoring function by its ID.
description: >-
Get a scoring function by its ID.
:param scoring_fn_id: The ID of the scoring function to get.
:returns: A ScoringFn.
parameters:
- name: scoring_fn_id
description: The ID of the scoring function to get.
required: true
schema:
type: string
in: path
deprecated: false
delete:
responses:
'200':
description: OK
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ScoringFunctions
summary: Unregister a scoring function.
description: >-
Unregister a scoring function.
:param scoring_fn_id: The ID of the scoring function to unregister.
parameters:
- name: scoring_fn_id
description: >-
The ID of the scoring function to unregister.
required: true
schema:
type: string
in: path
deprecated: false
/v1/scoring/score:
post:
responses:
'200':
description: >-
A ScoreResponse object containing rows and aggregated results.
content:
application/json:
schema:
$ref: '#/components/schemas/ScoreResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Scoring
summary: Score a list of rows.
description: >-
Score a list of rows.
:param input_rows: The rows to score.
:param scoring_functions: The scoring functions to use for the scoring.
:returns: A ScoreResponse object containing rows and aggregated results.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ScoreRequest'
required: true
deprecated: false
/v1/scoring/score-batch:
post:
responses:
'200':
description: A ScoreBatchResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ScoreBatchResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Scoring
summary: Score a batch of rows.
description: >-
Score a batch of rows.
:param dataset_id: The ID of the dataset to score.
:param scoring_functions: The scoring functions to use for the scoring.
:param save_results_dataset: Whether to save the results to a dataset.
:returns: A ScoreBatchResponse.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ScoreBatchRequest'
required: true
deprecated: false
/v1/shields:
get:
responses:
'200':
description: A ListShieldsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListShieldsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Shields
summary: List all shields.
description: >-
List all shields.
:returns: A ListShieldsResponse.
parameters: []
deprecated: false
post:
responses:
'200':
description: A Shield.
content:
application/json:
schema:
$ref: '#/components/schemas/Shield'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Shields
summary: Register a shield.
description: >-
Register a shield.
:param shield_id: The identifier of the shield to register.
:param provider_shield_id: The identifier of the shield in the provider.
:param provider_id: The identifier of the provider.
:param params: The parameters of the shield.
:returns: A Shield.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RegisterShieldRequest'
required: true
deprecated: false
/v1/shields/{identifier}:
get:
responses:
'200':
description: A Shield.
content:
application/json:
schema:
$ref: '#/components/schemas/Shield'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Shields
summary: Get a shield by its identifier.
description: >-
Get a shield by its identifier.
:param identifier: The identifier of the shield to get.
:returns: A Shield.
parameters:
- name: identifier
description: The identifier of the shield to get.
required: true
schema:
type: string
in: path
deprecated: false
delete:
responses:
'200':
description: OK
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Shields
summary: Unregister a shield.
description: >-
Unregister a shield.
:param identifier: The identifier of the shield to unregister.
parameters:
- name: identifier
description: >-
The identifier of the shield to unregister.
required: true
schema:
type: string
in: path
deprecated: false
/v1/tool-runtime/invoke:
post:
responses:
'200':
description: A ToolInvocationResult.
content:
application/json:
schema:
$ref: '#/components/schemas/ToolInvocationResult'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ToolRuntime
summary: Run a tool with the given arguments.
description: >-
Run a tool with the given arguments.
:param tool_name: The name of the tool to invoke.
:param kwargs: A dictionary of arguments to pass to the tool.
:returns: A ToolInvocationResult.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/InvokeToolRequest'
required: true
deprecated: false
/v1/tool-runtime/list-tools:
get:
responses:
'200':
description: A ListToolDefsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListToolDefsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ToolRuntime
summary: List all tools in the runtime.
description: >-
List all tools in the runtime.
:param tool_group_id: The ID of the tool group to list tools for.
:param mcp_endpoint: The MCP endpoint to use for the tool group.
:returns: A ListToolDefsResponse.
parameters:
- name: tool_group_id
description: >-
The ID of the tool group to list tools for.
required: false
schema:
type: string
in: query
- name: mcp_endpoint
description: >-
The MCP endpoint to use for the tool group.
required: false
schema:
$ref: '#/components/schemas/URL'
in: query
deprecated: false
/v1/tool-runtime/rag-tool/insert:
post:
responses:
'200':
description: OK
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ToolRuntime
summary: >-
Index documents so they can be used by the RAG system.
description: >-
Index documents so they can be used by the RAG system.
:param documents: List of documents to index in the RAG system
:param vector_store_id: ID of the vector database to store the document
embeddings
:param chunk_size_in_tokens: (Optional) Size in tokens for document
chunking during indexing
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/InsertRequest'
required: true
deprecated: false
/v1/tool-runtime/rag-tool/query:
post:
responses:
'200':
description: >-
RAGQueryResult containing the retrieved content and metadata
content:
application/json:
schema:
$ref: '#/components/schemas/RAGQueryResult'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ToolRuntime
summary: >-
Query the RAG system for context; typically invoked by the agent.
description: >-
Query the RAG system for context; typically invoked by the agent.
:param content: The query content to search for in the indexed documents
:param vector_store_ids: List of vector database IDs to search within
:param query_config: (Optional) Configuration parameters for the query
operation
:returns: RAGQueryResult containing the retrieved content and metadata
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/QueryRequest'
required: true
deprecated: false
/v1/toolgroups:
get:
responses:
'200':
description: A ListToolGroupsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListToolGroupsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ToolGroups
summary: List tool groups with optional provider.
description: >-
List tool groups with optional provider.
:returns: A ListToolGroupsResponse.
parameters: []
deprecated: false
post:
responses:
'200':
description: OK
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ToolGroups
summary: Register a tool group.
description: >-
Register a tool group.
:param toolgroup_id: The ID of the tool group to register.
:param provider_id: The ID of the provider to use for the tool group.
:param mcp_endpoint: The MCP endpoint to use for the tool group.
:param args: A dictionary of arguments to pass to the tool group.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RegisterToolGroupRequest'
required: true
deprecated: false
/v1/toolgroups/{toolgroup_id}:
get:
responses:
'200':
description: A ToolGroup.
content:
application/json:
schema:
$ref: '#/components/schemas/ToolGroup'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ToolGroups
summary: Get a tool group by its ID.
description: >-
Get a tool group by its ID.
:param toolgroup_id: The ID of the tool group to get.
:returns: A ToolGroup.
parameters:
- name: toolgroup_id
description: The ID of the tool group to get.
required: true
schema:
type: string
in: path
deprecated: false
delete:
responses:
'200':
description: OK
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ToolGroups
summary: Unregister a tool group.
description: >-
Unregister a tool group.
:param toolgroup_id: The ID of the tool group to unregister.
parameters:
- name: toolgroup_id
description: The ID of the tool group to unregister.
required: true
schema:
type: string
in: path
deprecated: false
/v1/tools:
get:
responses:
'200':
description: A ListToolDefsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListToolDefsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ToolGroups
summary: List tools with optional tool group.
description: >-
List tools with optional tool group.
:param toolgroup_id: The ID of the tool group to list tools for.
:returns: A ListToolDefsResponse.
parameters:
- name: toolgroup_id
description: >-
The ID of the tool group to list tools for.
required: false
schema:
type: string
in: query
deprecated: false
/v1/tools/{tool_name}:
get:
responses:
'200':
description: A ToolDef.
content:
application/json:
schema:
$ref: '#/components/schemas/ToolDef'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ToolGroups
summary: Get a tool by its name.
description: >-
Get a tool by its name.
:param tool_name: The name of the tool to get.
:returns: A ToolDef.
parameters:
- name: tool_name
description: The name of the tool to get.
required: true
schema:
type: string
in: path
deprecated: false
/v1/vector-io/insert:
post:
responses:
'200':
description: OK
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Insert chunks into a vector database.
description: >-
Insert chunks into a vector database.
:param vector_store_id: The identifier of the vector database to insert the
chunks into.
:param chunks: The chunks to insert. Each `Chunk` should contain content
which can be interleaved text, images, or other types.
`metadata`: `dict[str, Any]` and `embedding`: `List[float]` are
optional.
If `metadata` is provided, you configure how Llama Stack formats
the chunk during generation.
If `embedding` is not provided, it will be computed later.
:param ttl_seconds: The time to live of the chunks.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/InsertChunksRequest'
required: true
deprecated: false
/v1/vector-io/query:
post:
responses:
'200':
description: A QueryChunksResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/QueryChunksResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Query chunks from a vector database.
description: >-
Query chunks from a vector database.
:param vector_store_id: The identifier of the vector database to query.
:param query: The query to search for.
:param params: The parameters of the query.
:returns: A QueryChunksResponse.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/QueryChunksRequest'
required: true
deprecated: false
/v1/vector_stores:
get:
responses:
'200':
description: >-
A VectorStoreListResponse containing the list of vector stores.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreListResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Returns a list of vector stores.
description: >-
Returns a list of vector stores.
:param limit: A limit on the number of objects to be returned. Limit can range
between 1 and 100, and the default is 20.
:param order: Sort order by the `created_at` timestamp of the objects.
`asc` for ascending order and `desc` for descending order.
:param after: A cursor for use in pagination. `after` is an object
ID that defines your place in the list.
:param before: A cursor for use in pagination. `before` is an object
ID that defines your place in the list.
:returns: A VectorStoreListResponse containing the list of vector
stores.
parameters:
- name: limit
description: >-
A limit on the number of objects to be returned. Limit can range between
1 and 100, and the default is 20.
required: false
schema:
type: integer
in: query
- name: order
description: >-
Sort order by the `created_at` timestamp of the objects. `asc` for ascending
order and `desc` for descending order.
required: false
schema:
type: string
in: query
- name: after
description: >-
A cursor for use in pagination. `after` is an object ID that defines your
place in the list.
required: false
schema:
type: string
in: query
- name: before
description: >-
A cursor for use in pagination. `before` is an object ID that defines
your place in the list.
required: false
schema:
type: string
in: query
deprecated: false
post:
responses:
'200':
description: >-
A VectorStoreObject representing the created vector store.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Creates a vector store.
description: >-
Creates a vector store.
Generate an OpenAI-compatible vector store with the given parameters.
:returns: A VectorStoreObject representing the created vector store.
parameters: []
requestBody:
content:
application/json:
schema:
id: Annotated
required: true
deprecated: false
/v1/vector_stores/{vector_store_id}:
get:
responses:
'200':
description: >-
A VectorStoreObject representing the vector store.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Retrieves a vector store.
description: >-
Retrieves a vector store.
:param vector_store_id: The ID of the vector store to retrieve.
:returns: A VectorStoreObject representing the vector store.
parameters:
- name: vector_store_id
description: The ID of the vector store to retrieve.
required: true
schema:
type: string
in: path
deprecated: false
post:
responses:
'200':
description: >-
A VectorStoreObject representing the updated vector store.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Updates a vector store.
description: >-
Updates a vector store.
:param vector_store_id: The ID of the vector store to update.
:param name: The name of the vector store.
:param expires_after: The expiration policy for a vector store.
:param metadata: Set of 16 key-value pairs that can be attached to
an object.
:returns: A VectorStoreObject representing the updated vector store.
parameters:
- name: vector_store_id
description: The ID of the vector store to update.
required: true
schema:
type: string
in: path
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiUpdateVectorStoreRequest'
required: true
deprecated: false
delete:
responses:
'200':
description: >-
A VectorStoreDeleteResponse indicating the deletion status.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreDeleteResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Delete a vector store.
description: >-
Delete a vector store.
:param vector_store_id: The ID of the vector store to delete.
:returns: A VectorStoreDeleteResponse indicating the deletion status.
parameters:
- name: vector_store_id
description: The ID of the vector store to delete.
required: true
schema:
type: string
in: path
deprecated: false
/v1/vector_stores/{vector_store_id}/file_batches:
post:
responses:
'200':
description: >-
A VectorStoreFileBatchObject representing the created file batch.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileBatchObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Create a vector store file batch.
description: >-
Create a vector store file batch.
Generate an OpenAI-compatible vector store file batch for the given vector
store.
:param vector_store_id: The ID of the vector store to create the file
batch for.
:returns: A VectorStoreFileBatchObject representing the created file
batch.
parameters:
- name: vector_store_id
description: >-
The ID of the vector store to create the file batch for.
required: true
schema:
type: string
in: path
requestBody:
content:
application/json:
schema:
id: Annotated
required: true
deprecated: false
/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}:
get:
responses:
'200':
description: >-
A VectorStoreFileBatchObject representing the file batch.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileBatchObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Retrieve a vector store file batch.
description: >-
Retrieve a vector store file batch.
:param batch_id: The ID of the file batch to retrieve.
:param vector_store_id: The ID of the vector store containing the
file batch.
:returns: A VectorStoreFileBatchObject representing the file batch.
parameters:
- name: batch_id
description: The ID of the file batch to retrieve.
required: true
schema:
type: string
in: path
- name: vector_store_id
description: >-
The ID of the vector store containing the file batch.
required: true
schema:
type: string
in: path
deprecated: false
/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel:
post:
responses:
'200':
description: >-
A VectorStoreFileBatchObject representing the cancelled file batch.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileBatchObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Cancels a vector store file batch.
description: >-
Cancels a vector store file batch.
:param batch_id: The ID of the file batch to cancel.
:param vector_store_id: The ID of the vector store containing the
file batch.
:returns: A VectorStoreFileBatchObject representing the cancelled
file batch.
parameters:
- name: batch_id
description: The ID of the file batch to cancel.
required: true
schema:
type: string
in: path
- name: vector_store_id
description: >-
The ID of the vector store containing the file batch.
required: true
schema:
type: string
in: path
deprecated: false
/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/files:
get:
responses:
'200':
description: >-
A VectorStoreFilesListInBatchResponse containing the list of files in
the batch.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFilesListInBatchResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: >-
Returns a list of vector store files in a batch.
description: >-
Returns a list of vector store files in a batch.
:param batch_id: The ID of the file batch to list files from.
:param vector_store_id: The ID of the vector store containing the
file batch.
:param after: A cursor for use in pagination. `after` is an object
ID that defines your place in the list.
:param before: A cursor for use in pagination. `before` is an object
ID that defines your place in the list.
:param filter: Filter by file status. One of in_progress, completed,
failed, cancelled.
:param limit: A limit on the number of objects to be returned. Limit
can range between 1 and 100, and the default is 20.
:param order: Sort order by the `created_at` timestamp of the objects.
`asc` for ascending order and `desc` for descending order.
:returns: A VectorStoreFilesListInBatchResponse containing the list
of files in the batch.
parameters:
- name: batch_id
description: >-
The ID of the file batch to list files from.
required: true
schema:
type: string
in: path
- name: vector_store_id
description: >-
The ID of the vector store containing the file batch.
required: true
schema:
type: string
in: path
- name: after
description: >-
A cursor for use in pagination. `after` is an object ID that defines your
place in the list.
required: false
schema:
type: string
in: query
- name: before
description: >-
A cursor for use in pagination. `before` is an object ID that defines
your place in the list.
required: false
schema:
type: string
in: query
- name: filter
description: >-
Filter by file status. One of in_progress, completed, failed, cancelled.
required: false
schema:
type: string
in: query
- name: limit
description: >-
A limit on the number of objects to be returned. Limit can range between
1 and 100, and the default is 20.
required: false
schema:
type: integer
in: query
- name: order
description: >-
Sort order by the `created_at` timestamp of the objects. `asc` for ascending
order and `desc` for descending order.
required: false
schema:
type: string
in: query
deprecated: false
/v1/vector_stores/{vector_store_id}/files:
get:
responses:
'200':
description: >-
A VectorStoreListFilesResponse containing the list of files.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreListFilesResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: List files in a vector store.
description: >-
List files in a vector store.
:param vector_store_id: The ID of the vector store to list files from.
:param limit: (Optional) A limit on the number of objects to be returned.
Limit can range between 1 and 100, and the default is 20.
:param order: (Optional) Sort order by the `created_at` timestamp
of the objects. `asc` for ascending order and `desc` for descending order.
:param after: (Optional) A cursor for use in pagination. `after` is
an object ID that defines your place in the list.
:param before: (Optional) A cursor for use in pagination. `before`
is an object ID that defines your place in the list.
:param filter: (Optional) Filter by file status to only return files
with the specified status.
:returns: A VectorStoreListFilesResponse containing the list of files.
parameters:
- name: vector_store_id
description: >-
The ID of the vector store to list files from.
required: true
schema:
type: string
in: path
- name: limit
description: >-
(Optional) A limit on the number of objects to be returned. Limit can
range between 1 and 100, and the default is 20.
required: false
schema:
type: integer
in: query
- name: order
description: >-
(Optional) Sort order by the `created_at` timestamp of the objects. `asc`
for ascending order and `desc` for descending order.
required: false
schema:
type: string
in: query
- name: after
description: >-
(Optional) A cursor for use in pagination. `after` is an object ID that
defines your place in the list.
required: false
schema:
type: string
in: query
- name: before
description: >-
(Optional) A cursor for use in pagination. `before` is an object ID that
defines your place in the list.
required: false
schema:
type: string
in: query
- name: filter
description: >-
(Optional) Filter by file status to only return files with the specified
status.
required: false
schema:
id: Union
in: query
deprecated: false
post:
responses:
'200':
description: >-
A VectorStoreFileObject representing the attached file.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Attach a file to a vector store.
description: >-
Attach a file to a vector store.
:param vector_store_id: The ID of the vector store to attach the file to.
:param file_id: The ID of the file to attach to the vector store.
:param attributes: The key-value attributes stored with the file,
which can be used for filtering.
:param chunking_strategy: The chunking strategy to use for the file.
:returns: A VectorStoreFileObject representing the attached file.
parameters:
- name: vector_store_id
description: >-
The ID of the vector store to attach the file to.
required: true
schema:
type: string
in: path
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiAttachFileToVectorStoreRequest'
required: true
deprecated: false
/v1/vector_stores/{vector_store_id}/files/{file_id}:
get:
responses:
'200':
description: >-
A VectorStoreFileObject representing the file.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Retrieves a vector store file.
description: >-
Retrieves a vector store file.
:param vector_store_id: The ID of the vector store containing the file to
retrieve.
:param file_id: The ID of the file to retrieve.
:returns: A VectorStoreFileObject representing the file.
parameters:
- name: vector_store_id
description: >-
The ID of the vector store containing the file to retrieve.
required: true
schema:
type: string
in: path
- name: file_id
description: The ID of the file to retrieve.
required: true
schema:
type: string
in: path
deprecated: false
post:
responses:
'200':
description: >-
A VectorStoreFileObject representing the updated file.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileObject'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Updates a vector store file.
description: >-
Updates a vector store file.
:param vector_store_id: The ID of the vector store containing the file to
update.
:param file_id: The ID of the file to update.
:param attributes: The updated key-value attributes to store with
the file.
:returns: A VectorStoreFileObject representing the updated file.
parameters:
- name: vector_store_id
description: >-
The ID of the vector store containing the file to update.
required: true
schema:
type: string
in: path
- name: file_id
description: The ID of the file to update.
required: true
schema:
type: string
in: path
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiUpdateVectorStoreFileRequest'
required: true
deprecated: false
delete:
responses:
'200':
description: >-
A VectorStoreFileDeleteResponse indicating the deletion status.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileDeleteResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Delete a vector store file.
description: >-
Delete a vector store file.
:param vector_store_id: The ID of the vector store containing the file to
delete.
:param file_id: The ID of the file to delete.
:returns: A VectorStoreFileDeleteResponse indicating the deletion
status.
parameters:
- name: vector_store_id
description: >-
The ID of the vector store containing the file to delete.
required: true
schema:
type: string
in: path
- name: file_id
description: The ID of the file to delete.
required: true
schema:
type: string
in: path
deprecated: false
/v1/vector_stores/{vector_store_id}/files/{file_id}/content:
get:
responses:
'200':
description: >-
A list of InterleavedContent representing the file contents.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileContentsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: >-
Retrieves the contents of a vector store file.
description: >-
Retrieves the contents of a vector store file.
:param vector_store_id: The ID of the vector store containing the file to
retrieve.
:param file_id: The ID of the file to retrieve.
:returns: A list of InterleavedContent representing the file contents.
parameters:
- name: vector_store_id
description: >-
The ID of the vector store containing the file to retrieve.
required: true
schema:
type: string
in: path
- name: file_id
description: The ID of the file to retrieve.
required: true
schema:
type: string
in: path
deprecated: false
/v1/vector_stores/{vector_store_id}/search:
post:
responses:
'200':
description: >-
A VectorStoreSearchResponse containing the search results.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreSearchResponsePage'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorIO
summary: Search for chunks in a vector store.
description: >-
Search for chunks in a vector store.
Searches a vector store for relevant chunks based on a query and optional
file attribute filters.
:param vector_store_id: The ID of the vector store to search.
:param query: The query string or array for performing the search.
:param filters: Filters based on file attributes to narrow the search
results.
:param max_num_results: Maximum number of results to return (1 to
50 inclusive, default 10).
:param ranking_options: Ranking options for fine-tuning the search
results.
:param rewrite_query: Whether to rewrite the natural language query
for vector search (default false)
:param search_mode: The search mode to use - "keyword", "vector",
or "hybrid" (default "vector")
:returns: A VectorStoreSearchResponse containing the search results.
parameters:
- name: vector_store_id
description: The ID of the vector store to search.
required: true
schema:
type: string
in: path
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiSearchVectorStoreRequest'
required: true
deprecated: false
/v1/version:
get:
responses:
'200':
description: >-
Version information containing the service version number.
content:
application/json:
schema:
$ref: '#/components/schemas/VersionInfo'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inspect
summary: Get version.
description: >-
Get version.
Get the version of the service.
:returns: Version information containing the service version number.
parameters: []
deprecated: false
/v1beta/datasetio/append-rows/{dataset_id}:
post:
tags:
- V1Beta
summary: Append rows to a dataset.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: append_rows_v1beta_datasetio_append_rows__dataset_id__post
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
- name: dataset_id
in: path
required: true
schema:
type: string
description: 'Path parameter: dataset_id'
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1beta/datasetio/iterrows/{dataset_id}:
get:
tags:
- V1Beta
summary: Get a paginated list of rows from a dataset.
description: Query endpoint for proper schema generation.
operationId: iterrows_v1beta_datasetio_iterrows__dataset_id__get
parameters:
- name: limit
in: query
required: true
schema:
type: integer
title: Limit
- name: start_index
in: query
required: true
schema:
type: integer
title: Start Index
- name: dataset_id
in: path
required: true
schema:
type: string
title: Dataset Id
responses:
'200':
description: A PaginatedResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/PaginatedResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1beta/datasets:
get:
tags:
- V1Beta
summary: List all datasets.
description: Response-only endpoint for proper schema generation.
operationId: list_datasets_v1beta_datasets_get
responses:
'200':
description: A ListDatasetsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListDatasetsResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
post:
tags:
- V1Beta
summary: Register a new dataset.
description: Typed endpoint for proper schema generation.
operationId: register_dataset_v1beta_datasets_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/__main_____datasets_Request'
required: true
responses:
'200':
description: A Dataset.
content:
application/json:
schema:
$ref: '#/components/schemas/Dataset'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1beta/datasets/{dataset_id}:
delete:
tags:
- V1Beta
summary: Unregister a dataset by its ID.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: unregister_dataset_v1beta_datasets__dataset_id__delete
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
- name: dataset_id
in: path
required: true
schema:
type: string
description: 'Path parameter: dataset_id'
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1Beta
summary: Get a dataset by its ID.
description: Query endpoint for proper schema generation.
operationId: get_dataset_v1beta_datasets__dataset_id__get
parameters:
- name: dataset_id
in: path
required: true
schema:
type: string
title: Dataset Id
responses:
'200':
description: A Dataset.
content:
application/json:
schema:
$ref: '#/components/schemas/Dataset'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1alpha/agents:
get:
tags:
- V1Alpha
summary: List all agents.
description: Query endpoint for proper schema generation.
operationId: list_agents_v1alpha_agents_get
parameters:
- name: limit
in: query
required: true
schema:
type: integer
title: Limit
- name: start_index
in: query
required: true
schema:
type: integer
title: Start Index
responses:
'200':
description: A PaginatedResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/PaginatedResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1Alpha
summary: Create an agent with the given configuration.
description: Typed endpoint for proper schema generation.
operationId: create_agent_v1alpha_agents_post
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/AgentConfig'
responses:
'200':
description: An AgentCreateResponse with the agent ID.
content:
application/json:
schema:
$ref: '#/components/schemas/AgentCreateResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1alpha/agents/{agent_id}:
delete:
tags:
- V1Alpha
summary: Delete an agent by its ID and its associated sessions and turns.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: delete_agent_v1alpha_agents__agent_id__delete
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
- name: agent_id
in: path
required: true
schema:
type: string
description: The ID of the agent to delete.
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1Alpha
summary: Describe an agent by its ID.
description: Query endpoint for proper schema generation.
operationId: get_agent_v1alpha_agents__agent_id__get
parameters:
- name: agent_id
in: path
required: true
schema:
type: string
title: Agent Id
description: ID of the agent.
responses:
'200':
description: An Agent of the agent.
content:
application/json:
schema:
$ref: '#/components/schemas/Agent'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1alpha/agents/{agent_id}/session:
post:
tags:
- V1Alpha
summary: Create a new session for an agent.
description: Typed endpoint for proper schema generation.
operationId: create_agent_session_v1alpha_agents__agent_id__session_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/__main_____agents_agent_id_session_Request'
required: true
responses:
'200':
description: An AgentSessionCreateResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/AgentSessionCreateResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
parameters:
- name: agent_id
in: path
required: true
schema:
type: string
description: The ID of the agent to create the session for.
/v1alpha/agents/{agent_id}/session/{session_id}:
delete:
tags:
- V1Alpha
summary: Delete an agent session by its ID and its associated turns.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: delete_agents_session_v1alpha_agents__agent_id__session__session_id__delete
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
- name: session_id
in: path
required: true
schema:
type: string
description: The ID of the session to delete.
- name: agent_id
in: path
required: true
schema:
type: string
description: The ID of the agent to delete the session for.
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1Alpha
summary: Retrieve an agent session by its ID.
description: Query endpoint for proper schema generation.
operationId: get_agents_session_v1alpha_agents__agent_id__session__session_id__get
parameters:
- name: turn_ids
in: query
required: true
schema:
type: string
title: Turn Ids
- name: session_id
in: path
required: true
schema:
type: string
title: Session Id
description: The ID of the session to get.
- name: agent_id
in: path
required: true
schema:
type: string
title: Agent Id
description: The ID of the agent to get the session for.
responses:
'200':
description: A Session.
content:
application/json:
schema:
$ref: '#/components/schemas/Session'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1alpha/agents/{agent_id}/session/{session_id}/turn:
post:
tags:
- V1Alpha
summary: Create a new turn for an agent.
description: Typed endpoint for proper schema generation.
operationId: create_agent_turn_v1alpha_agents__agent_id__session__session_id__turn_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/__main_____agents_agent_id_session_session_id_turn_Request'
required: true
responses:
'200':
description: If stream=False, returns a Turn object.
content:
application/json:
schema:
$ref: '#/components/schemas/Turn'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
parameters:
- name: agent_id
in: path
required: true
schema:
type: string
description: The ID of the agent to create the turn for.
- name: session_id
in: path
required: true
schema:
type: string
description: The ID of the session to create the turn for.
/v1alpha/agents/{agent_id}/session/{session_id}/turn/{turn_id}:
get:
tags:
- V1Alpha
summary: Retrieve an agent turn by its ID.
description: Query endpoint for proper schema generation.
operationId: get_agents_turn_v1alpha_agents__agent_id__session__session_id__turn__turn_id__get
parameters:
- name: agent_id
in: path
required: true
schema:
type: string
title: Agent Id
description: The ID of the agent to get the turn for.
- name: session_id
in: path
required: true
schema:
type: string
title: Session Id
description: The ID of the session to get the turn for.
- name: turn_id
in: path
required: true
schema:
type: string
title: Turn Id
description: The ID of the turn to get.
responses:
'200':
description: A Turn.
content:
application/json:
schema:
$ref: '#/components/schemas/Turn'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1alpha/agents/{agent_id}/session/{session_id}/turn/{turn_id}/resume:
post:
tags:
- V1Alpha
summary: Resume an agent turn with executed tool call responses.
description: Typed endpoint for proper schema generation.
operationId: resume_agent_turn_v1alpha_agents__agent_id__session__session_id__turn__turn_id__resume_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/__main_____agents_agent_id_session_session_id_turn_turn_id_resume_Request'
required: true
responses:
'200':
description: A Turn object if stream is False, otherwise an AsyncIterator of AgentTurnResponseStreamChunk objects.
content:
application/json:
schema:
$ref: '#/components/schemas/Turn'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
parameters:
- name: agent_id
in: path
required: true
schema:
type: string
description: The ID of the agent to resume.
- name: session_id
in: path
required: true
schema:
type: string
description: The ID of the session to resume.
- name: turn_id
in: path
required: true
schema:
type: string
description: The ID of the turn to resume.
/v1alpha/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id}:
get:
tags:
- V1Alpha
summary: Retrieve an agent step by its ID.
description: Query endpoint for proper schema generation.
operationId: get_agents_step_v1alpha_agents__agent_id__session__session_id__turn__turn_id__step__step_id__get
parameters:
- name: agent_id
in: path
required: true
schema:
type: string
title: Agent Id
description: The ID of the agent to get the step for.
- name: session_id
in: path
required: true
schema:
type: string
title: Session Id
description: The ID of the session to get the step for.
- name: turn_id
in: path
required: true
schema:
type: string
title: Turn Id
description: The ID of the turn to get the step for.
- name: step_id
in: path
required: true
schema:
type: string
title: Step Id
description: The ID of the step to get.
responses:
'200':
description: An AgentStepResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/AgentStepResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1alpha/agents/{agent_id}/sessions:
get:
tags:
- V1Alpha
summary: List all session(s) of a given agent.
description: Query endpoint for proper schema generation.
operationId: list_agent_sessions_v1alpha_agents__agent_id__sessions_get
parameters:
- name: limit
in: query
required: true
schema:
type: integer
title: Limit
- name: start_index
in: query
required: true
schema:
type: integer
title: Start Index
- name: agent_id
in: path
required: true
schema:
type: string
title: Agent Id
description: The ID of the agent to list sessions for.
responses:
'200':
description: A PaginatedResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/PaginatedResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1alpha/eval/benchmarks:
get:
tags:
- V1Alpha
summary: List all benchmarks.
description: Response-only endpoint for proper schema generation.
operationId: list_benchmarks_v1alpha_eval_benchmarks_get
responses:
'200':
description: A ListBenchmarksResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListBenchmarksResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1Alpha
summary: Register a benchmark.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: register_benchmark_v1alpha_eval_benchmarks_post
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1alpha/eval/benchmarks/{benchmark_id}:
delete:
tags:
- V1Alpha
summary: Unregister a benchmark.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: unregister_benchmark_v1alpha_eval_benchmarks__benchmark_id__delete
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
- name: benchmark_id
in: path
required: true
schema:
type: string
description: The ID of the benchmark to unregister.
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1Alpha
summary: Get a benchmark by its ID.
description: Query endpoint for proper schema generation.
operationId: get_benchmark_v1alpha_eval_benchmarks__benchmark_id__get
parameters:
- name: benchmark_id
in: path
required: true
schema:
type: string
title: Benchmark Id
description: The ID of the benchmark to get.
responses:
'200':
description: A Benchmark.
content:
application/json:
schema:
$ref: '#/components/schemas/Benchmark'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1alpha/eval/benchmarks/{benchmark_id}/evaluations:
post:
tags:
- V1Alpha
summary: Evaluate a list of rows on a benchmark.
description: Typed endpoint for proper schema generation.
operationId: evaluate_rows_v1alpha_eval_benchmarks__benchmark_id__evaluations_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/BenchmarkConfig'
required: true
responses:
'200':
description: EvaluateResponse object containing generations and scores.
content:
application/json:
schema:
$ref: '#/components/schemas/EvaluateResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
parameters:
- name: benchmark_id
in: path
required: true
schema:
type: string
description: The ID of the benchmark to run the evaluation on.
/v1alpha/eval/benchmarks/{benchmark_id}/jobs:
post:
tags:
- V1Alpha
summary: Run an evaluation on a benchmark.
description: Typed endpoint for proper schema generation.
operationId: run_eval_v1alpha_eval_benchmarks__benchmark_id__jobs_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/BenchmarkConfig'
required: true
responses:
'200':
description: The job that was created to run the evaluation.
content:
application/json:
schema:
$ref: '#/components/schemas/Job'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
parameters:
- name: benchmark_id
in: path
required: true
schema:
type: string
description: The ID of the benchmark to run the evaluation on.
/v1alpha/eval/benchmarks/{benchmark_id}/jobs/{job_id}:
delete:
tags:
- V1Alpha
summary: Cancel a job.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: job_cancel_v1alpha_eval_benchmarks__benchmark_id__jobs__job_id__delete
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
- name: benchmark_id
in: path
required: true
schema:
type: string
description: The ID of the benchmark to run the evaluation on.
- name: job_id
in: path
required: true
schema:
type: string
description: The ID of the job to cancel.
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1Alpha
summary: Get the status of a job.
description: Query endpoint for proper schema generation.
operationId: job_status_v1alpha_eval_benchmarks__benchmark_id__jobs__job_id__get
parameters:
- name: benchmark_id
in: path
required: true
schema:
type: string
title: Benchmark Id
description: The ID of the benchmark to run the evaluation on.
- name: job_id
in: path
required: true
schema:
type: string
title: Job Id
description: The ID of the job to get the status of.
responses:
'200':
description: The status of the evaluation job.
content:
application/json:
schema:
$ref: '#/components/schemas/Job'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1alpha/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result:
get:
tags:
- V1Alpha
summary: Get the result of a job.
description: Query endpoint for proper schema generation.
operationId: job_result_v1alpha_eval_benchmarks__benchmark_id__jobs__job_id__result_get
parameters:
- name: benchmark_id
in: path
required: true
schema:
type: string
title: Benchmark Id
description: The ID of the benchmark to run the evaluation on.
- name: job_id
in: path
required: true
schema:
type: string
title: Job Id
description: The ID of the job to get the result of.
responses:
'200':
description: The result of the job.
content:
application/json:
schema:
$ref: '#/components/schemas/EvaluateResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1alpha/inference/rerank:
post:
tags:
- V1Alpha
summary: Rerank a list of documents based on their relevance to a query.
description: Typed endpoint for proper schema generation.
operationId: rerank_v1alpha_inference_rerank_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_inference_rerank_Request'
required: true
responses:
'200':
description: RerankResponse with indices sorted by relevance score (descending).
content:
application/json:
schema:
$ref: '#/components/schemas/RerankResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1alpha/post-training/job/artifacts:
get:
tags:
- V1Alpha
summary: Get the artifacts of a training job.
description: Query endpoint for proper schema generation.
operationId: get_training_job_artifacts_v1alpha_post_training_job_artifacts_get
parameters:
- name: job_uuid
in: query
required: true
schema:
type: string
title: Job Uuid
responses:
'200':
description: A PostTrainingJobArtifactsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/PostTrainingJobArtifactsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1alpha/post-training/job/cancel:
post:
tags:
- V1Alpha
summary: Cancel a training job.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: cancel_training_job_v1alpha_post_training_job_cancel_post
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1alpha/post-training/job/status:
get:
tags:
- V1Alpha
summary: Get the status of a training job.
description: Query endpoint for proper schema generation.
operationId: get_training_job_status_v1alpha_post_training_job_status_get
parameters:
- name: job_uuid
in: query
required: true
schema:
type: string
title: Job Uuid
responses:
'200':
description: A PostTrainingJobStatusResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/PostTrainingJobStatusResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1alpha/post-training/jobs:
get:
tags:
- V1Alpha
summary: Get all training jobs.
description: Response-only endpoint for proper schema generation.
operationId: get_training_jobs_v1alpha_post_training_jobs_get
responses:
'200':
description: A ListPostTrainingJobsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListPostTrainingJobsResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1alpha/post-training/preference-optimize:
post:
tags:
- V1Alpha
summary: Run preference optimization of a model.
description: Typed endpoint for proper schema generation.
operationId: preference_optimize_v1alpha_post_training_preference_optimize_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/DPOAlignmentConfig'
required: true
responses:
'200':
description: A PostTrainingJob.
content:
application/json:
schema:
$ref: '#/components/schemas/PostTrainingJob'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1alpha/post-training/supervised-fine-tune:
post:
tags:
- V1Alpha
summary: Run supervised fine-tuning of a model.
description: Typed endpoint for proper schema generation.
operationId: supervised_fine_tune_v1alpha_post_training_supervised_fine_tune_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/TrainingConfig'
required: true
responses:
'200':
description: A PostTrainingJob.
content:
application/json:
schema:
$ref: '#/components/schemas/PostTrainingJob'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/batches:
get:
tags:
- V1
summary: List all batches for the current user.
description: Query endpoint for proper schema generation.
operationId: list_batches_v1_batches_get
parameters:
- name: after
in: query
required: true
schema:
type: string
title: After
- name: limit
in: query
required: false
schema:
type: integer
default: 20
title: Limit
responses:
'200':
description: A list of batch objects.
content:
application/json:
schema:
$ref: '#/components/schemas/ListBatchesResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1
summary: Create a new batch for processing multiple API requests.
description: Typed endpoint for proper schema generation.
operationId: create_batch_v1_batches_post
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/_batches_Request'
responses:
'200':
description: The created batch object.
content:
application/json:
schema:
$ref: '#/components/schemas/Batch'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/batches/{batch_id}:
get:
tags:
- V1
summary: Retrieve information about a specific batch.
description: Query endpoint for proper schema generation.
operationId: retrieve_batch_v1_batches__batch_id__get
parameters:
- name: batch_id
in: path
required: true
schema:
type: string
title: Batch Id
description: The ID of the batch to retrieve.
responses:
'200':
description: The batch object.
content:
application/json:
schema:
$ref: '#/components/schemas/Batch'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/batches/{batch_id}/cancel:
post:
tags:
- V1
summary: Cancel a batch that is in progress.
description: Typed endpoint for proper schema generation.
operationId: cancel_batch_v1_batches__batch_id__cancel_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_batches_batch_id_cancel_Request'
required: true
responses:
'200':
description: The updated batch object.
content:
application/json:
schema:
$ref: '#/components/schemas/Batch'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
parameters:
- name: batch_id
in: path
required: true
schema:
type: string
description: The ID of the batch to cancel.
/v1/chat/completions:
get:
tags:
- V1
summary: List chat completions.
description: Query endpoint for proper schema generation.
operationId: list_chat_completions_v1_chat_completions_get
parameters:
- name: after
in: query
required: true
schema:
type: string
title: After
- name: model
in: query
required: true
schema:
type: string
title: Model
- name: limit
in: query
required: false
schema:
type: integer
default: 20
title: Limit
- name: order
in: query
required: false
schema:
$ref: '#/components/schemas/Order'
default: desc
responses:
'200':
description: A ListOpenAIChatCompletionResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListOpenAIChatCompletionResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1
summary: Create chat completions.
description: Typed endpoint for proper schema generation.
operationId: openai_chat_completion_v1_chat_completions_post
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIChatCompletionRequestWithExtraBody'
responses:
'200':
description: An OpenAIChatCompletion.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIChatCompletion'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/chat/completions/{completion_id}:
get:
tags:
- V1
summary: Get chat completion.
description: Query endpoint for proper schema generation.
operationId: get_chat_completion_v1_chat_completions__completion_id__get
parameters:
- name: completion_id
in: path
required: true
schema:
type: string
title: Completion Id
description: ID of the chat completion.
responses:
'200':
description: A OpenAICompletionWithInputMessages.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAICompletionWithInputMessages'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/completions:
post:
tags:
- V1
summary: Create completion.
description: Typed endpoint for proper schema generation.
operationId: openai_completion_v1_completions_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAICompletionRequestWithExtraBody'
required: true
responses:
'200':
description: An OpenAICompletion.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAICompletion'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/conversations:
post:
tags:
- V1
summary: Create a conversation.
description: Typed endpoint for proper schema generation.
operationId: create_conversation_v1_conversations_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_conversations_Request'
required: true
responses:
'200':
description: The created conversation object.
content:
application/json:
schema:
$ref: '#/components/schemas/Conversation'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/conversations/{conversation_id}:
delete:
tags:
- V1
summary: Delete a conversation.
description: Query endpoint for proper schema generation.
operationId: openai_delete_conversation_v1_conversations__conversation_id__delete
parameters:
- name: conversation_id
in: path
required: true
schema:
type: string
title: Conversation Id
description: The conversation identifier.
responses:
'200':
description: The deleted conversation resource.
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationDeletedResource'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1
summary: Retrieve a conversation.
description: Query endpoint for proper schema generation.
operationId: get_conversation_v1_conversations__conversation_id__get
parameters:
- name: conversation_id
in: path
required: true
schema:
type: string
title: Conversation Id
description: The conversation identifier.
responses:
'200':
description: The conversation object.
content:
application/json:
schema:
$ref: '#/components/schemas/Conversation'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1
summary: Update a conversation.
description: Typed endpoint for proper schema generation.
operationId: update_conversation_v1_conversations__conversation_id__post
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/_conversations_conversation_id_Request'
responses:
'200':
description: The updated conversation object.
content:
application/json:
schema:
$ref: '#/components/schemas/Conversation'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
parameters:
- name: conversation_id
in: path
required: true
schema:
type: string
description: The conversation identifier.
/v1/conversations/{conversation_id}/items:
get:
tags:
- V1
summary: List items.
description: Query endpoint for proper schema generation.
operationId: list_items_v1_conversations__conversation_id__items_get
parameters:
- name: after
in: query
required: true
schema:
type: string
title: After
- name: include
in: query
required: true
schema:
$ref: '#/components/schemas/ConversationItemInclude'
- name: limit
in: query
required: true
schema:
type: integer
title: Limit
- name: order
in: query
required: true
schema:
type: string
title: Order
- name: conversation_id
in: path
required: true
schema:
type: string
title: Conversation Id
description: The conversation identifier.
responses:
'200':
description: List of conversation items.
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationItemList'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1
summary: Create items.
description: Typed endpoint for proper schema generation.
operationId: add_items_v1_conversations__conversation_id__items_post
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/_conversations_conversation_id_items_Request'
responses:
'200':
description: List of created items.
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationItemList'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
parameters:
- name: conversation_id
in: path
required: true
schema:
type: string
description: The conversation identifier.
/v1/conversations/{conversation_id}/items/{item_id}:
delete:
tags:
- V1
summary: Delete an item.
description: Query endpoint for proper schema generation.
operationId: openai_delete_conversation_item_v1_conversations__conversation_id__items__item_id__delete
parameters:
- name: conversation_id
in: path
required: true
schema:
type: string
title: Conversation Id
description: The conversation identifier.
- name: item_id
in: path
required: true
schema:
type: string
title: Item Id
description: The item identifier.
responses:
'200':
description: The deleted item resource.
content:
application/json:
schema:
$ref: '#/components/schemas/ConversationItemDeletedResource'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1
summary: Retrieve an item.
description: Query endpoint for proper schema generation.
operationId: retrieve_v1_conversations__conversation_id__items__item_id__get
parameters:
- name: conversation_id
in: path
required: true
schema:
type: string
title: Conversation Id
description: The conversation identifier.
- name: item_id
in: path
required: true
schema:
type: string
title: Item Id
description: The item identifier.
responses:
'200':
description: The conversation item.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIResponseMessage'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/embeddings:
post:
tags:
- V1
summary: Create embeddings.
description: Typed endpoint for proper schema generation.
operationId: openai_embeddings_v1_embeddings_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIEmbeddingsRequestWithExtraBody'
required: true
responses:
'200':
description: An OpenAIEmbeddingsResponse containing the embeddings.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIEmbeddingsResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/files:
get:
tags:
- V1
summary: List files.
description: Query endpoint for proper schema generation.
operationId: openai_list_files_v1_files_get
parameters:
- name: after
in: query
required: true
schema:
type: string
title: After
- name: purpose
in: query
required: true
schema:
$ref: '#/components/schemas/OpenAIFilePurpose'
- name: limit
in: query
required: false
schema:
type: integer
default: 10000
title: Limit
- name: order
in: query
required: false
schema:
$ref: '#/components/schemas/Order'
default: desc
responses:
'200':
description: An ListOpenAIFileResponse containing the list of files.
content:
application/json:
schema:
$ref: '#/components/schemas/ListOpenAIFileResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1
summary: Upload file.
description: Response-only endpoint for proper schema generation.
operationId: openai_upload_file_v1_files_post
responses:
'200':
description: An OpenAIFileObject representing the uploaded file.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIFileObject'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/files/{file_id}:
delete:
tags:
- V1
summary: Delete file.
description: Query endpoint for proper schema generation.
operationId: openai_delete_file_v1_files__file_id__delete
parameters:
- name: file_id
in: path
required: true
schema:
type: string
title: File Id
description: The ID of the file to use for this request.
responses:
'200':
description: An OpenAIFileDeleteResponse indicating successful deletion.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIFileDeleteResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1
summary: Retrieve file.
description: Query endpoint for proper schema generation.
operationId: openai_retrieve_file_v1_files__file_id__get
parameters:
- name: file_id
in: path
required: true
schema:
type: string
title: File Id
description: The ID of the file to use for this request.
responses:
'200':
description: An OpenAIFileObject containing file information.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIFileObject'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/files/{file_id}/content:
get:
tags:
- V1
summary: Retrieve file content.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: openai_retrieve_file_content_v1_files__file_id__content_get
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
- name: file_id
in: path
required: true
schema:
type: string
description: The ID of the file to use for this request.
responses:
'200':
description: The raw file content as a binary response.
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/health:
get:
tags:
- V1
summary: Get health status.
description: Response-only endpoint for proper schema generation.
operationId: health_v1_health_get
responses:
'200':
description: Health information indicating if the service is operational.
content:
application/json:
schema:
$ref: '#/components/schemas/HealthInfo'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/inspect/routes:
get:
tags:
- V1
summary: List routes.
description: Response-only endpoint for proper schema generation.
operationId: list_routes_v1_inspect_routes_get
responses:
'200':
description: Response containing information about all available routes.
content:
application/json:
schema:
$ref: '#/components/schemas/ListRoutesResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/models:
get:
tags:
- V1
summary: List all models.
description: Response-only endpoint for proper schema generation.
operationId: list_models_v1_models_get
responses:
'200':
description: A ListModelsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListModelsResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
post:
tags:
- V1
summary: Register model.
description: Typed endpoint for proper schema generation.
operationId: register_model_v1_models_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_models_Request'
required: true
responses:
'200':
description: A Model.
content:
application/json:
schema:
$ref: '#/components/schemas/Model'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/models/{model_id}:
delete:
tags:
- V1
summary: Unregister model.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: unregister_model_v1_models__model_id__delete
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
- name: model_id
in: path
required: true
schema:
type: string
description: 'Path parameter: model_id'
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1
summary: Get model.
description: Query endpoint for proper schema generation.
operationId: get_model_v1_models__model_id__get
parameters:
- name: model_id
in: path
required: true
schema:
type: string
title: Model Id
responses:
'200':
description: A Model.
content:
application/json:
schema:
$ref: '#/components/schemas/Model'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/moderations:
post:
tags:
- V1
summary: Create moderation.
description: Typed endpoint for proper schema generation.
operationId: run_moderation_v1_moderations_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_moderations_Request'
required: true
responses:
'200':
description: A moderation object.
content:
application/json:
schema:
$ref: '#/components/schemas/ModerationObject'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/prompts:
get:
tags:
- V1
summary: List all prompts.
description: Response-only endpoint for proper schema generation.
operationId: list_prompts_v1_prompts_get
responses:
'200':
description: A ListPromptsResponse containing all prompts.
content:
application/json:
schema:
$ref: '#/components/schemas/ListPromptsResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
post:
tags:
- V1
summary: Create prompt.
description: Typed endpoint for proper schema generation.
operationId: create_prompt_v1_prompts_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_prompts_Request'
required: true
responses:
'200':
description: The created Prompt resource.
content:
application/json:
schema:
$ref: '#/components/schemas/Prompt'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/prompts/{prompt_id}:
delete:
tags:
- V1
summary: Delete prompt.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: delete_prompt_v1_prompts__prompt_id__delete
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
- name: prompt_id
in: path
required: true
schema:
type: string
description: The identifier of the prompt to delete.
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1
summary: Get prompt.
description: Query endpoint for proper schema generation.
operationId: get_prompt_v1_prompts__prompt_id__get
parameters:
- name: version
in: query
required: true
schema:
type: integer
title: Version
- name: prompt_id
in: path
required: true
schema:
type: string
title: Prompt Id
description: The identifier of the prompt to get.
responses:
'200':
description: A Prompt resource.
content:
application/json:
schema:
$ref: '#/components/schemas/Prompt'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1
summary: Update prompt.
description: Typed endpoint for proper schema generation.
operationId: update_prompt_v1_prompts__prompt_id__post
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/_prompts_prompt_id_Request'
responses:
'200':
description: The updated Prompt resource with incremented version.
content:
application/json:
schema:
$ref: '#/components/schemas/Prompt'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
parameters:
- name: prompt_id
in: path
required: true
schema:
type: string
description: The identifier of the prompt to update.
/v1/prompts/{prompt_id}/set-default-version:
post:
tags:
- V1
summary: Set prompt version.
description: Typed endpoint for proper schema generation.
operationId: set_default_version_v1_prompts__prompt_id__set_default_version_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_prompts_prompt_id_set_default_version_Request'
required: true
responses:
'200':
description: The prompt with the specified version now set as default.
content:
application/json:
schema:
$ref: '#/components/schemas/Prompt'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
parameters:
- name: prompt_id
in: path
required: true
schema:
type: string
description: The identifier of the prompt.
/v1/prompts/{prompt_id}/versions:
get:
tags:
- V1
summary: List prompt versions.
description: Query endpoint for proper schema generation.
operationId: list_prompt_versions_v1_prompts__prompt_id__versions_get
parameters:
- name: prompt_id
in: path
required: true
schema:
type: string
title: Prompt Id
description: The identifier of the prompt to list versions for.
responses:
'200':
description: A ListPromptsResponse containing all versions of the prompt.
content:
application/json:
schema:
$ref: '#/components/schemas/ListPromptsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/providers:
get:
tags:
- V1
summary: List providers.
description: Response-only endpoint for proper schema generation.
operationId: list_providers_v1_providers_get
responses:
'200':
description: A ListProvidersResponse containing information about all providers.
content:
application/json:
schema:
$ref: '#/components/schemas/ListProvidersResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/providers/{provider_id}:
get:
tags:
- V1
summary: Get provider.
description: Query endpoint for proper schema generation.
operationId: inspect_provider_v1_providers__provider_id__get
parameters:
- name: provider_id
in: path
required: true
schema:
type: string
title: Provider Id
description: The ID of the provider to inspect.
responses:
'200':
description: A ProviderInfo object containing the provider's details.
content:
application/json:
schema:
$ref: '#/components/schemas/ProviderInfo'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/responses:
get:
tags:
- V1
summary: List all responses.
description: Query endpoint for proper schema generation.
operationId: list_openai_responses_v1_responses_get
parameters:
- name: after
in: query
required: true
schema:
type: string
title: After
- name: model
in: query
required: true
schema:
type: string
title: Model
- name: limit
in: query
required: false
schema:
type: integer
default: 50
title: Limit
- name: order
in: query
required: false
schema:
$ref: '#/components/schemas/Order'
default: desc
responses:
'200':
description: A ListOpenAIResponseObject.
content:
application/json:
schema:
$ref: '#/components/schemas/ListOpenAIResponseObject'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1
summary: Create a model response.
description: Typed endpoint for proper schema generation.
operationId: create_openai_response_v1_responses_post
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/_responses_Request'
responses:
'200':
description: An OpenAIResponseObject.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIResponseObject'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/responses/{response_id}:
delete:
tags:
- V1
summary: Delete a response.
description: Query endpoint for proper schema generation.
operationId: delete_openai_response_v1_responses__response_id__delete
parameters:
- name: response_id
in: path
required: true
schema:
type: string
title: Response Id
description: The ID of the OpenAI response to delete.
responses:
'200':
description: An OpenAIDeleteResponseObject
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIDeleteResponseObject'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1
summary: Get a model response.
description: Query endpoint for proper schema generation.
operationId: get_openai_response_v1_responses__response_id__get
parameters:
- name: response_id
in: path
required: true
schema:
type: string
title: Response Id
description: The ID of the OpenAI response to retrieve.
responses:
'200':
description: An OpenAIResponseObject.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIResponseObject'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/responses/{response_id}/input_items:
get:
tags:
- V1
summary: List input items.
description: Query endpoint for proper schema generation.
operationId: list_openai_response_input_items_v1_responses__response_id__input_items_get
parameters:
- name: after
in: query
required: true
schema:
type: string
title: After
- name: before
in: query
required: true
schema:
type: string
title: Before
- name: include
in: query
required: true
schema:
type: string
title: Include
- name: limit
in: query
required: false
schema:
type: integer
default: 20
title: Limit
- name: order
in: query
required: false
schema:
$ref: '#/components/schemas/Order'
default: desc
- name: response_id
in: path
required: true
schema:
type: string
title: Response Id
description: The ID of the response to retrieve input items for.
responses:
'200':
description: An ListOpenAIResponseInputItem.
content:
application/json:
schema:
$ref: '#/components/schemas/ListOpenAIResponseInputItem'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/safety/run-shield:
post:
tags:
- V1
summary: Run shield.
description: Typed endpoint for proper schema generation.
operationId: run_shield_v1_safety_run_shield_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_safety_run_shield_Request'
required: true
responses:
'200':
description: A RunShieldResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/RunShieldResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/scoring-functions:
get:
tags:
- V1
summary: List all scoring functions.
description: Response-only endpoint for proper schema generation.
operationId: list_scoring_functions_v1_scoring_functions_get
responses:
'200':
description: A ListScoringFunctionsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListScoringFunctionsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1
summary: Register a scoring function.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: register_scoring_function_v1_scoring_functions_post
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/scoring-functions/{scoring_fn_id}:
delete:
tags:
- V1
summary: Unregister a scoring function.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: unregister_scoring_function_v1_scoring_functions__scoring_fn_id__delete
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
- name: scoring_fn_id
in: path
required: true
schema:
type: string
description: 'Path parameter: scoring_fn_id'
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1
summary: Get a scoring function by its ID.
description: Query endpoint for proper schema generation.
operationId: get_scoring_function_v1_scoring_functions__scoring_fn_id__get
parameters:
- name: scoring_fn_id
in: path
required: true
schema:
type: string
title: Scoring Fn Id
responses:
'200':
description: A ScoringFn.
content:
application/json:
schema:
$ref: '#/components/schemas/ScoringFn'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/scoring/score:
post:
tags:
- V1
summary: Score a list of rows.
description: Typed endpoint for proper schema generation.
operationId: score_v1_scoring_score_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_scoring_score_Request'
required: true
responses:
'200':
description: A ScoreResponse object containing rows and aggregated results.
content:
application/json:
schema:
$ref: '#/components/schemas/ScoreResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/scoring/score-batch:
post:
tags:
- V1
summary: Score a batch of rows.
description: Typed endpoint for proper schema generation.
operationId: score_batch_v1_scoring_score_batch_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_scoring_score_batch_Request'
required: true
responses:
'200':
description: A ScoreBatchResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ScoreBatchResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/shields:
get:
tags:
- V1
summary: List all shields.
description: Response-only endpoint for proper schema generation.
operationId: list_shields_v1_shields_get
responses:
'200':
description: A ListShieldsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListShieldsResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
post:
tags:
- V1
summary: Register a shield.
description: Typed endpoint for proper schema generation.
operationId: register_shield_v1_shields_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_shields_Request'
required: true
responses:
'200':
description: A Shield.
content:
application/json:
schema:
$ref: '#/components/schemas/Shield'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/shields/{identifier}:
delete:
tags:
- V1
summary: Unregister a shield.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: unregister_shield_v1_shields__identifier__delete
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
- name: identifier
in: path
required: true
schema:
type: string
description: 'Path parameter: identifier'
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1
summary: Get a shield by its identifier.
description: Query endpoint for proper schema generation.
operationId: get_shield_v1_shields__identifier__get
parameters:
- name: identifier
in: path
required: true
schema:
type: string
title: Identifier
responses:
'200':
description: A Shield.
content:
application/json:
schema:
$ref: '#/components/schemas/Shield'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/tool-runtime/invoke:
post:
tags:
- V1
summary: Run a tool with the given arguments.
description: Typed endpoint for proper schema generation.
operationId: invoke_tool_v1_tool_runtime_invoke_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_tool_runtime_invoke_Request'
required: true
responses:
'200':
description: A ToolInvocationResult.
content:
application/json:
schema:
$ref: '#/components/schemas/ToolInvocationResult'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/tool-runtime/list-tools:
get:
tags:
- V1
summary: List all tools in the runtime.
description: Query endpoint for proper schema generation.
operationId: list_runtime_tools_v1_tool_runtime_list_tools_get
parameters:
- name: tool_group_id
in: query
required: true
schema:
type: string
title: Tool Group Id
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/URL'
responses:
'200':
description: A ListToolDefsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListToolDefsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/tool-runtime/rag-tool/insert:
post:
tags:
- V1
summary: Index documents so they can be used by the RAG system.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: rag_tool_insert_v1_tool_runtime_rag_tool_insert_post
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/tool-runtime/rag-tool/query:
post:
tags:
- V1
summary: Query the RAG system for context; typically invoked by the agent.
description: Typed endpoint for proper schema generation.
operationId: rag_tool_query_v1_tool_runtime_rag_tool_query_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_tool_runtime_rag_tool_query_Request'
required: true
responses:
'200':
description: RAGQueryResult containing the retrieved content and metadata
content:
application/json:
schema:
$ref: '#/components/schemas/RAGQueryResult'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/toolgroups:
get:
tags:
- V1
summary: List tool groups with optional provider.
description: Response-only endpoint for proper schema generation.
operationId: list_tool_groups_v1_toolgroups_get
responses:
'200':
description: A ListToolGroupsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListToolGroupsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1
summary: Register a tool group.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: register_tool_group_v1_toolgroups_post
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/toolgroups/{toolgroup_id}:
delete:
tags:
- V1
summary: Unregister a tool group.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: unregister_toolgroup_v1_toolgroups__toolgroup_id__delete
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
- name: toolgroup_id
in: path
required: true
schema:
type: string
description: 'Path parameter: toolgroup_id'
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1
summary: Get a tool group by its ID.
description: Query endpoint for proper schema generation.
operationId: get_tool_group_v1_toolgroups__toolgroup_id__get
parameters:
- name: toolgroup_id
in: path
required: true
schema:
type: string
title: Toolgroup Id
responses:
'200':
description: A ToolGroup.
content:
application/json:
schema:
$ref: '#/components/schemas/ToolGroup'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/tools:
get:
tags:
- V1
summary: List tools with optional tool group.
description: Query endpoint for proper schema generation.
operationId: list_tools_v1_tools_get
parameters:
- name: toolgroup_id
in: query
required: true
schema:
type: string
title: Toolgroup Id
responses:
'200':
description: A ListToolDefsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListToolDefsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/tools/{tool_name}:
get:
tags:
- V1
summary: Get a tool by its name.
description: Query endpoint for proper schema generation.
operationId: get_tool_v1_tools__tool_name__get
parameters:
- name: tool_name
in: path
required: true
schema:
type: string
title: Tool Name
responses:
'200':
description: A ToolDef.
content:
application/json:
schema:
$ref: '#/components/schemas/ToolDef'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/vector-io/insert:
post:
tags:
- V1
summary: Insert chunks into a vector database.
description: Generic endpoint - this would be replaced with actual implementation.
operationId: insert_chunks_v1_vector_io_insert_post
parameters:
- name: args
in: query
required: true
schema:
title: Args
- name: kwargs
in: query
required: true
schema:
title: Kwargs
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/vector-io/query:
post:
tags:
- V1
summary: Query chunks from a vector database.
description: Typed endpoint for proper schema generation.
operationId: query_chunks_v1_vector_io_query_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_vector_io_query_Request'
required: true
responses:
'200':
description: A QueryChunksResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/QueryChunksResponse'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
/v1/vector_stores:
get:
tags:
- V1
summary: Returns a list of vector stores.
description: Query endpoint for proper schema generation.
operationId: openai_list_vector_stores_v1_vector_stores_get
parameters:
- name: after
in: query
required: true
schema:
type: string
title: After
- name: before
in: query
required: true
schema:
type: string
title: Before
- name: limit
in: query
required: false
schema:
type: integer
default: 20
title: Limit
- name: order
in: query
required: false
schema:
type: string
default: desc
title: Order
responses:
'200':
description: A VectorStoreListResponse containing the list of vector stores.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreListResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1
summary: Creates a vector store.
description: Typed endpoint for proper schema generation.
operationId: openai_create_vector_store_v1_vector_stores_post
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAICreateVectorStoreRequestWithExtraBody'
responses:
'200':
description: A VectorStoreObject representing the created vector store.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreObject'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/vector_stores/{vector_store_id}:
delete:
tags:
- V1
summary: Delete a vector store.
description: Query endpoint for proper schema generation.
operationId: openai_delete_vector_store_v1_vector_stores__vector_store_id__delete
parameters:
- name: vector_store_id
in: path
required: true
schema:
type: string
title: Vector Store Id
description: The ID of the vector store to delete.
responses:
'200':
description: A VectorStoreDeleteResponse indicating the deletion status.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreDeleteResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1
summary: Retrieves a vector store.
description: Query endpoint for proper schema generation.
operationId: openai_retrieve_vector_store_v1_vector_stores__vector_store_id__get
parameters:
- name: vector_store_id
in: path
required: true
schema:
type: string
title: Vector Store Id
description: The ID of the vector store to retrieve.
responses:
'200':
description: A VectorStoreObject representing the vector store.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreObject'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1
summary: Updates a vector store.
description: Typed endpoint for proper schema generation.
operationId: openai_update_vector_store_v1_vector_stores__vector_store_id__post
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/_vector_stores_vector_store_id_Request'
responses:
'200':
description: A VectorStoreObject representing the updated vector store.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreObject'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
parameters:
- name: vector_store_id
in: path
required: true
schema:
type: string
description: The ID of the vector store to update.
/v1/vector_stores/{vector_store_id}/file_batches:
post:
tags:
- V1
summary: Create a vector store file batch.
description: Typed endpoint for proper schema generation.
operationId: openai_create_vector_store_file_batch_v1_vector_stores__vector_store_id__file_batches_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAICreateVectorStoreFileBatchRequestWithExtraBody'
required: true
responses:
'200':
description: A VectorStoreFileBatchObject representing the created file batch.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileBatchObject'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
parameters:
- name: vector_store_id
in: path
required: true
schema:
type: string
description: The ID of the vector store to create the file batch for.
/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}:
get:
tags:
- V1
summary: Retrieve a vector store file batch.
description: Query endpoint for proper schema generation.
operationId: openai_retrieve_vector_store_file_batch_v1_vector_stores__vector_store_id__file_batches__batch_id__get
parameters:
- name: batch_id
in: path
required: true
schema:
type: string
title: Batch Id
description: The ID of the file batch to retrieve.
- name: vector_store_id
in: path
required: true
schema:
type: string
title: Vector Store Id
description: The ID of the vector store containing the file batch.
responses:
'200':
description: A VectorStoreFileBatchObject representing the file batch.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileBatchObject'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel:
post:
tags:
- V1
summary: Cancels a vector store file batch.
description: Typed endpoint for proper schema generation.
operationId: openai_cancel_vector_store_file_batch_v1_vector_stores__vector_store_id__file_batches__batch_id__cancel_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_vector_stores_vector_store_id_file_batches_batch_id_cancel_Request'
required: true
responses:
'200':
description: A VectorStoreFileBatchObject representing the cancelled file batch.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileBatchObject'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
parameters:
- name: batch_id
in: path
required: true
schema:
type: string
description: The ID of the file batch to cancel.
- name: vector_store_id
in: path
required: true
schema:
type: string
description: The ID of the vector store containing the file batch.
/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}/files:
get:
tags:
- V1
summary: Returns a list of vector store files in a batch.
description: Query endpoint for proper schema generation.
operationId: openai_list_files_in_vector_store_file_batch_v1_vector_stores__vector_store_id__file_batches__batch_id__files_get
parameters:
- name: after
in: query
required: true
schema:
type: string
title: After
- name: before
in: query
required: true
schema:
type: string
title: Before
- name: filter
in: query
required: true
schema:
type: string
title: Filter
- name: limit
in: query
required: false
schema:
type: integer
default: 20
title: Limit
- name: order
in: query
required: false
schema:
type: string
default: desc
title: Order
- name: batch_id
in: path
required: true
schema:
type: string
title: Batch Id
description: The ID of the file batch to list files from.
- name: vector_store_id
in: path
required: true
schema:
type: string
title: Vector Store Id
description: The ID of the vector store containing the file batch.
responses:
'200':
description: A VectorStoreFilesListInBatchResponse containing the list of files in the batch.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFilesListInBatchResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/vector_stores/{vector_store_id}/files:
get:
tags:
- V1
summary: List files in a vector store.
description: Query endpoint for proper schema generation.
operationId: openai_list_files_in_vector_store_v1_vector_stores__vector_store_id__files_get
parameters:
- name: after
in: query
required: true
schema:
type: string
title: After
- name: before
in: query
required: true
schema:
type: string
title: Before
- name: filter
in: query
required: true
schema:
type: string
title: Filter
- name: limit
in: query
required: false
schema:
type: integer
default: 20
title: Limit
- name: order
in: query
required: false
schema:
type: string
default: desc
title: Order
- name: vector_store_id
in: path
required: true
schema:
type: string
title: Vector Store Id
description: The ID of the vector store to list files from.
responses:
'200':
description: A VectorStoreListFilesResponse containing the list of files.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreListFilesResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1
summary: Attach a file to a vector store.
description: Typed endpoint for proper schema generation.
operationId: openai_attach_file_to_vector_store_v1_vector_stores__vector_store_id__files_post
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/_vector_stores_vector_store_id_files_Request'
responses:
'200':
description: A VectorStoreFileObject representing the attached file.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileObject'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
parameters:
- name: vector_store_id
in: path
required: true
schema:
type: string
description: The ID of the vector store to attach the file to.
/v1/vector_stores/{vector_store_id}/files/{file_id}:
delete:
tags:
- V1
summary: Delete a vector store file.
description: Query endpoint for proper schema generation.
operationId: openai_delete_vector_store_file_v1_vector_stores__vector_store_id__files__file_id__delete
parameters:
- name: vector_store_id
in: path
required: true
schema:
type: string
title: Vector Store Id
description: The ID of the vector store containing the file to delete.
- name: file_id
in: path
required: true
schema:
type: string
title: File Id
description: The ID of the file to delete.
responses:
'200':
description: A VectorStoreFileDeleteResponse indicating the deletion status.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileDeleteResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
get:
tags:
- V1
summary: Retrieves a vector store file.
description: Query endpoint for proper schema generation.
operationId: openai_retrieve_vector_store_file_v1_vector_stores__vector_store_id__files__file_id__get
parameters:
- name: vector_store_id
in: path
required: true
schema:
type: string
title: Vector Store Id
description: The ID of the vector store containing the file to retrieve.
- name: file_id
in: path
required: true
schema:
type: string
title: File Id
description: The ID of the file to retrieve.
responses:
'200':
description: A VectorStoreFileObject representing the file.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileObject'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
post:
tags:
- V1
summary: Updates a vector store file.
description: Typed endpoint for proper schema generation.
operationId: openai_update_vector_store_file_v1_vector_stores__vector_store_id__files__file_id__post
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/_vector_stores_vector_store_id_files_file_id_Request'
responses:
'200':
description: A VectorStoreFileObject representing the updated file.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileObject'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
parameters:
- name: vector_store_id
in: path
required: true
schema:
type: string
description: The ID of the vector store containing the file to update.
- name: file_id
in: path
required: true
schema:
type: string
description: The ID of the file to update.
/v1/vector_stores/{vector_store_id}/files/{file_id}/content:
get:
tags:
- V1
summary: Retrieves the contents of a vector store file.
description: Query endpoint for proper schema generation.
operationId: openai_retrieve_vector_store_file_contents_v1_vector_stores__vector_store_id__files__file_id__content_get
parameters:
- name: vector_store_id
in: path
required: true
schema:
type: string
title: Vector Store Id
description: The ID of the vector store containing the file to retrieve.
- name: file_id
in: path
required: true
schema:
type: string
title: File Id
description: The ID of the file to retrieve.
responses:
'200':
description: A list of InterleavedContent representing the file contents.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreFileContentsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
description: Bad Request
'429':
$ref: '#/components/responses/TooManyRequests429'
description: Too Many Requests
'500':
$ref: '#/components/responses/InternalServerError500'
description: Internal Server Error
default:
$ref: '#/components/responses/DefaultError'
description: Default Response
/v1/vector_stores/{vector_store_id}/search:
post:
tags:
- V1
summary: Search for chunks in a vector store.
description: Typed endpoint for proper schema generation.
operationId: openai_search_vector_store_v1_vector_stores__vector_store_id__search_post
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/_vector_stores_vector_store_id_search_Request'
required: true
responses:
'200':
description: A VectorStoreSearchResponse containing the search results.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorStoreSearchResponsePage'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
parameters:
- name: vector_store_id
in: path
required: true
schema:
type: string
description: The ID of the vector store to search.
/v1/version:
get:
tags:
- V1
summary: Get version.
description: Response-only endpoint for proper schema generation.
operationId: version_v1_version_get
responses:
'200':
description: Version information containing the service version number.
content:
application/json:
schema:
$ref: '#/components/schemas/VersionInfo'
'400':
description: Bad Request
$ref: '#/components/responses/BadRequest400'
'429':
description: Too Many Requests
$ref: '#/components/responses/TooManyRequests429'
'500':
description: Internal Server Error
$ref: '#/components/responses/InternalServerError500'
default:
description: Default Response
$ref: '#/components/responses/DefaultError'
components:
schemas:
AgentCandidate:
properties:
type:
type: string
const: agent
title: Type
default: agent
config:
$ref: '#/components/schemas/AgentConfig'
type: object
required:
- config
title: AgentCandidate
description: An agent candidate for evaluation.
AgentConfig:
properties:
sampling_params:
$ref: '#/components/schemas/SamplingParams'
input_shields:
title: Input Shields
items:
type: string
type: array
output_shields:
title: Output Shields
items:
type: string
type: array
toolgroups:
title: Toolgroups
items:
anyOf:
- type: string
- $ref: '#/components/schemas/AgentToolGroupWithArgs'
type: array
client_tools:
title: Client Tools
items:
$ref: '#/components/schemas/ToolDef'
type: array
tool_choice:
deprecated: true
$ref: '#/components/schemas/ToolChoice'
tool_prompt_format:
deprecated: true
$ref: '#/components/schemas/ToolPromptFormat'
tool_config:
$ref: '#/components/schemas/ToolConfig'
max_infer_iters:
title: Max Infer Iters
default: 10
type: integer
model:
type: string
title: Model
instructions:
type: string
title: Instructions
name:
title: Name
type: string
enable_session_persistence:
title: Enable Session Persistence
default: false
type: boolean
response_format:
title: Response Format
oneOf:
- $ref: '#/components/schemas/JsonSchemaResponseFormat'
- $ref: '#/components/schemas/GrammarResponseFormat'
discriminator:
propertyName: type
mapping:
grammar: '#/components/schemas/GrammarResponseFormat'
json_schema: '#/components/schemas/JsonSchemaResponseFormat'
type: object
required:
- model
- instructions
title: AgentConfig
description: Configuration for an agent.
AgentCreateResponse:
properties:
agent_id:
type: string
title: Agent Id
type: object
required:
- agent_id
title: AgentCreateResponse
description: Response returned when creating a new agent.
AgentSessionCreateResponse:
properties:
session_id:
type: string
title: Session Id
type: object
required:
- session_id
title: AgentSessionCreateResponse
description: Response returned when creating a new agent session.
AgentToolGroupWithArgs:
properties:
name:
type: string
title: Name
args:
additionalProperties: true
type: object
title: Args
type: object
required:
- name
- args
title: AgentToolGroupWithArgs
AgentTurnInputType:
properties:
type:
type: string
const: agent_turn_input
title: Type
default: agent_turn_input
type: object
title: AgentTurnInputType
description: Parameter type for agent turn input.
AggregationFunctionType:
type: string
enum:
- average
- weighted_average
- median
- categorical_count
- accuracy
title: AggregationFunctionType
description: Types of aggregation functions for scoring results.
AllowedToolsFilter:
properties:
tool_names:
title: Tool Names
items:
type: string
type: array
type: object
title: AllowedToolsFilter
description: Filter configuration for restricting which MCP tools can be used.
ApprovalFilter:
properties:
always:
title: Always
items:
type: string
type: array
never:
title: Never
items:
type: string
type: array
type: object
title: ApprovalFilter
description: Filter configuration for MCP tool approval requirements.
ArrayType:
properties:
type:
type: string
const: array
title: Type
default: array
type: object
title: ArrayType
description: Parameter type for array values.
Attachment-Output:
properties:
content:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
type: array
- $ref: '#/components/schemas/URL'
title: Content
mime_type:
type: string
title: Mime Type
type: object
required:
- content
- mime_type
title: Attachment
description: An attachment to an agent turn.
BasicScoringFnParams:
properties:
type:
type: string
const: basic
title: Type
default: basic
aggregation_functions:
items:
$ref: '#/components/schemas/AggregationFunctionType'
type: array
title: Aggregation Functions
description: Aggregation functions to apply to the scores of each row
type: object
title: BasicScoringFnParams
description: Parameters for basic scoring function configuration.
Batch:
properties:
id:
type: string
title: Id
completion_window:
type: string
title: Completion Window
created_at:
type: integer
title: Created At
endpoint:
type: string
title: Endpoint
input_file_id:
type: string
title: Input File Id
object:
type: string
const: batch
title: Object
status:
type: string
enum:
- validating
- failed
- in_progress
- finalizing
- completed
- expired
- cancelling
- cancelled
title: Status
cancelled_at:
title: Cancelled At
type: integer
cancelling_at:
title: Cancelling At
type: integer
completed_at:
title: Completed At
type: integer
error_file_id:
title: Error File Id
type: string
errors:
$ref: '#/components/schemas/Errors'
expired_at:
title: Expired At
type: integer
expires_at:
title: Expires At
type: integer
failed_at:
title: Failed At
type: integer
finalizing_at:
title: Finalizing At
type: integer
in_progress_at:
title: In Progress At
type: integer
metadata:
title: Metadata
additionalProperties:
type: string
type: object
model:
title: Model
type: string
output_file_id:
title: Output File Id
type: string
request_counts:
$ref: '#/components/schemas/BatchRequestCounts'
usage:
$ref: '#/components/schemas/BatchUsage'
additionalProperties: true
type: object
required:
- id
- completion_window
- created_at
- endpoint
- input_file_id
- object
- status
title: Batch
BatchError:
properties:
code:
title: Code
type: string
line:
title: Line
type: integer
message:
title: Message
type: string
param:
title: Param
type: string
additionalProperties: true
type: object
title: BatchError
BatchRequestCounts:
properties:
completed:
type: integer
title: Completed
failed:
type: integer
title: Failed
total:
type: integer
title: Total
additionalProperties: true
type: object
required:
- completed
- failed
- total
title: BatchRequestCounts
BatchUsage:
properties:
input_tokens:
type: integer
title: Input Tokens
input_tokens_details:
$ref: '#/components/schemas/InputTokensDetails'
output_tokens:
type: integer
title: Output Tokens
output_tokens_details:
$ref: '#/components/schemas/OutputTokensDetails'
total_tokens:
type: integer
title: Total Tokens
additionalProperties: true
type: object
required:
- input_tokens
- input_tokens_details
- output_tokens
- output_tokens_details
- total_tokens
title: BatchUsage
Benchmark:
properties:
identifier:
type: string
title: Identifier
description: Unique identifier for this resource in llama stack
provider_resource_id:
title: Provider Resource Id
description: Unique identifier for this resource in the provider
type: string
provider_id:
type: string
title: Provider Id
description: ID of the provider that owns this resource
type:
type: string
const: benchmark
title: Type
default: benchmark
dataset_id:
type: string
title: Dataset Id
scoring_functions:
items:
type: string
type: array
title: Scoring Functions
metadata:
additionalProperties: true
type: object
title: Metadata
description: Metadata for this evaluation task
type: object
required:
- identifier
- provider_id
- dataset_id
- scoring_functions
title: Benchmark
description: A benchmark resource for evaluating model performance.
BenchmarkConfig:
properties:
eval_candidate:
oneOf:
- $ref: '#/components/schemas/ModelCandidate'
- $ref: '#/components/schemas/AgentCandidate'
title: Eval Candidate
discriminator:
propertyName: type
mapping:
agent: '#/components/schemas/AgentCandidate'
model: '#/components/schemas/ModelCandidate'
scoring_params:
additionalProperties:
oneOf:
- $ref: '#/components/schemas/LLMAsJudgeScoringFnParams'
- $ref: '#/components/schemas/RegexParserScoringFnParams'
- $ref: '#/components/schemas/BasicScoringFnParams'
discriminator:
propertyName: type
mapping:
basic: '#/components/schemas/BasicScoringFnParams'
llm_as_judge: '#/components/schemas/LLMAsJudgeScoringFnParams'
regex_parser: '#/components/schemas/RegexParserScoringFnParams'
type: object
title: Scoring Params
description: Map between scoring function id and parameters for each scoring function you want to run
num_examples:
title: Num Examples
description: Number of examples to evaluate (useful for testing), if not provided, all examples in the dataset will be evaluated
type: integer
type: object
required:
- eval_candidate
title: BenchmarkConfig
description: A benchmark configuration for evaluation.
BooleanType:
properties:
type:
type: string
const: boolean
title: Type
default: boolean
type: object
title: BooleanType
description: Parameter type for boolean values.
BuiltinTool:
type: string
enum:
- brave_search
- wolfram_alpha
- photogen
- code_interpreter
title: BuiltinTool
ChatCompletionInputType:
properties:
type:
type: string
const: chat_completion_input
title: Type
default: chat_completion_input
type: object
title: ChatCompletionInputType
description: Parameter type for chat completion input.
Chunk-Output:
properties:
content:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
type: array
title: Content
chunk_id:
type: string
title: Chunk Id
metadata:
additionalProperties: true
type: object
title: Metadata
embedding:
title: Embedding
items:
type: number
type: array
chunk_metadata:
$ref: '#/components/schemas/ChunkMetadata'
type: object
required:
- content
- chunk_id
title: Chunk
description: A chunk of content that can be inserted into a vector database.
ChunkMetadata:
properties:
chunk_id:
title: Chunk Id
type: string
document_id:
title: Document Id
type: string
source:
title: Source
type: string
created_timestamp:
title: Created Timestamp
type: integer
updated_timestamp:
title: Updated Timestamp
type: integer
chunk_window:
title: Chunk Window
type: string
chunk_tokenizer:
title: Chunk Tokenizer
type: string
chunk_embedding_model:
title: Chunk Embedding Model
type: string
chunk_embedding_dimension:
title: Chunk Embedding Dimension
type: integer
content_token_count:
title: Content Token Count
type: integer
metadata_token_count:
title: Metadata Token Count
type: integer
type: object
title: ChunkMetadata
description: "`ChunkMetadata` is backend metadata for a `Chunk` that is used to store additional information about the chunk that\n will not be used in the context during inference, but is required for backend functionality. The `ChunkMetadata`\n is set during chunk creation in `MemoryToolRuntimeImpl().insert()`and is not expected to change after.\n Use `Chunk.metadata` for metadata that will be used in the context during inference."
CompletionInputType:
properties:
type:
type: string
const: completion_input
title: Type
default: completion_input
type: object
title: CompletionInputType
description: Parameter type for completion input.
CompletionMessage-Output:
properties:
role:
type: string
const: assistant
title: Role
default: assistant
content:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
type: array
title: Content
stop_reason:
$ref: '#/components/schemas/StopReason'
tool_calls:
title: Tool Calls
items:
$ref: '#/components/schemas/ToolCall'
type: array
type: object
required:
- content
- stop_reason
title: CompletionMessage
description: A message containing the model's (assistant) response in a chat conversation.
Conversation:
properties:
id:
type: string
title: Id
description: The unique ID of the conversation.
object:
type: string
const: conversation
title: Object
description: The object type, which is always conversation.
default: conversation
created_at:
type: integer
title: Created At
description: The time at which the conversation was created, measured in seconds since the Unix epoch.
metadata:
title: Metadata
description: Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
additionalProperties:
type: string
type: object
items:
title: Items
description: Initial items to include in the conversation context. You may add up to 20 items at a time.
items:
additionalProperties: true
type: object
type: array
type: object
required:
- id
- created_at
title: Conversation
description: OpenAI-compatible conversation object.
ConversationItemInclude:
type: string
enum:
- web_search_call.action.sources
- code_interpreter_call.outputs
- computer_call_output.output.image_url
- file_search_call.results
- message.input_image.image_url
- message.output_text.logprobs
- reasoning.encrypted_content
title: ConversationItemInclude
description: Specify additional output data to include in the model response.
ConversationItemList:
properties:
object:
type: string
title: Object
description: Object type
default: list
data:
items:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseMessage-Output'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
- $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalResponse'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
discriminator:
propertyName: type
mapping:
file_search_call: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
function_call_output: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
mcp_approval_request: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
mcp_approval_response: '#/components/schemas/OpenAIResponseMCPApprovalResponse'
mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
message: '#/components/schemas/OpenAIResponseMessage-Output'
web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
type: array
title: Data
description: List of conversation items
first_id:
title: First Id
description: The ID of the first item in the list
type: string
last_id:
title: Last Id
description: The ID of the last item in the list
type: string
has_more:
type: boolean
title: Has More
description: Whether there are more items available
default: false
type: object
required:
- data
title: ConversationItemList
description: List of conversation items with pagination.
DPOAlignmentConfig:
properties:
beta:
type: number
title: Beta
loss_type:
$ref: '#/components/schemas/DPOLossType'
default: sigmoid
type: object
required:
- beta
title: DPOAlignmentConfig
description: Configuration for Direct Preference Optimization (DPO) alignment.
DPOLossType:
type: string
enum:
- sigmoid
- hinge
- ipo
- kto_pair
title: DPOLossType
DataConfig:
properties:
dataset_id:
type: string
title: Dataset Id
batch_size:
type: integer
title: Batch Size
shuffle:
type: boolean
title: Shuffle
data_format:
$ref: '#/components/schemas/DatasetFormat'
validation_dataset_id:
title: Validation Dataset Id
type: string
packed:
title: Packed
default: false
type: boolean
train_on_input:
title: Train On Input
default: false
type: boolean
type: object
required:
- dataset_id
- batch_size
- shuffle
- data_format
title: DataConfig
description: Configuration for training data and data loading.
Dataset:
properties:
identifier:
type: string
title: Identifier
description: Unique identifier for this resource in llama stack
provider_resource_id:
title: Provider Resource Id
description: Unique identifier for this resource in the provider
type: string
provider_id:
type: string
title: Provider Id
description: ID of the provider that owns this resource
type:
type: string
const: dataset
title: Type
default: dataset
purpose:
$ref: '#/components/schemas/DatasetPurpose'
source:
oneOf:
- $ref: '#/components/schemas/URIDataSource'
- $ref: '#/components/schemas/RowsDataSource'
title: Source
discriminator:
propertyName: type
mapping:
rows: '#/components/schemas/RowsDataSource'
uri: '#/components/schemas/URIDataSource'
metadata:
additionalProperties: true
type: object
title: Metadata
description: Any additional metadata for this dataset
type: object
required:
- identifier
- provider_id
- purpose
- source
title: Dataset
description: Dataset resource for storing and accessing training or evaluation data.
DatasetFormat:
type: string
enum:
- instruct
- dialog
title: DatasetFormat
description: Format of the training dataset.
DatasetPurpose:
type: string
enum:
- post-training/messages
- eval/question-answer
- eval/messages-answer
title: DatasetPurpose
description: Purpose of the dataset. Each purpose has a required input data schema.
DefaultRAGQueryGeneratorConfig:
properties:
type:
type: string
const: default
title: Type
default: default
separator:
type: string
title: Separator
default: ' '
type: object
title: DefaultRAGQueryGeneratorConfig
description: Configuration for the default RAG query generator.
Document:
properties:
content:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Input'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Input'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Input'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Input'
text: '#/components/schemas/TextContentItem'
type: array
- $ref: '#/components/schemas/URL'
title: Content
mime_type:
type: string
title: Mime Type
type: object
required:
- content
- mime_type
title: Document
description: A document to be used by an agent.
EfficiencyConfig:
properties:
enable_activation_checkpointing:
title: Enable Activation Checkpointing
default: false
type: boolean
enable_activation_offloading:
title: Enable Activation Offloading
default: false
type: boolean
memory_efficient_fsdp_wrap:
title: Memory Efficient Fsdp Wrap
default: false
type: boolean
fsdp_cpu_offload:
title: Fsdp Cpu Offload
default: false
type: boolean
type: object
title: EfficiencyConfig
description: Configuration for memory and compute efficiency optimizations.
Errors:
properties:
data:
title: Data
items:
$ref: '#/components/schemas/BatchError'
type: array
object:
title: Object
type: string
additionalProperties: true
type: object
title: Errors
EvaluateResponse:
properties:
generations:
items:
additionalProperties: true
type: object
type: array
title: Generations
scores:
additionalProperties:
$ref: '#/components/schemas/ScoringResult'
type: object
title: Scores
type: object
required:
- generations
- scores
title: EvaluateResponse
description: The response from an evaluation.
GrammarResponseFormat:
properties:
type:
type: string
const: grammar
title: Type
default: grammar
bnf:
additionalProperties: true
type: object
title: Bnf
type: object
required:
- bnf
title: GrammarResponseFormat
description: Configuration for grammar-guided response generation.
GreedySamplingStrategy:
properties:
type:
type: string
const: greedy
title: Type
default: greedy
type: object
title: GreedySamplingStrategy
description: Greedy sampling strategy that selects the highest probability token at each step.
HealthInfo:
properties:
status:
$ref: '#/components/schemas/HealthStatus'
type: object
required:
- status
title: HealthInfo
description: Health status information for the service.
HealthStatus:
type: string
enum:
- OK
- Error
- Not Implemented
title: HealthStatus
ImageContentItem-Input:
properties:
type:
type: string
const: image
title: Type
default: image
image:
$ref: '#/components/schemas/_URLOrData'
type: object
required:
- image
title: ImageContentItem
description: A image content item
ImageContentItem-Output:
properties:
type:
type: string
const: image
title: Type
default: image
image:
$ref: '#/components/schemas/_URLOrData'
type: object
required:
- image
title: ImageContentItem
description: A image content item
InferenceStep-Output:
properties:
turn_id:
type: string
title: Turn Id
step_id:
type: string
title: Step Id
started_at:
title: Started At
type: string
format: date-time
completed_at:
title: Completed At
type: string
format: date-time
step_type:
type: string
const: inference
title: Step Type
default: inference
model_response:
$ref: '#/components/schemas/CompletionMessage-Output'
type: object
required:
- turn_id
- step_id
- model_response
title: InferenceStep
description: An inference step in an agent turn.
InputTokensDetails:
properties:
cached_tokens:
type: integer
title: Cached Tokens
additionalProperties: true
type: object
required:
- cached_tokens
title: InputTokensDetails
Job:
properties:
job_id:
type: string
title: Job Id
status:
$ref: '#/components/schemas/JobStatus'
type: object
required:
- job_id
- status
title: Job
description: A job execution instance with status tracking.
JobStatus:
type: string
enum:
- completed
- in_progress
- failed
- scheduled
- cancelled
title: JobStatus
description: Status of a job execution.
JsonSchemaResponseFormat:
properties:
type:
type: string
const: json_schema
title: Type
default: json_schema
json_schema:
additionalProperties: true
type: object
title: Json Schema
type: object
required:
- json_schema
title: JsonSchemaResponseFormat
description: Configuration for JSON schema-guided response generation.
JsonType:
properties:
type:
type: string
const: json
title: Type
default: json
type: object
title: JsonType
description: Parameter type for JSON values.
LLMAsJudgeScoringFnParams:
properties:
type:
type: string
const: llm_as_judge
title: Type
default: llm_as_judge
judge_model:
type: string
title: Judge Model
prompt_template:
title: Prompt Template
type: string
judge_score_regexes:
items:
type: string
type: array
title: Judge Score Regexes
description: Regexes to extract the answer from generated response
aggregation_functions:
items:
$ref: '#/components/schemas/AggregationFunctionType'
type: array
title: Aggregation Functions
description: Aggregation functions to apply to the scores of each row
type: object
required:
- judge_model
title: LLMAsJudgeScoringFnParams
description: Parameters for LLM-as-judge scoring function configuration.
LLMRAGQueryGeneratorConfig:
properties:
type:
type: string
const: llm
title: Type
default: llm
model:
type: string
title: Model
template:
type: string
title: Template
type: object
required:
- model
- template
title: LLMRAGQueryGeneratorConfig
description: Configuration for the LLM-based RAG query generator.
ListBenchmarksResponse:
properties:
data:
items:
$ref: '#/components/schemas/Benchmark'
type: array
title: Data
type: object
required:
- data
title: ListBenchmarksResponse
ListDatasetsResponse:
properties:
data:
items:
$ref: '#/components/schemas/Dataset'
type: array
title: Data
type: object
required:
- data
title: ListDatasetsResponse
description: Response from listing datasets.
ListModelsResponse:
properties:
data:
items:
$ref: '#/components/schemas/Model'
type: array
title: Data
type: object
required:
- data
title: ListModelsResponse
ListPostTrainingJobsResponse:
properties:
data:
items:
$ref: '#/components/schemas/PostTrainingJob'
type: array
title: Data
type: object
required:
- data
title: ListPostTrainingJobsResponse
ListPromptsResponse:
properties:
data:
items:
$ref: '#/components/schemas/Prompt'
type: array
title: Data
type: object
required:
- data
title: ListPromptsResponse
description: Response model to list prompts.
ListProvidersResponse:
properties:
data:
items:
$ref: '#/components/schemas/ProviderInfo'
type: array
title: Data
type: object
required:
- data
title: ListProvidersResponse
description: Response containing a list of all available providers.
ListRoutesResponse:
properties:
data:
items:
$ref: '#/components/schemas/RouteInfo'
type: array
title: Data
type: object
required:
- data
title: ListRoutesResponse
description: Response containing a list of all available API routes.
ListScoringFunctionsResponse:
properties:
data:
items:
$ref: '#/components/schemas/ScoringFn-Output'
type: array
title: Data
type: object
required:
- data
title: ListScoringFunctionsResponse
ListShieldsResponse:
properties:
data:
items:
$ref: '#/components/schemas/Shield'
type: array
title: Data
type: object
required:
- data
title: ListShieldsResponse
ListToolGroupsResponse:
properties:
data:
items:
$ref: '#/components/schemas/ToolGroup'
type: array
title: Data
type: object
required:
- data
title: ListToolGroupsResponse
description: Response containing a list of tool groups.
MCPListToolsTool:
properties:
input_schema:
additionalProperties: true
type: object
title: Input Schema
name:
type: string
title: Name
description:
title: Description
type: string
type: object
required:
- input_schema
- name
title: MCPListToolsTool
description: Tool definition returned by MCP list tools operation.
MemoryRetrievalStep-Output:
properties:
turn_id:
type: string
title: Turn Id
step_id:
type: string
title: Step Id
started_at:
title: Started At
type: string
format: date-time
completed_at:
title: Completed At
type: string
format: date-time
step_type:
type: string
const: memory_retrieval
title: Step Type
default: memory_retrieval
vector_store_ids:
type: string
title: Vector Store Ids
inserted_context:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
type: array
title: Inserted Context
type: object
required:
- turn_id
- step_id
- vector_store_ids
- inserted_context
title: MemoryRetrievalStep
description: A memory retrieval step in an agent turn.
Model:
properties:
identifier:
type: string
title: Identifier
description: Unique identifier for this resource in llama stack
provider_resource_id:
title: Provider Resource Id
description: Unique identifier for this resource in the provider
type: string
provider_id:
type: string
title: Provider Id
description: ID of the provider that owns this resource
type:
type: string
const: model
title: Type
default: model
metadata:
additionalProperties: true
type: object
title: Metadata
description: Any additional metadata for this model
model_type:
$ref: '#/components/schemas/ModelType'
default: llm
type: object
required:
- identifier
- provider_id
title: Model
description: A model resource representing an AI model registered in Llama Stack.
ModelCandidate:
properties:
type:
type: string
const: model
title: Type
default: model
model:
type: string
title: Model
sampling_params:
$ref: '#/components/schemas/SamplingParams'
system_message:
$ref: '#/components/schemas/SystemMessage'
type: object
required:
- model
- sampling_params
title: ModelCandidate
description: A model candidate for evaluation.
ModelType:
type: string
enum:
- llm
- embedding
- rerank
title: ModelType
description: Enumeration of supported model types in Llama Stack.
ModerationObject:
properties:
id:
type: string
title: Id
model:
type: string
title: Model
results:
items:
$ref: '#/components/schemas/ModerationObjectResults'
type: array
title: Results
type: object
required:
- id
- model
- results
title: ModerationObject
description: A moderation object.
ModerationObjectResults:
properties:
flagged:
type: boolean
title: Flagged
categories:
title: Categories
additionalProperties:
type: boolean
type: object
category_applied_input_types:
title: Category Applied Input Types
additionalProperties:
items:
type: string
type: array
type: object
category_scores:
title: Category Scores
additionalProperties:
type: number
type: object
user_message:
title: User Message
type: string
metadata:
additionalProperties: true
type: object
title: Metadata
type: object
required:
- flagged
title: ModerationObjectResults
description: A moderation object.
NumberType:
properties:
type:
type: string
const: number
title: Type
default: number
type: object
title: NumberType
description: Parameter type for numeric values.
ObjectType:
properties:
type:
type: string
const: object
title: Type
default: object
type: object
title: ObjectType
description: Parameter type for object values.
OpenAIAssistantMessageParam-Input:
properties:
role:
type: string
const: assistant
title: Role
default: assistant
content:
anyOf:
- type: string
- items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
type: array
title: Content
name:
title: Name
type: string
tool_calls:
title: Tool Calls
items:
$ref: '#/components/schemas/OpenAIChatCompletionToolCall'
type: array
type: object
title: OpenAIAssistantMessageParam
description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request.
OpenAIAssistantMessageParam-Output:
properties:
role:
type: string
const: assistant
title: Role
default: assistant
content:
anyOf:
- type: string
- items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
type: array
title: Content
name:
title: Name
type: string
tool_calls:
title: Tool Calls
items:
$ref: '#/components/schemas/OpenAIChatCompletionToolCall'
type: array
type: object
title: OpenAIAssistantMessageParam
description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request.
OpenAIChatCompletion:
properties:
id:
type: string
title: Id
choices:
items:
$ref: '#/components/schemas/OpenAIChoice-Output'
type: array
title: Choices
object:
type: string
const: chat.completion
title: Object
default: chat.completion
created:
type: integer
title: Created
model:
type: string
title: Model
usage:
$ref: '#/components/schemas/OpenAIChatCompletionUsage'
type: object
required:
- id
- choices
- created
- model
title: OpenAIChatCompletion
description: Response from an OpenAI-compatible chat completion request.
OpenAIChatCompletionContentPartImageParam:
properties:
type:
type: string
const: image_url
title: Type
default: image_url
image_url:
$ref: '#/components/schemas/OpenAIImageURL'
type: object
required:
- image_url
title: OpenAIChatCompletionContentPartImageParam
description: Image content part for OpenAI-compatible chat completion messages.
OpenAIChatCompletionContentPartTextParam:
properties:
type:
type: string
const: text
title: Type
default: text
text:
type: string
title: Text
type: object
required:
- text
title: OpenAIChatCompletionContentPartTextParam
description: Text content part for OpenAI-compatible chat completion messages.
OpenAIChatCompletionRequestWithExtraBody:
properties:
model:
type: string
title: Model
messages:
items:
oneOf:
- $ref: '#/components/schemas/OpenAIUserMessageParam-Input'
- $ref: '#/components/schemas/OpenAISystemMessageParam'
- $ref: '#/components/schemas/OpenAIAssistantMessageParam-Input'
- $ref: '#/components/schemas/OpenAIToolMessageParam'
- $ref: '#/components/schemas/OpenAIDeveloperMessageParam'
discriminator:
propertyName: role
mapping:
assistant: '#/components/schemas/OpenAIAssistantMessageParam-Input'
developer: '#/components/schemas/OpenAIDeveloperMessageParam'
system: '#/components/schemas/OpenAISystemMessageParam'
tool: '#/components/schemas/OpenAIToolMessageParam'
user: '#/components/schemas/OpenAIUserMessageParam-Input'
type: array
minItems: 1
title: Messages
frequency_penalty:
title: Frequency Penalty
type: number
function_call:
anyOf:
- type: string
- additionalProperties: true
type: object
title: Function Call
functions:
title: Functions
items:
additionalProperties: true
type: object
type: array
logit_bias:
title: Logit Bias
additionalProperties:
type: number
type: object
logprobs:
title: Logprobs
type: boolean
max_completion_tokens:
title: Max Completion Tokens
type: integer
max_tokens:
title: Max Tokens
type: integer
n:
title: N
type: integer
parallel_tool_calls:
title: Parallel Tool Calls
type: boolean
presence_penalty:
title: Presence Penalty
type: number
response_format:
title: Response Format
oneOf:
- $ref: '#/components/schemas/OpenAIResponseFormatText'
- $ref: '#/components/schemas/OpenAIResponseFormatJSONSchema'
- $ref: '#/components/schemas/OpenAIResponseFormatJSONObject'
discriminator:
propertyName: type
mapping:
json_object: '#/components/schemas/OpenAIResponseFormatJSONObject'
json_schema: '#/components/schemas/OpenAIResponseFormatJSONSchema'
text: '#/components/schemas/OpenAIResponseFormatText'
seed:
title: Seed
type: integer
stop:
anyOf:
- type: string
- items:
type: string
type: array
title: Stop
stream:
title: Stream
type: boolean
stream_options:
title: Stream Options
additionalProperties: true
type: object
temperature:
title: Temperature
type: number
tool_choice:
anyOf:
- type: string
- additionalProperties: true
type: object
title: Tool Choice
tools:
title: Tools
items:
additionalProperties: true
type: object
type: array
top_logprobs:
title: Top Logprobs
type: integer
top_p:
title: Top P
type: number
user:
title: User
type: string
additionalProperties: true
type: object
required:
- model
- messages
title: OpenAIChatCompletionRequestWithExtraBody
description: Request parameters for OpenAI-compatible chat completion endpoint.
OpenAIChatCompletionToolCall:
properties:
index:
title: Index
type: integer
id:
title: Id
type: string
type:
type: string
const: function
title: Type
default: function
function:
$ref: '#/components/schemas/OpenAIChatCompletionToolCallFunction'
type: object
title: OpenAIChatCompletionToolCall
description: Tool call specification for OpenAI-compatible chat completion responses.
OpenAIChatCompletionToolCallFunction:
properties:
name:
title: Name
type: string
arguments:
title: Arguments
type: string
type: object
title: OpenAIChatCompletionToolCallFunction
description: Function call details for OpenAI-compatible tool calls.
OpenAIChatCompletionUsage:
properties:
prompt_tokens:
type: integer
title: Prompt Tokens
completion_tokens:
type: integer
title: Completion Tokens
total_tokens:
type: integer
title: Total Tokens
prompt_tokens_details:
$ref: '#/components/schemas/OpenAIChatCompletionUsagePromptTokensDetails'
completion_tokens_details:
$ref: '#/components/schemas/OpenAIChatCompletionUsageCompletionTokensDetails'
type: object
required:
- prompt_tokens
- completion_tokens
- total_tokens
title: OpenAIChatCompletionUsage
description: Usage information for OpenAI chat completion.
OpenAIChatCompletionUsageCompletionTokensDetails:
properties:
reasoning_tokens:
title: Reasoning Tokens
type: integer
type: object
title: OpenAIChatCompletionUsageCompletionTokensDetails
description: Token details for output tokens in OpenAI chat completion usage.
OpenAIChatCompletionUsagePromptTokensDetails:
properties:
cached_tokens:
title: Cached Tokens
type: integer
type: object
title: OpenAIChatCompletionUsagePromptTokensDetails
description: Token details for prompt tokens in OpenAI chat completion usage.
OpenAIChoice-Output:
properties:
message:
oneOf:
- $ref: '#/components/schemas/OpenAIUserMessageParam-Output'
- $ref: '#/components/schemas/OpenAISystemMessageParam'
- $ref: '#/components/schemas/OpenAIAssistantMessageParam-Output'
- $ref: '#/components/schemas/OpenAIToolMessageParam'
- $ref: '#/components/schemas/OpenAIDeveloperMessageParam'
title: Message
discriminator:
propertyName: role
mapping:
assistant: '#/components/schemas/OpenAIAssistantMessageParam-Output'
developer: '#/components/schemas/OpenAIDeveloperMessageParam'
system: '#/components/schemas/OpenAISystemMessageParam'
tool: '#/components/schemas/OpenAIToolMessageParam'
user: '#/components/schemas/OpenAIUserMessageParam-Output'
finish_reason:
type: string
title: Finish Reason
index:
type: integer
title: Index
logprobs:
$ref: '#/components/schemas/OpenAIChoiceLogprobs-Output'
type: object
required:
- message
- finish_reason
- index
title: OpenAIChoice
description: A choice from an OpenAI-compatible chat completion response.
OpenAIChoiceLogprobs-Output:
properties:
content:
title: Content
items:
$ref: '#/components/schemas/OpenAITokenLogProb'
type: array
refusal:
title: Refusal
items:
$ref: '#/components/schemas/OpenAITokenLogProb'
type: array
type: object
title: OpenAIChoiceLogprobs
description: The log probabilities for the tokens in the message from an OpenAI-compatible chat completion response.
OpenAICompletion:
properties:
id:
type: string
title: Id
choices:
items:
$ref: '#/components/schemas/OpenAICompletionChoice-Output'
type: array
title: Choices
created:
type: integer
title: Created
model:
type: string
title: Model
object:
type: string
const: text_completion
title: Object
default: text_completion
type: object
required:
- id
- choices
- created
- model
title: OpenAICompletion
description: Response from an OpenAI-compatible completion request.
OpenAICompletionChoice-Output:
properties:
finish_reason:
type: string
title: Finish Reason
text:
type: string
title: Text
index:
type: integer
title: Index
logprobs:
$ref: '#/components/schemas/OpenAIChoiceLogprobs-Output'
type: object
required:
- finish_reason
- text
- index
title: OpenAICompletionChoice
description: A choice from an OpenAI-compatible completion response.
OpenAICompletionRequestWithExtraBody:
properties:
model:
type: string
title: Model
prompt:
anyOf:
- type: string
- items:
type: string
type: array
- items:
type: integer
type: array
- items:
items:
type: integer
type: array
type: array
title: Prompt
best_of:
title: Best Of
type: integer
echo:
title: Echo
type: boolean
frequency_penalty:
title: Frequency Penalty
type: number
logit_bias:
title: Logit Bias
additionalProperties:
type: number
type: object
logprobs:
title: Logprobs
type: boolean
max_tokens:
title: Max Tokens
type: integer
n:
title: N
type: integer
presence_penalty:
title: Presence Penalty
type: number
seed:
title: Seed
type: integer
stop:
anyOf:
- type: string
- items:
type: string
type: array
title: Stop
stream:
title: Stream
type: boolean
stream_options:
title: Stream Options
additionalProperties: true
type: object
temperature:
title: Temperature
type: number
top_p:
title: Top P
type: number
user:
title: User
type: string
suffix:
title: Suffix
type: string
additionalProperties: true
type: object
required:
- model
- prompt
title: OpenAICompletionRequestWithExtraBody
description: Request parameters for OpenAI-compatible completion endpoint.
OpenAICreateVectorStoreFileBatchRequestWithExtraBody:
properties:
file_ids:
items:
type: string
type: array
title: File Ids
attributes:
title: Attributes
additionalProperties: true
type: object
chunking_strategy:
title: Chunking Strategy
oneOf:
- $ref: '#/components/schemas/VectorStoreChunkingStrategyAuto'
- $ref: '#/components/schemas/VectorStoreChunkingStrategyStatic'
discriminator:
propertyName: type
mapping:
auto: '#/components/schemas/VectorStoreChunkingStrategyAuto'
static: '#/components/schemas/VectorStoreChunkingStrategyStatic'
additionalProperties: true
type: object
required:
- file_ids
title: OpenAICreateVectorStoreFileBatchRequestWithExtraBody
description: Request to create a vector store file batch with extra_body support.
OpenAICreateVectorStoreRequestWithExtraBody:
properties:
name:
title: Name
type: string
file_ids:
title: File Ids
items:
type: string
type: array
expires_after:
title: Expires After
additionalProperties: true
type: object
chunking_strategy:
title: Chunking Strategy
additionalProperties: true
type: object
metadata:
title: Metadata
additionalProperties: true
type: object
additionalProperties: true
type: object
title: OpenAICreateVectorStoreRequestWithExtraBody
description: Request to create a vector store with extra_body support.
OpenAIDeveloperMessageParam:
properties:
role:
type: string
const: developer
title: Role
default: developer
content:
anyOf:
- type: string
- items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
type: array
title: Content
name:
title: Name
type: string
type: object
required:
- content
title: OpenAIDeveloperMessageParam
description: A message from the developer in an OpenAI-compatible chat completion request.
OpenAIEmbeddingData:
properties:
object:
type: string
const: embedding
title: Object
default: embedding
embedding:
anyOf:
- items:
type: number
type: array
- type: string
title: Embedding
index:
type: integer
title: Index
type: object
required:
- embedding
- index
title: OpenAIEmbeddingData
description: A single embedding data object from an OpenAI-compatible embeddings response.
OpenAIEmbeddingUsage:
properties:
prompt_tokens:
type: integer
title: Prompt Tokens
total_tokens:
type: integer
title: Total Tokens
type: object
required:
- prompt_tokens
- total_tokens
title: OpenAIEmbeddingUsage
description: Usage information for an OpenAI-compatible embeddings response.
OpenAIEmbeddingsRequestWithExtraBody:
properties:
model:
type: string
title: Model
input:
anyOf:
- type: string
- items:
type: string
type: array
title: Input
encoding_format:
title: Encoding Format
default: float
type: string
dimensions:
title: Dimensions
type: integer
user:
title: User
type: string
additionalProperties: true
type: object
required:
- model
- input
title: OpenAIEmbeddingsRequestWithExtraBody
description: Request parameters for OpenAI-compatible embeddings endpoint.
OpenAIEmbeddingsResponse:
properties:
object:
type: string
const: list
title: Object
default: list
data:
items:
$ref: '#/components/schemas/OpenAIEmbeddingData'
type: array
title: Data
model:
type: string
title: Model
usage:
$ref: '#/components/schemas/OpenAIEmbeddingUsage'
type: object
required:
- data
- model
- usage
title: OpenAIEmbeddingsResponse
description: Response from an OpenAI-compatible embeddings request.
OpenAIFile:
properties:
type:
type: string
const: file
title: Type
default: file
file:
$ref: '#/components/schemas/OpenAIFileFile'
type: object
required:
- file
title: OpenAIFile
OpenAIFileFile:
properties:
file_data:
title: File Data
type: string
file_id:
title: File Id
type: string
filename:
title: Filename
type: string
type: object
title: OpenAIFileFile
OpenAIFileObject:
properties:
object:
type: string
const: file
title: Object
default: file
id:
type: string
title: Id
bytes:
type: integer
title: Bytes
created_at:
type: integer
title: Created At
expires_at:
type: integer
title: Expires At
filename:
type: string
title: Filename
purpose:
$ref: '#/components/schemas/OpenAIFilePurpose'
type: object
required:
- id
- bytes
- created_at
- expires_at
- filename
- purpose
title: OpenAIFileObject
description: OpenAI File object as defined in the OpenAI Files API.
OpenAIFilePurpose:
type: string
enum:
- assistants
- batch
title: OpenAIFilePurpose
description: Valid purpose values for OpenAI Files API.
OpenAIImageURL:
properties:
url:
type: string
title: Url
detail:
title: Detail
type: string
type: object
required:
- url
title: OpenAIImageURL
description: Image URL specification for OpenAI-compatible chat completion messages.
OpenAIJSONSchema:
properties:
name:
type: string
title: Name
description:
title: Description
type: string
strict:
title: Strict
type: boolean
schema:
title: Schema
additionalProperties: true
type: object
type: object
title: OpenAIJSONSchema
description: JSON schema specification for OpenAI-compatible structured response format.
OpenAIResponseAnnotationCitation:
properties:
type:
type: string
const: url_citation
title: Type
default: url_citation
end_index:
type: integer
title: End Index
start_index:
type: integer
title: Start Index
title:
type: string
title: Title
url:
type: string
title: Url
type: object
required:
- end_index
- start_index
- title
- url
title: OpenAIResponseAnnotationCitation
description: URL citation annotation for referencing external web resources.
OpenAIResponseAnnotationContainerFileCitation:
properties:
type:
type: string
const: container_file_citation
title: Type
default: container_file_citation
container_id:
type: string
title: Container Id
end_index:
type: integer
title: End Index
file_id:
type: string
title: File Id
filename:
type: string
title: Filename
start_index:
type: integer
title: Start Index
type: object
required:
- container_id
- end_index
- file_id
- filename
- start_index
title: OpenAIResponseAnnotationContainerFileCitation
OpenAIResponseAnnotationFileCitation:
properties:
type:
type: string
const: file_citation
title: Type
default: file_citation
file_id:
type: string
title: File Id
filename:
type: string
title: Filename
index:
type: integer
title: Index
type: object
required:
- file_id
- filename
- index
title: OpenAIResponseAnnotationFileCitation
description: File citation annotation for referencing specific files in response content.
OpenAIResponseAnnotationFilePath:
properties:
type:
type: string
const: file_path
title: Type
default: file_path
file_id:
type: string
title: File Id
index:
type: integer
title: Index
type: object
required:
- file_id
- index
title: OpenAIResponseAnnotationFilePath
OpenAIResponseContentPartRefusal:
properties:
type:
type: string
const: refusal
title: Type
default: refusal
refusal:
type: string
title: Refusal
type: object
required:
- refusal
title: OpenAIResponseContentPartRefusal
description: Refusal content within a streamed response part.
OpenAIResponseError:
properties:
code:
type: string
title: Code
message:
type: string
title: Message
type: object
required:
- code
- message
title: OpenAIResponseError
description: Error details for failed OpenAI response requests.
OpenAIResponseFormatJSONObject:
properties:
type:
type: string
const: json_object
title: Type
default: json_object
type: object
title: OpenAIResponseFormatJSONObject
description: JSON object response format for OpenAI-compatible chat completion requests.
OpenAIResponseFormatJSONSchema:
properties:
type:
type: string
const: json_schema
title: Type
default: json_schema
json_schema:
$ref: '#/components/schemas/OpenAIJSONSchema'
type: object
required:
- json_schema
title: OpenAIResponseFormatJSONSchema
description: JSON schema response format for OpenAI-compatible chat completion requests.
OpenAIResponseFormatText:
properties:
type:
type: string
const: text
title: Type
default: text
type: object
title: OpenAIResponseFormatText
description: Text response format for OpenAI-compatible chat completion requests.
OpenAIResponseInputFunctionToolCallOutput:
properties:
call_id:
type: string
title: Call Id
output:
type: string
title: Output
type:
type: string
const: function_call_output
title: Type
default: function_call_output
id:
title: Id
type: string
status:
title: Status
type: string
type: object
required:
- call_id
- output
title: OpenAIResponseInputFunctionToolCallOutput
description: This represents the output of a function call that gets passed back to the model.
OpenAIResponseInputMessageContentFile:
properties:
type:
type: string
const: input_file
title: Type
default: input_file
file_data:
title: File Data
type: string
file_id:
title: File Id
type: string
file_url:
title: File Url
type: string
filename:
title: Filename
type: string
type: object
title: OpenAIResponseInputMessageContentFile
description: File content for input messages in OpenAI response format.
OpenAIResponseInputMessageContentImage:
properties:
detail:
anyOf:
- type: string
const: low
- type: string
const: high
- type: string
const: auto
title: Detail
default: auto
type:
type: string
const: input_image
title: Type
default: input_image
file_id:
title: File Id
type: string
image_url:
title: Image Url
type: string
type: object
title: OpenAIResponseInputMessageContentImage
description: Image content for input messages in OpenAI response format.
OpenAIResponseInputMessageContentText:
properties:
text:
type: string
title: Text
type:
type: string
const: input_text
title: Type
default: input_text
type: object
required:
- text
title: OpenAIResponseInputMessageContentText
description: Text content for input messages in OpenAI response format.
OpenAIResponseInputToolFileSearch:
properties:
type:
type: string
const: file_search
title: Type
default: file_search
vector_store_ids:
items:
type: string
type: array
title: Vector Store Ids
filters:
title: Filters
additionalProperties: true
type: object
max_num_results:
title: Max Num Results
default: 10
type: integer
maximum: 50.0
minimum: 1.0
ranking_options:
$ref: '#/components/schemas/SearchRankingOptions'
type: object
required:
- vector_store_ids
title: OpenAIResponseInputToolFileSearch
description: File search tool configuration for OpenAI response inputs.
OpenAIResponseInputToolFunction:
properties:
type:
type: string
const: function
title: Type
default: function
name:
type: string
title: Name
description:
title: Description
type: string
parameters:
title: Parameters
additionalProperties: true
type: object
strict:
title: Strict
type: boolean
type: object
required:
- name
- parameters
title: OpenAIResponseInputToolFunction
description: Function tool configuration for OpenAI response inputs.
OpenAIResponseInputToolMCP:
properties:
type:
type: string
const: mcp
title: Type
default: mcp
server_label:
type: string
title: Server Label
server_url:
type: string
title: Server Url
headers:
title: Headers
additionalProperties: true
type: object
require_approval:
anyOf:
- type: string
const: always
- type: string
const: never
- $ref: '#/components/schemas/ApprovalFilter'
title: Require Approval
default: never
allowed_tools:
anyOf:
- items:
type: string
type: array
- $ref: '#/components/schemas/AllowedToolsFilter'
title: Allowed Tools
type: object
required:
- server_label
- server_url
title: OpenAIResponseInputToolMCP
description: Model Context Protocol (MCP) tool configuration for OpenAI response inputs.
OpenAIResponseInputToolWebSearch:
properties:
type:
anyOf:
- type: string
const: web_search
- type: string
const: web_search_preview
- type: string
const: web_search_preview_2025_03_11
title: Type
default: web_search
search_context_size:
title: Search Context Size
default: medium
type: string
pattern: ^low|medium|high$
type: object
title: OpenAIResponseInputToolWebSearch
description: Web search tool configuration for OpenAI response inputs.
OpenAIResponseMCPApprovalRequest:
properties:
arguments:
type: string
title: Arguments
id:
type: string
title: Id
name:
type: string
title: Name
server_label:
type: string
title: Server Label
type:
type: string
const: mcp_approval_request
title: Type
default: mcp_approval_request
type: object
required:
- arguments
- id
- name
- server_label
title: OpenAIResponseMCPApprovalRequest
description: A request for human approval of a tool invocation.
OpenAIResponseMCPApprovalResponse:
properties:
approval_request_id:
type: string
title: Approval Request Id
approve:
type: boolean
title: Approve
type:
type: string
const: mcp_approval_response
title: Type
default: mcp_approval_response
id:
title: Id
type: string
reason:
title: Reason
type: string
type: object
required:
- approval_request_id
- approve
title: OpenAIResponseMCPApprovalResponse
description: A response to an MCP approval request.
OpenAIResponseMessage-Input:
properties:
content:
anyOf:
- type: string
- items:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentText'
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentImage'
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentFile'
discriminator:
propertyName: type
mapping:
input_file: '#/components/schemas/OpenAIResponseInputMessageContentFile'
input_image: '#/components/schemas/OpenAIResponseInputMessageContentImage'
input_text: '#/components/schemas/OpenAIResponseInputMessageContentText'
type: array
- items:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseOutputMessageContentOutputText'
- $ref: '#/components/schemas/OpenAIResponseContentPartRefusal'
discriminator:
propertyName: type
mapping:
output_text: '#/components/schemas/OpenAIResponseOutputMessageContentOutputText'
refusal: '#/components/schemas/OpenAIResponseContentPartRefusal'
type: array
title: Content
role:
anyOf:
- type: string
const: system
- type: string
const: developer
- type: string
const: user
- type: string
const: assistant
title: Role
type:
type: string
const: message
title: Type
default: message
id:
title: Id
type: string
status:
title: Status
type: string
type: object
required:
- content
- role
title: OpenAIResponseMessage
description: "Corresponds to the various Message types in the Responses API.\nThey are all under one type because the Responses API gives them all\nthe same \"type\" value, and there is no way to tell them apart in certain\nscenarios."
OpenAIResponseMessage-Output:
properties:
content:
anyOf:
- type: string
- items:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentText'
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentImage'
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentFile'
discriminator:
propertyName: type
mapping:
input_file: '#/components/schemas/OpenAIResponseInputMessageContentFile'
input_image: '#/components/schemas/OpenAIResponseInputMessageContentImage'
input_text: '#/components/schemas/OpenAIResponseInputMessageContentText'
type: array
- items:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseOutputMessageContentOutputText'
- $ref: '#/components/schemas/OpenAIResponseContentPartRefusal'
discriminator:
propertyName: type
mapping:
output_text: '#/components/schemas/OpenAIResponseOutputMessageContentOutputText'
refusal: '#/components/schemas/OpenAIResponseContentPartRefusal'
type: array
title: Content
role:
anyOf:
- type: string
const: system
- type: string
const: developer
- type: string
const: user
- type: string
const: assistant
title: Role
type:
type: string
const: message
title: Type
default: message
id:
title: Id
type: string
status:
title: Status
type: string
type: object
required:
- content
- role
title: OpenAIResponseMessage
description: "Corresponds to the various Message types in the Responses API.\nThey are all under one type because the Responses API gives them all\nthe same \"type\" value, and there is no way to tell them apart in certain\nscenarios."
OpenAIResponseObject:
properties:
created_at:
type: integer
title: Created At
error:
$ref: '#/components/schemas/OpenAIResponseError'
id:
type: string
title: Id
model:
type: string
title: Model
object:
type: string
const: response
title: Object
default: response
output:
items:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseMessage-Output'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
discriminator:
propertyName: type
mapping:
file_search_call: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
mcp_approval_request: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
message: '#/components/schemas/OpenAIResponseMessage-Output'
web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
type: array
title: Output
parallel_tool_calls:
type: boolean
title: Parallel Tool Calls
default: false
previous_response_id:
title: Previous Response Id
type: string
prompt:
$ref: '#/components/schemas/OpenAIResponsePrompt'
status:
type: string
title: Status
temperature:
title: Temperature
type: number
text:
$ref: '#/components/schemas/OpenAIResponseText'
default:
format:
type: text
top_p:
title: Top P
type: number
tools:
title: Tools
items:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseInputToolWebSearch'
- $ref: '#/components/schemas/OpenAIResponseInputToolFileSearch'
- $ref: '#/components/schemas/OpenAIResponseInputToolFunction'
- $ref: '#/components/schemas/OpenAIResponseToolMCP'
discriminator:
propertyName: type
mapping:
file_search: '#/components/schemas/OpenAIResponseInputToolFileSearch'
function: '#/components/schemas/OpenAIResponseInputToolFunction'
mcp: '#/components/schemas/OpenAIResponseToolMCP'
web_search: '#/components/schemas/OpenAIResponseInputToolWebSearch'
web_search_preview: '#/components/schemas/OpenAIResponseInputToolWebSearch'
web_search_preview_2025_03_11: '#/components/schemas/OpenAIResponseInputToolWebSearch'
type: array
truncation:
title: Truncation
type: string
usage:
$ref: '#/components/schemas/OpenAIResponseUsage'
instructions:
title: Instructions
type: string
type: object
required:
- created_at
- id
- model
- output
- status
title: OpenAIResponseObject
description: Complete OpenAI response object containing generation results and metadata.
OpenAIResponseOutputMessageContentOutputText:
properties:
text:
type: string
title: Text
type:
type: string
const: output_text
title: Type
default: output_text
annotations:
items:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseAnnotationFileCitation'
- $ref: '#/components/schemas/OpenAIResponseAnnotationCitation'
- $ref: '#/components/schemas/OpenAIResponseAnnotationContainerFileCitation'
- $ref: '#/components/schemas/OpenAIResponseAnnotationFilePath'
discriminator:
propertyName: type
mapping:
container_file_citation: '#/components/schemas/OpenAIResponseAnnotationContainerFileCitation'
file_citation: '#/components/schemas/OpenAIResponseAnnotationFileCitation'
file_path: '#/components/schemas/OpenAIResponseAnnotationFilePath'
url_citation: '#/components/schemas/OpenAIResponseAnnotationCitation'
type: array
title: Annotations
type: object
required:
- text
title: OpenAIResponseOutputMessageContentOutputText
OpenAIResponseOutputMessageFileSearchToolCall:
properties:
id:
type: string
title: Id
queries:
items:
type: string
type: array
title: Queries
status:
type: string
title: Status
type:
type: string
const: file_search_call
title: Type
default: file_search_call
results:
title: Results
items:
$ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCallResults'
type: array
type: object
required:
- id
- queries
- status
title: OpenAIResponseOutputMessageFileSearchToolCall
description: File search tool call output message for OpenAI responses.
OpenAIResponseOutputMessageFileSearchToolCallResults:
properties:
attributes:
additionalProperties: true
type: object
title: Attributes
file_id:
type: string
title: File Id
filename:
type: string
title: Filename
score:
type: number
title: Score
text:
type: string
title: Text
type: object
required:
- attributes
- file_id
- filename
- score
- text
title: OpenAIResponseOutputMessageFileSearchToolCallResults
description: Search results returned by the file search operation.
OpenAIResponseOutputMessageFunctionToolCall:
properties:
call_id:
type: string
title: Call Id
name:
type: string
title: Name
arguments:
type: string
title: Arguments
type:
type: string
const: function_call
title: Type
default: function_call
id:
title: Id
type: string
status:
title: Status
type: string
type: object
required:
- call_id
- name
- arguments
title: OpenAIResponseOutputMessageFunctionToolCall
description: Function tool call output message for OpenAI responses.
OpenAIResponseOutputMessageMCPCall:
properties:
id:
type: string
title: Id
type:
type: string
const: mcp_call
title: Type
default: mcp_call
arguments:
type: string
title: Arguments
name:
type: string
title: Name
server_label:
type: string
title: Server Label
error:
title: Error
type: string
output:
title: Output
type: string
type: object
required:
- id
- arguments
- name
- server_label
title: OpenAIResponseOutputMessageMCPCall
description: Model Context Protocol (MCP) call output message for OpenAI responses.
OpenAIResponseOutputMessageMCPListTools:
properties:
id:
type: string
title: Id
type:
type: string
const: mcp_list_tools
title: Type
default: mcp_list_tools
server_label:
type: string
title: Server Label
tools:
items:
$ref: '#/components/schemas/MCPListToolsTool'
type: array
title: Tools
type: object
required:
- id
- server_label
- tools
title: OpenAIResponseOutputMessageMCPListTools
description: MCP list tools output message containing available tools from an MCP server.
OpenAIResponseOutputMessageWebSearchToolCall:
properties:
id:
type: string
title: Id
status:
type: string
title: Status
type:
type: string
const: web_search_call
title: Type
default: web_search_call
type: object
required:
- id
- status
title: OpenAIResponseOutputMessageWebSearchToolCall
description: Web search tool call output message for OpenAI responses.
OpenAIResponsePrompt:
properties:
id:
type: string
title: Id
variables:
title: Variables
additionalProperties:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentText'
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentImage'
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentFile'
discriminator:
propertyName: type
mapping:
input_file: '#/components/schemas/OpenAIResponseInputMessageContentFile'
input_image: '#/components/schemas/OpenAIResponseInputMessageContentImage'
input_text: '#/components/schemas/OpenAIResponseInputMessageContentText'
type: object
version:
title: Version
type: string
type: object
required:
- id
title: OpenAIResponsePrompt
description: OpenAI compatible Prompt object that is used in OpenAI responses.
OpenAIResponseText:
properties:
format:
$ref: '#/components/schemas/OpenAIResponseTextFormat'
type: object
title: OpenAIResponseText
description: Text response configuration for OpenAI responses.
OpenAIResponseTextFormat:
properties:
type:
anyOf:
- type: string
const: text
- type: string
const: json_schema
- type: string
const: json_object
title: Type
name:
title: Name
type: string
schema:
title: Schema
additionalProperties: true
type: object
description:
title: Description
type: string
strict:
title: Strict
type: boolean
type: object
title: OpenAIResponseTextFormat
description: Configuration for Responses API text format.
OpenAIResponseToolMCP:
properties:
type:
type: string
const: mcp
title: Type
default: mcp
server_label:
type: string
title: Server Label
allowed_tools:
anyOf:
- items:
type: string
type: array
- $ref: '#/components/schemas/AllowedToolsFilter'
title: Allowed Tools
type: object
required:
- server_label
title: OpenAIResponseToolMCP
description: Model Context Protocol (MCP) tool configuration for OpenAI response object.
OpenAIResponseUsage:
properties:
input_tokens:
type: integer
title: Input Tokens
output_tokens:
type: integer
title: Output Tokens
total_tokens:
type: integer
title: Total Tokens
input_tokens_details:
$ref: '#/components/schemas/OpenAIResponseUsageInputTokensDetails'
output_tokens_details:
$ref: '#/components/schemas/OpenAIResponseUsageOutputTokensDetails'
type: object
required:
- input_tokens
- output_tokens
- total_tokens
title: OpenAIResponseUsage
description: Usage information for OpenAI response.
OpenAIResponseUsageInputTokensDetails:
properties:
cached_tokens:
title: Cached Tokens
type: integer
type: object
title: OpenAIResponseUsageInputTokensDetails
description: Token details for input tokens in OpenAI response usage.
OpenAIResponseUsageOutputTokensDetails:
properties:
reasoning_tokens:
title: Reasoning Tokens
type: integer
type: object
title: OpenAIResponseUsageOutputTokensDetails
description: Token details for output tokens in OpenAI response usage.
OpenAISystemMessageParam:
properties:
role:
type: string
const: system
title: Role
default: system
content:
anyOf:
- type: string
- items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
type: array
title: Content
name:
title: Name
type: string
type: object
required:
- content
title: OpenAISystemMessageParam
description: A system message providing instructions or context to the model.
OpenAITokenLogProb:
properties:
token:
type: string
title: Token
bytes:
title: Bytes
items:
type: integer
type: array
logprob:
type: number
title: Logprob
top_logprobs:
items:
$ref: '#/components/schemas/OpenAITopLogProb'
type: array
title: Top Logprobs
type: object
required:
- token
- logprob
- top_logprobs
title: OpenAITokenLogProb
description: The log probability for a token from an OpenAI-compatible chat completion response.
OpenAIToolMessageParam:
properties:
role:
type: string
const: tool
title: Role
default: tool
tool_call_id:
type: string
title: Tool Call Id
content:
anyOf:
- type: string
- items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
type: array
title: Content
type: object
required:
- tool_call_id
- content
title: OpenAIToolMessageParam
description: A message representing the result of a tool invocation in an OpenAI-compatible chat completion request.
OpenAITopLogProb:
properties:
token:
type: string
title: Token
bytes:
title: Bytes
items:
type: integer
type: array
logprob:
type: number
title: Logprob
type: object
required:
- token
- logprob
title: OpenAITopLogProb
description: The top log probability for a token from an OpenAI-compatible chat completion response.
OpenAIUserMessageParam-Input:
properties:
role:
type: string
const: user
title: Role
default: user
content:
anyOf:
- type: string
- items:
oneOf:
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
- $ref: '#/components/schemas/OpenAIFile'
discriminator:
propertyName: type
mapping:
file: '#/components/schemas/OpenAIFile'
image_url: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
text: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
type: array
title: Content
name:
title: Name
type: string
type: object
required:
- content
title: OpenAIUserMessageParam
description: A message from the user in an OpenAI-compatible chat completion request.
OpenAIUserMessageParam-Output:
properties:
role:
type: string
const: user
title: Role
default: user
content:
anyOf:
- type: string
- items:
oneOf:
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
- $ref: '#/components/schemas/OpenAIFile'
discriminator:
propertyName: type
mapping:
file: '#/components/schemas/OpenAIFile'
image_url: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
text: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
type: array
title: Content
name:
title: Name
type: string
type: object
required:
- content
title: OpenAIUserMessageParam
description: A message from the user in an OpenAI-compatible chat completion request.
OptimizerConfig:
properties:
optimizer_type:
$ref: '#/components/schemas/OptimizerType'
lr:
type: number
title: Lr
weight_decay:
type: number
title: Weight Decay
num_warmup_steps:
type: integer
title: Num Warmup Steps
type: object
required:
- optimizer_type
- lr
- weight_decay
- num_warmup_steps
title: OptimizerConfig
description: Configuration parameters for the optimization algorithm.
OptimizerType:
type: string
enum:
- adam
- adamw
- sgd
title: OptimizerType
description: Available optimizer algorithms for training.
Order:
type: string
enum:
- asc
- desc
title: Order
description: Sort order for paginated responses.
OutputTokensDetails:
properties:
reasoning_tokens:
type: integer
title: Reasoning Tokens
additionalProperties: true
type: object
required:
- reasoning_tokens
title: OutputTokensDetails
PostTrainingJob:
properties:
job_uuid:
type: string
title: Job Uuid
type: object
required:
- job_uuid
title: PostTrainingJob
Prompt:
properties:
prompt:
title: Prompt
description: The system prompt with variable placeholders
type: string
version:
type: integer
minimum: 1.0
title: Version
description: Version (integer starting at 1, incremented on save)
prompt_id:
type: string
title: Prompt Id
description: Unique identifier in format 'pmpt_<48-digit-hash>'
variables:
items:
type: string
type: array
title: Variables
description: List of variable names that can be used in the prompt template
is_default:
type: boolean
title: Is Default
description: Boolean indicating whether this version is the default version
default: false
type: object
required:
- version
- prompt_id
title: Prompt
description: A prompt resource representing a stored OpenAI Compatible prompt template in Llama Stack.
ProviderInfo:
properties:
api:
type: string
title: Api
provider_id:
type: string
title: Provider Id
provider_type:
type: string
title: Provider Type
config:
additionalProperties: true
type: object
title: Config
health:
additionalProperties: true
type: object
title: Health
type: object
required:
- api
- provider_id
- provider_type
- config
- health
title: ProviderInfo
description: Information about a registered provider including its configuration and health status.
QueryChunksResponse:
properties:
chunks:
items:
$ref: '#/components/schemas/Chunk-Output'
type: array
title: Chunks
scores:
items:
type: number
type: array
title: Scores
type: object
required:
- chunks
- scores
title: QueryChunksResponse
description: Response from querying chunks in a vector database.
RAGQueryConfig:
properties:
query_generator_config:
oneOf:
- $ref: '#/components/schemas/DefaultRAGQueryGeneratorConfig'
- $ref: '#/components/schemas/LLMRAGQueryGeneratorConfig'
title: Query Generator Config
default:
type: default
separator: ' '
discriminator:
propertyName: type
mapping:
default: '#/components/schemas/DefaultRAGQueryGeneratorConfig'
llm: '#/components/schemas/LLMRAGQueryGeneratorConfig'
max_tokens_in_context:
type: integer
title: Max Tokens In Context
default: 4096
max_chunks:
type: integer
title: Max Chunks
default: 5
chunk_template:
type: string
title: Chunk Template
default: "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n"
mode:
default: vector
$ref: '#/components/schemas/RAGSearchMode'
ranker:
title: Ranker
oneOf:
- $ref: '#/components/schemas/RRFRanker'
- $ref: '#/components/schemas/WeightedRanker'
discriminator:
propertyName: type
mapping:
rrf: '#/components/schemas/RRFRanker'
weighted: '#/components/schemas/WeightedRanker'
type: object
title: RAGQueryConfig
description: Configuration for the RAG query generation.
RAGQueryResult:
properties:
content:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
type: array
title: Content
metadata:
additionalProperties: true
type: object
title: Metadata
type: object
title: RAGQueryResult
description: Result of a RAG query containing retrieved content and metadata.
RAGSearchMode:
type: string
enum:
- vector
- keyword
- hybrid
title: RAGSearchMode
description: "Search modes for RAG query retrieval:\n- VECTOR: Uses vector similarity search for semantic matching\n- KEYWORD: Uses keyword-based search for exact matching\n- HYBRID: Combines both vector and keyword search for better results"
RRFRanker:
properties:
type:
type: string
const: rrf
title: Type
default: rrf
impact_factor:
type: number
title: Impact Factor
default: 60.0
minimum: 0.0
type: object
title: RRFRanker
description: Reciprocal Rank Fusion (RRF) ranker configuration.
RegexParserScoringFnParams:
properties:
type:
type: string
const: regex_parser
title: Type
default: regex_parser
parsing_regexes:
items:
type: string
type: array
title: Parsing Regexes
description: Regex to extract the answer from generated response
aggregation_functions:
items:
$ref: '#/components/schemas/AggregationFunctionType'
type: array
title: Aggregation Functions
description: Aggregation functions to apply to the scores of each row
type: object
title: RegexParserScoringFnParams
description: Parameters for regex parser scoring function configuration.
RerankData:
properties:
index:
type: integer
title: Index
relevance_score:
type: number
title: Relevance Score
type: object
required:
- index
- relevance_score
title: RerankData
description: A single rerank result from a reranking response.
RerankResponse:
properties:
data:
items:
$ref: '#/components/schemas/RerankData'
type: array
title: Data
type: object
required:
- data
title: RerankResponse
description: Response from a reranking request.
RouteInfo:
properties:
route:
type: string
title: Route
method:
type: string
title: Method
provider_types:
items:
type: string
type: array
title: Provider Types
type: object
required:
- route
- method
- provider_types
title: RouteInfo
description: Information about an API route including its path, method, and implementing providers.
RowsDataSource:
properties:
type:
type: string
const: rows
title: Type
default: rows
rows:
items:
additionalProperties: true
type: object
type: array
title: Rows
type: object
required:
- rows
title: RowsDataSource
description: A dataset stored in rows.
RunShieldResponse:
properties:
violation:
$ref: '#/components/schemas/SafetyViolation'
type: object
title: RunShieldResponse
description: Response from running a safety shield.
SafetyViolation:
properties:
violation_level:
$ref: '#/components/schemas/ViolationLevel'
user_message:
title: User Message
type: string
metadata:
additionalProperties: true
type: object
title: Metadata
type: object
required:
- violation_level
title: SafetyViolation
description: Details of a safety violation detected by content moderation.
SamplingParams:
properties:
strategy:
oneOf:
- $ref: '#/components/schemas/GreedySamplingStrategy'
- $ref: '#/components/schemas/TopPSamplingStrategy'
- $ref: '#/components/schemas/TopKSamplingStrategy'
title: Strategy
discriminator:
propertyName: type
mapping:
greedy: '#/components/schemas/GreedySamplingStrategy'
top_k: '#/components/schemas/TopKSamplingStrategy'
top_p: '#/components/schemas/TopPSamplingStrategy'
max_tokens:
title: Max Tokens
type: integer
repetition_penalty:
title: Repetition Penalty
default: 1.0
type: number
stop:
title: Stop
items:
type: string
type: array
type: object
title: SamplingParams
description: Sampling parameters.
ScoreBatchResponse:
properties:
dataset_id:
title: Dataset Id
type: string
results:
additionalProperties:
$ref: '#/components/schemas/ScoringResult'
type: object
title: Results
type: object
required:
- results
title: ScoreBatchResponse
description: Response from batch scoring operations on datasets.
ScoreResponse:
properties:
results:
additionalProperties:
$ref: '#/components/schemas/ScoringResult'
type: object
title: Results
type: object
required:
- results
title: ScoreResponse
description: The response from scoring.
ScoringFn-Output:
properties:
identifier:
type: string
title: Identifier
description: Unique identifier for this resource in llama stack
provider_resource_id:
title: Provider Resource Id
description: Unique identifier for this resource in the provider
type: string
provider_id:
type: string
title: Provider Id
description: ID of the provider that owns this resource
type:
type: string
const: scoring_function
title: Type
default: scoring_function
description:
title: Description
type: string
metadata:
additionalProperties: true
type: object
title: Metadata
description: Any additional metadata for this definition
return_type:
oneOf:
- $ref: '#/components/schemas/StringType'
- $ref: '#/components/schemas/NumberType'
- $ref: '#/components/schemas/BooleanType'
- $ref: '#/components/schemas/ArrayType'
- $ref: '#/components/schemas/ObjectType'
- $ref: '#/components/schemas/JsonType'
- $ref: '#/components/schemas/UnionType'
- $ref: '#/components/schemas/ChatCompletionInputType'
- $ref: '#/components/schemas/CompletionInputType'
- $ref: '#/components/schemas/AgentTurnInputType'
title: Return Type
description: The return type of the deterministic function
discriminator:
propertyName: type
mapping:
agent_turn_input: '#/components/schemas/AgentTurnInputType'
array: '#/components/schemas/ArrayType'
boolean: '#/components/schemas/BooleanType'
chat_completion_input: '#/components/schemas/ChatCompletionInputType'
completion_input: '#/components/schemas/CompletionInputType'
json: '#/components/schemas/JsonType'
number: '#/components/schemas/NumberType'
object: '#/components/schemas/ObjectType'
string: '#/components/schemas/StringType'
union: '#/components/schemas/UnionType'
params:
title: Params
description: The parameters for the scoring function for benchmark eval, these can be overridden for app eval
oneOf:
- $ref: '#/components/schemas/LLMAsJudgeScoringFnParams'
- $ref: '#/components/schemas/RegexParserScoringFnParams'
- $ref: '#/components/schemas/BasicScoringFnParams'
discriminator:
propertyName: type
mapping:
basic: '#/components/schemas/BasicScoringFnParams'
llm_as_judge: '#/components/schemas/LLMAsJudgeScoringFnParams'
regex_parser: '#/components/schemas/RegexParserScoringFnParams'
type: object
required:
- identifier
- provider_id
- return_type
title: ScoringFn
description: A scoring function resource for evaluating model outputs.
ScoringResult:
properties:
score_rows:
items:
additionalProperties: true
type: object
type: array
title: Score Rows
aggregated_results:
additionalProperties: true
type: object
title: Aggregated Results
type: object
required:
- score_rows
- aggregated_results
title: ScoringResult
description: A scoring result for a single row.
SearchRankingOptions:
properties:
ranker:
title: Ranker
type: string
score_threshold:
title: Score Threshold
default: 0.0
type: number
type: object
title: SearchRankingOptions
description: Options for ranking and filtering search results.
Shield:
properties:
identifier:
type: string
title: Identifier
description: Unique identifier for this resource in llama stack
provider_resource_id:
title: Provider Resource Id
description: Unique identifier for this resource in the provider
type: string
provider_id:
type: string
title: Provider Id
description: ID of the provider that owns this resource
type:
type: string
const: shield
title: Type
default: shield
params:
title: Params
additionalProperties: true
type: object
type: object
required:
- identifier
- provider_id
title: Shield
description: A safety shield resource that can be used to check content.
ShieldCallStep-Output:
properties:
turn_id:
type: string
title: Turn Id
step_id:
type: string
title: Step Id
started_at:
title: Started At
type: string
format: date-time
completed_at:
title: Completed At
type: string
format: date-time
step_type:
type: string
const: shield_call
title: Step Type
default: shield_call
violation:
$ref: '#/components/schemas/SafetyViolation'
type: object
required:
- turn_id
- step_id
- violation
title: ShieldCallStep
description: A shield call step in an agent turn.
StopReason:
type: string
enum:
- end_of_turn
- end_of_message
- out_of_tokens
title: StopReason
StringType:
properties:
type:
type: string
const: string
title: Type
default: string
type: object
title: StringType
description: Parameter type for string values.
SystemMessage:
properties:
role:
type: string
const: system
title: Role
default: system
content:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Input'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Input'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Input'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Input'
text: '#/components/schemas/TextContentItem'
type: array
title: Content
type: object
required:
- content
title: SystemMessage
description: A system message providing instructions or context to the model.
SystemMessageBehavior:
type: string
enum:
- append
- replace
title: SystemMessageBehavior
description: Config for how to override the default system prompt.
TextContentItem:
properties:
type:
type: string
const: text
title: Type
default: text
text:
type: string
title: Text
type: object
required:
- text
title: TextContentItem
description: A text content item
ToolCall:
properties:
call_id:
type: string
title: Call Id
tool_name:
anyOf:
- $ref: '#/components/schemas/BuiltinTool'
- type: string
title: Tool Name
arguments:
type: string
title: Arguments
type: object
required:
- call_id
- tool_name
- arguments
title: ToolCall
ToolChoice:
type: string
enum:
- auto
- required
- none
title: ToolChoice
description: Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model.
ToolConfig:
properties:
tool_choice:
anyOf:
- $ref: '#/components/schemas/ToolChoice'
- type: string
title: Tool Choice
default: auto
tool_prompt_format:
$ref: '#/components/schemas/ToolPromptFormat'
system_message_behavior:
default: append
$ref: '#/components/schemas/SystemMessageBehavior'
type: object
title: ToolConfig
description: Configuration for tool use.
ToolDef:
properties:
toolgroup_id:
title: Toolgroup Id
type: string
name:
type: string
title: Name
description:
title: Description
type: string
input_schema:
title: Input Schema
additionalProperties: true
type: object
output_schema:
title: Output Schema
additionalProperties: true
type: object
metadata:
title: Metadata
additionalProperties: true
type: object
type: object
required:
- name
title: ToolDef
description: Tool definition used in runtime contexts.
ToolExecutionStep-Output:
properties:
turn_id:
type: string
title: Turn Id
step_id:
type: string
title: Step Id
started_at:
title: Started At
type: string
format: date-time
completed_at:
title: Completed At
type: string
format: date-time
step_type:
type: string
const: tool_execution
title: Step Type
default: tool_execution
tool_calls:
items:
$ref: '#/components/schemas/ToolCall'
type: array
title: Tool Calls
tool_responses:
items:
$ref: '#/components/schemas/ToolResponse-Output'
type: array
title: Tool Responses
type: object
required:
- turn_id
- step_id
- tool_calls
- tool_responses
title: ToolExecutionStep
description: A tool execution step in an agent turn.
ToolGroup:
properties:
identifier:
type: string
title: Identifier
description: Unique identifier for this resource in llama stack
provider_resource_id:
title: Provider Resource Id
description: Unique identifier for this resource in the provider
type: string
provider_id:
type: string
title: Provider Id
description: ID of the provider that owns this resource
type:
type: string
const: tool_group
title: Type
default: tool_group
mcp_endpoint:
$ref: '#/components/schemas/URL'
args:
title: Args
additionalProperties: true
type: object
type: object
required:
- identifier
- provider_id
title: ToolGroup
description: A group of related tools managed together.
ToolInvocationResult:
properties:
content:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
type: array
title: Content
error_message:
title: Error Message
type: string
error_code:
title: Error Code
type: integer
metadata:
title: Metadata
additionalProperties: true
type: object
type: object
title: ToolInvocationResult
description: Result of a tool invocation.
ToolPromptFormat:
type: string
enum:
- json
- function_tag
- python_list
title: ToolPromptFormat
description: Prompt format for calling custom / zero shot tools.
ToolResponse-Input:
properties:
call_id:
type: string
title: Call Id
tool_name:
anyOf:
- $ref: '#/components/schemas/BuiltinTool'
- type: string
title: Tool Name
content:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Input'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Input'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Input'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Input'
text: '#/components/schemas/TextContentItem'
type: array
title: Content
metadata:
title: Metadata
additionalProperties: true
type: object
type: object
required:
- call_id
- tool_name
- content
title: ToolResponse
description: Response from a tool invocation.
ToolResponse-Output:
properties:
call_id:
type: string
title: Call Id
tool_name:
anyOf:
- $ref: '#/components/schemas/BuiltinTool'
- type: string
title: Tool Name
content:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
type: array
title: Content
metadata:
title: Metadata
additionalProperties: true
type: object
type: object
required:
- call_id
- tool_name
- content
title: ToolResponse
description: Response from a tool invocation.
ToolResponseMessage-Output:
properties:
role:
type: string
const: tool
title: Role
default: tool
call_id:
type: string
title: Call Id
content:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
type: array
title: Content
type: object
required:
- call_id
- content
title: ToolResponseMessage
description: A message representing the result of a tool invocation.
TopKSamplingStrategy:
properties:
type:
type: string
const: top_k
title: Type
default: top_k
top_k:
type: integer
minimum: 1.0
title: Top K
type: object
required:
- top_k
title: TopKSamplingStrategy
description: Top-k sampling strategy that restricts sampling to the k most likely tokens.
TopPSamplingStrategy:
properties:
type:
type: string
const: top_p
title: Type
default: top_p
temperature:
title: Temperature
type: number
minimum: 0.0
top_p:
title: Top P
default: 0.95
type: number
type: object
required:
- temperature
title: TopPSamplingStrategy
description: Top-p (nucleus) sampling strategy that samples from the smallest set of tokens with cumulative probability >= p.
TrainingConfig:
properties:
n_epochs:
type: integer
title: N Epochs
max_steps_per_epoch:
type: integer
title: Max Steps Per Epoch
default: 1
gradient_accumulation_steps:
type: integer
title: Gradient Accumulation Steps
default: 1
max_validation_steps:
title: Max Validation Steps
default: 1
type: integer
data_config:
$ref: '#/components/schemas/DataConfig'
optimizer_config:
$ref: '#/components/schemas/OptimizerConfig'
efficiency_config:
$ref: '#/components/schemas/EfficiencyConfig'
dtype:
title: Dtype
default: bf16
type: string
type: object
required:
- n_epochs
title: TrainingConfig
description: Comprehensive configuration for the training process.
Turn:
properties:
turn_id:
type: string
title: Turn Id
session_id:
type: string
title: Session Id
input_messages:
items:
anyOf:
- $ref: '#/components/schemas/UserMessage-Output'
- $ref: '#/components/schemas/ToolResponseMessage-Output'
type: array
title: Input Messages
steps:
items:
oneOf:
- $ref: '#/components/schemas/InferenceStep-Output'
- $ref: '#/components/schemas/ToolExecutionStep-Output'
- $ref: '#/components/schemas/ShieldCallStep-Output'
- $ref: '#/components/schemas/MemoryRetrievalStep-Output'
discriminator:
propertyName: step_type
mapping:
inference: '#/components/schemas/InferenceStep-Output'
memory_retrieval: '#/components/schemas/MemoryRetrievalStep-Output'
shield_call: '#/components/schemas/ShieldCallStep-Output'
tool_execution: '#/components/schemas/ToolExecutionStep-Output'
type: array
title: Steps
output_message:
$ref: '#/components/schemas/CompletionMessage-Output'
output_attachments:
title: Output Attachments
items:
$ref: '#/components/schemas/Attachment-Output'
type: array
started_at:
type: string
format: date-time
title: Started At
completed_at:
title: Completed At
type: string
format: date-time
type: object
required:
- turn_id
- session_id
- input_messages
- steps
- output_message
- started_at
title: Turn
description: A single turn in an interaction with an Agentic System.
URIDataSource:
properties:
type:
type: string
const: uri
title: Type
default: uri
uri:
type: string
title: Uri
type: object
required:
- uri
title: URIDataSource
description: A dataset that can be obtained from a URI.
URL:
properties:
uri:
type: string
title: Uri
type: object
required:
- uri
title: URL
description: A URL reference to external content.
UnionType:
properties:
type:
type: string
const: union
title: Type
default: union
type: object
title: UnionType
description: Parameter type for union values.
UserMessage-Input:
properties:
role:
type: string
const: user
title: Role
default: user
content:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Input'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Input'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Input'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Input'
text: '#/components/schemas/TextContentItem'
type: array
title: Content
context:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Input'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Input'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Input'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Input'
text: '#/components/schemas/TextContentItem'
type: array
title: Context
type: object
required:
- content
title: UserMessage
description: A message from the user in a chat conversation.
UserMessage-Output:
properties:
role:
type: string
const: user
title: Role
default: user
content:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
type: array
title: Content
context:
anyOf:
- type: string
- oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
- items:
oneOf:
- $ref: '#/components/schemas/ImageContentItem-Output'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem-Output'
text: '#/components/schemas/TextContentItem'
type: array
title: Context
type: object
required:
- content
title: UserMessage
description: A message from the user in a chat conversation.
VectorStoreChunkingStrategyAuto:
properties:
type:
type: string
const: auto
title: Type
default: auto
type: object
title: VectorStoreChunkingStrategyAuto
description: Automatic chunking strategy for vector store files.
VectorStoreChunkingStrategyStatic:
properties:
type:
type: string
const: static
title: Type
default: static
static:
$ref: '#/components/schemas/VectorStoreChunkingStrategyStaticConfig'
type: object
required:
- static
title: VectorStoreChunkingStrategyStatic
description: Static chunking strategy with configurable parameters.
VectorStoreChunkingStrategyStaticConfig:
properties:
chunk_overlap_tokens:
type: integer
title: Chunk Overlap Tokens
default: 400
max_chunk_size_tokens:
type: integer
maximum: 4096.0
minimum: 100.0
title: Max Chunk Size Tokens
default: 800
type: object
title: VectorStoreChunkingStrategyStaticConfig
description: Configuration for static chunking strategy.
VectorStoreContent:
properties:
type:
type: string
const: text
title: Type
text:
type: string
title: Text
type: object
required:
- type
- text
title: VectorStoreContent
description: Content item from a vector store file or search result.
VectorStoreFileBatchObject:
properties:
id:
type: string
title: Id
object:
type: string
title: Object
default: vector_store.file_batch
created_at:
type: integer
title: Created At
vector_store_id:
type: string
title: Vector Store Id
status:
anyOf:
- type: string
const: completed
- type: string
const: in_progress
- type: string
const: cancelled
- type: string
const: failed
title: Status
file_counts:
$ref: '#/components/schemas/VectorStoreFileCounts'
type: object
required:
- id
- created_at
- vector_store_id
- status
- file_counts
title: VectorStoreFileBatchObject
description: OpenAI Vector Store File Batch object.
VectorStoreFileCounts:
properties:
completed:
type: integer
title: Completed
cancelled:
type: integer
title: Cancelled
failed:
type: integer
title: Failed
in_progress:
type: integer
title: In Progress
total:
type: integer
title: Total
type: object
required:
- completed
- cancelled
- failed
- in_progress
- total
title: VectorStoreFileCounts
description: File processing status counts for a vector store.
VectorStoreFileLastError:
properties:
code:
anyOf:
- type: string
const: server_error
- type: string
const: rate_limit_exceeded
title: Code
message:
type: string
title: Message
type: object
required:
- code
- message
title: VectorStoreFileLastError
description: Error information for failed vector store file processing.
VectorStoreFileObject:
properties:
id:
type: string
title: Id
object:
type: string
title: Object
default: vector_store.file
attributes:
additionalProperties: true
type: object
title: Attributes
chunking_strategy:
oneOf:
- $ref: '#/components/schemas/VectorStoreChunkingStrategyAuto'
- $ref: '#/components/schemas/VectorStoreChunkingStrategyStatic'
title: Chunking Strategy
discriminator:
propertyName: type
mapping:
auto: '#/components/schemas/VectorStoreChunkingStrategyAuto'
static: '#/components/schemas/VectorStoreChunkingStrategyStatic'
created_at:
type: integer
title: Created At
last_error:
$ref: '#/components/schemas/VectorStoreFileLastError'
status:
anyOf:
- type: string
const: completed
- type: string
const: in_progress
- type: string
const: cancelled
- type: string
const: failed
title: Status
usage_bytes:
type: integer
title: Usage Bytes
default: 0
vector_store_id:
type: string
title: Vector Store Id
type: object
required:
- id
- chunking_strategy
- created_at
- status
- vector_store_id
title: VectorStoreFileObject
description: OpenAI Vector Store File object.
VectorStoreObject:
properties:
id:
type: string
title: Id
object:
type: string
title: Object
default: vector_store
created_at:
type: integer
title: Created At
name:
title: Name
type: string
usage_bytes:
type: integer
title: Usage Bytes
default: 0
file_counts:
$ref: '#/components/schemas/VectorStoreFileCounts'
status:
type: string
title: Status
default: completed
expires_after:
title: Expires After
additionalProperties: true
type: object
expires_at:
title: Expires At
type: integer
last_active_at:
title: Last Active At
type: integer
metadata:
additionalProperties: true
type: object
title: Metadata
type: object
required:
- id
- created_at
- file_counts
title: VectorStoreObject
description: OpenAI Vector Store object.
VectorStoreSearchResponse:
properties:
file_id:
type: string
title: File Id
filename:
type: string
title: Filename
score:
type: number
title: Score
attributes:
title: Attributes
additionalProperties:
anyOf:
- type: string
- type: number
- type: boolean
type: object
content:
items:
$ref: '#/components/schemas/VectorStoreContent'
type: array
title: Content
type: object
required:
- file_id
- filename
- score
- content
title: VectorStoreSearchResponse
description: Response from searching a vector store.
VectorStoreSearchResponsePage:
properties:
object:
type: string
title: Object
default: vector_store.search_results.page
search_query:
type: string
title: Search Query
data:
items:
$ref: '#/components/schemas/VectorStoreSearchResponse'
type: array
title: Data
has_more:
type: boolean
title: Has More
default: false
next_page:
title: Next Page
type: string
type: object
required:
- search_query
- data
title: VectorStoreSearchResponsePage
description: Paginated response from searching a vector store.
VersionInfo:
properties:
version:
type: string
title: Version
type: object
required:
- version
title: VersionInfo
description: Version information for the service.
ViolationLevel:
type: string
enum:
- info
- warn
- error
title: ViolationLevel
description: Severity level of a safety violation.
WeightedRanker:
properties:
type:
type: string
const: weighted
title: Type
default: weighted
alpha:
type: number
maximum: 1.0
minimum: 0.0
title: Alpha
description: Weight factor between 0 and 1. 0 means only keyword scores, 1 means only vector scores.
default: 0.5
type: object
title: WeightedRanker
description: Weighted ranker configuration that combines vector and keyword scores.
_URLOrData:
properties:
url:
$ref: '#/components/schemas/URL'
data:
contentEncoding: base64
title: Data
type: string
type: object
title: _URLOrData
description: A URL or a base64 encoded string
__main_____agents_agent_id_session_Request:
properties:
agent_id:
type: string
title: Agent Id
session_name:
type: string
title: Session Name
type: object
required:
- agent_id
- session_name
title: _agents_agent_id_session_Request
__main_____agents_agent_id_session_session_id_turn_Request:
properties:
agent_id:
type: string
title: Agent Id
session_id:
type: string
title: Session Id
messages:
$ref: '#/components/schemas/UserMessage-Input'
stream:
type: boolean
title: Stream
default: false
documents:
$ref: '#/components/schemas/Document'
toolgroups:
anyOf:
- type: string
- $ref: '#/components/schemas/AgentToolGroupWithArgs'
title: Toolgroups
tool_config:
$ref: '#/components/schemas/ToolConfig'
type: object
required:
- agent_id
- session_id
- messages
- documents
- toolgroups
- tool_config
title: _agents_agent_id_session_session_id_turn_Request
__main_____agents_agent_id_session_session_id_turn_turn_id_resume_Request:
properties:
agent_id:
type: string
title: Agent Id
session_id:
type: string
title: Session Id
turn_id:
type: string
title: Turn Id
tool_responses:
$ref: '#/components/schemas/ToolResponse-Input'
stream:
type: boolean
title: Stream
default: false
type: object
required:
- agent_id
- session_id
- turn_id
- tool_responses
title: _agents_agent_id_session_session_id_turn_turn_id_resume_Request
__main_____datasets_Request:
properties:
purpose:
$ref: '#/components/schemas/DatasetPurpose'
metadata:
type: string
title: Metadata
dataset_id:
type: string
title: Dataset Id
type: object
required:
- purpose
- metadata
- dataset_id
title: _datasets_Request
_batches_Request:
properties:
input_file_id:
type: string
title: Input File Id
endpoint:
type: string
title: Endpoint
completion_window:
type: string
title: Completion Window
metadata:
type: string
title: Metadata
idempotency_key:
type: string
title: Idempotency Key
type: object
required:
- input_file_id
- endpoint
- completion_window
- metadata
- idempotency_key
title: _batches_Request
_batches_batch_id_cancel_Request:
properties:
batch_id:
type: string
title: Batch Id
type: object
required:
- batch_id
title: _batches_batch_id_cancel_Request
_conversations_Request:
properties:
items:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseMessage-Input'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
- $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalResponse'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
title: Items
discriminator:
propertyName: type
mapping:
file_search_call: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
function_call_output: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
mcp_approval_request: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
mcp_approval_response: '#/components/schemas/OpenAIResponseMCPApprovalResponse'
mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
message: '#/components/schemas/OpenAIResponseMessage-Input'
web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
metadata:
type: string
title: Metadata
type: object
required:
- items
- metadata
title: _conversations_Request
_conversations_conversation_id_Request:
properties:
conversation_id:
type: string
title: Conversation Id
metadata:
type: string
title: Metadata
type: object
required:
- conversation_id
- metadata
title: _conversations_conversation_id_Request
_conversations_conversation_id_items_Request:
properties:
conversation_id:
type: string
title: Conversation Id
items:
anyOf:
- $ref: '#/components/schemas/OpenAIResponseMessage-Input'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
- $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalResponse'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
title: Items
type: object
required:
- conversation_id
- items
title: _conversations_conversation_id_items_Request
_inference_rerank_Request:
properties:
model:
type: string
title: Model
query:
type: string
title: Query
items:
type: string
title: Items
max_num_results:
type: integer
title: Max Num Results
type: object
required:
- model
- query
- items
- max_num_results
title: _inference_rerank_Request
_models_Request:
properties:
model_id:
type: string
title: Model Id
provider_model_id:
type: string
title: Provider Model Id
provider_id:
type: string
title: Provider Id
metadata:
type: string
title: Metadata
model_type:
$ref: '#/components/schemas/ModelType'
type: object
required:
- model_id
- provider_model_id
- provider_id
- metadata
- model_type
title: _models_Request
_moderations_Request:
properties:
input:
type: string
title: Input
model:
type: string
title: Model
type: object
required:
- input
- model
title: _moderations_Request
_prompts_Request:
properties:
prompt:
type: string
title: Prompt
variables:
type: string
title: Variables
type: object
required:
- prompt
- variables
title: _prompts_Request
_prompts_prompt_id_Request:
properties:
prompt_id:
type: string
title: Prompt Id
prompt:
type: string
title: Prompt
version:
type: integer
title: Version
variables:
type: string
title: Variables
set_as_default:
type: boolean
title: Set As Default
default: true
type: object
required:
- prompt_id
- prompt
- version
- variables
title: _prompts_prompt_id_Request
_prompts_prompt_id_set_default_version_Request:
properties:
prompt_id:
type: string
title: Prompt Id
version:
type: integer
title: Version
type: object
required:
- prompt_id
- version
title: _prompts_prompt_id_set_default_version_Request
_responses_Request:
properties:
input:
type: string
title: Input
model:
type: string
title: Model
prompt:
$ref: '#/components/schemas/OpenAIResponsePrompt'
instructions:
type: string
title: Instructions
previous_response_id:
type: string
title: Previous Response Id
conversation:
type: string
title: Conversation
store:
type: boolean
title: Store
default: true
stream:
type: boolean
title: Stream
default: false
temperature:
type: number
title: Temperature
text:
$ref: '#/components/schemas/OpenAIResponseText'
tools:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseInputToolWebSearch'
- $ref: '#/components/schemas/OpenAIResponseInputToolFileSearch'
- $ref: '#/components/schemas/OpenAIResponseInputToolFunction'
- $ref: '#/components/schemas/OpenAIResponseInputToolMCP'
title: Tools
discriminator:
propertyName: type
mapping:
file_search: '#/components/schemas/OpenAIResponseInputToolFileSearch'
function: '#/components/schemas/OpenAIResponseInputToolFunction'
mcp: '#/components/schemas/OpenAIResponseInputToolMCP'
web_search: '#/components/schemas/OpenAIResponseInputToolWebSearch'
web_search_preview: '#/components/schemas/OpenAIResponseInputToolWebSearch'
web_search_preview_2025_03_11: '#/components/schemas/OpenAIResponseInputToolWebSearch'
include:
type: string
title: Include
max_infer_iters:
type: integer
title: Max Infer Iters
default: 10
type: object
required:
- input
- model
- prompt
- instructions
- previous_response_id
- conversation
- temperature
- text
- tools
- include
title: _responses_Request
_scoring_score_Request:
properties:
input_rows:
type: string
title: Input Rows
scoring_functions:
type: string
title: Scoring Functions
type: object
required:
- input_rows
- scoring_functions
title: _scoring_score_Request
_scoring_score_batch_Request:
properties:
dataset_id:
type: string
title: Dataset Id
scoring_functions:
type: string
title: Scoring Functions
save_results_dataset:
type: boolean
title: Save Results Dataset
default: false
type: object
required:
- dataset_id
- scoring_functions
title: _scoring_score_batch_Request
_shields_Request:
properties:
shield_id:
type: string
title: Shield Id
provider_shield_id:
type: string
title: Provider Shield Id
provider_id:
type: string
title: Provider Id
params:
type: string
title: Params
type: object
required:
- shield_id
- provider_shield_id
- provider_id
- params
title: _shields_Request
_tool_runtime_invoke_Request:
properties:
tool_name:
type: string
title: Tool Name
kwargs:
type: string
title: Kwargs
type: object
required:
- tool_name
- kwargs
title: _tool_runtime_invoke_Request
_tool_runtime_rag_tool_query_Request:
properties:
content:
type: string
title: Content
vector_store_ids:
type: string
title: Vector Store Ids
query_config:
$ref: '#/components/schemas/RAGQueryConfig'
type: object
required:
- content
- vector_store_ids
- query_config
title: _tool_runtime_rag_tool_query_Request
_vector_io_query_Request:
properties:
vector_store_id:
type: string
title: Vector Store Id
query:
type: string
title: Query
params:
type: string
title: Params
type: object
required:
- vector_store_id
- query
- params
title: _vector_io_query_Request
_vector_stores_vector_store_id_Request:
properties:
vector_store_id:
type: string
title: Vector Store Id
name:
type: string
title: Name
expires_after:
type: string
title: Expires After
metadata:
type: string
title: Metadata
type: object
required:
- vector_store_id
- name
- expires_after
- metadata
title: _vector_stores_vector_store_id_Request
_vector_stores_vector_store_id_file_batches_batch_id_cancel_Request:
properties:
batch_id:
type: string
title: Batch Id
vector_store_id:
type: string
title: Vector Store Id
type: object
required:
- batch_id
- vector_store_id
title: _vector_stores_vector_store_id_file_batches_batch_id_cancel_Request
_vector_stores_vector_store_id_files_Request:
properties:
vector_store_id:
type: string
title: Vector Store Id
file_id:
type: string
title: File Id
attributes:
type: string
title: Attributes
chunking_strategy:
anyOf:
- $ref: '#/components/schemas/VectorStoreChunkingStrategyAuto'
- $ref: '#/components/schemas/VectorStoreChunkingStrategyStatic'
title: Chunking Strategy
type: object
required:
- vector_store_id
- file_id
- attributes
- chunking_strategy
title: _vector_stores_vector_store_id_files_Request
_vector_stores_vector_store_id_files_file_id_Request:
properties:
vector_store_id:
type: string
title: Vector Store Id
file_id:
type: string
title: File Id
attributes:
type: string
title: Attributes
type: object
required:
- vector_store_id
- file_id
- attributes
title: _vector_stores_vector_store_id_files_file_id_Request
_vector_stores_vector_store_id_search_Request:
properties:
vector_store_id:
type: string
title: Vector Store Id
query:
type: string
title: Query
filters:
type: string
title: Filters
max_num_results:
type: integer
title: Max Num Results
default: 10
ranking_options:
$ref: '#/components/schemas/SearchRankingOptions'
rewrite_query:
type: boolean
title: Rewrite Query
default: false
search_mode:
type: string
title: Search Mode
default: vector
type: object
required:
- vector_store_id
- query
- filters
- ranking_options
title: _vector_stores_vector_store_id_search_Request
Error:
description: Error response from the API. Roughly follows RFC 7807.
properties:
status:
title: Status
type: integer
title:
title: Title
type: string
detail:
title: Detail
type: string
instance:
title: Instance
type: string
nullable: true
required:
- status
- title
- detail
title: Error
type: object
Agent:
description: An agent instance with configuration and metadata.
properties:
agent_id:
title: Agent Id
type: string
agent_config:
$ref: '#/components/schemas/AgentConfig'
created_at:
format: date-time
title: Created At
type: string
required:
- agent_id
- agent_config
- created_at
title: Agent
type: object
AgentStepResponse:
description: Response containing details of a specific agent step.
properties:
step:
discriminator:
mapping:
inference: '#/$defs/InferenceStep'
memory_retrieval: '#/$defs/MemoryRetrievalStep'
shield_call: '#/$defs/ShieldCallStep'
tool_execution: '#/$defs/ToolExecutionStep'
propertyName: step_type
oneOf:
- $ref: '#/components/schemas/InferenceStep'
- $ref: '#/components/schemas/ToolExecutionStep'
- $ref: '#/components/schemas/ShieldCallStep'
- $ref: '#/components/schemas/MemoryRetrievalStep'
title: Step
required:
- step
title: AgentStepResponse
type: object
CompletionMessage:
description: A message containing the model's (assistant) response in a chat conversation.
properties:
role:
const: assistant
default: assistant
title: Role
type: string
content:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/components/schemas/ImageContentItem'
- $ref: '#/components/schemas/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/components/schemas/ImageContentItem'
- $ref: '#/components/schemas/TextContentItem'
type: array
title: Content
stop_reason:
$ref: '#/components/schemas/StopReason'
tool_calls:
title: Tool Calls
items:
$ref: '#/components/schemas/ToolCall'
type: array
required:
- content
- stop_reason
title: CompletionMessage
type: object
InferenceStep:
description: An inference step in an agent turn.
properties:
turn_id:
title: Turn Id
type: string
step_id:
title: Step Id
type: string
started_at:
title: Started At
format: date-time
type: string
nullable: true
completed_at:
title: Completed At
format: date-time
type: string
nullable: true
step_type:
const: inference
default: inference
title: Step Type
type: string
model_response:
$ref: '#/components/schemas/CompletionMessage'
required:
- turn_id
- step_id
- model_response
title: InferenceStep
type: object
ListOpenAIResponseInputItem:
description: List container for OpenAI response input items.
properties:
data:
items:
anyOf:
- discriminator:
mapping:
file_search_call: '#/$defs/OpenAIResponseOutputMessageFileSearchToolCall'
function_call: '#/$defs/OpenAIResponseOutputMessageFunctionToolCall'
mcp_approval_request: '#/$defs/OpenAIResponseMCPApprovalRequest'
mcp_call: '#/$defs/OpenAIResponseOutputMessageMCPCall'
mcp_list_tools: '#/$defs/OpenAIResponseOutputMessageMCPListTools'
message: '#/$defs/OpenAIResponseMessage'
web_search_call: '#/$defs/OpenAIResponseOutputMessageWebSearchToolCall'
propertyName: type
oneOf:
- $ref: '#/components/schemas/OpenAIResponseMessage'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
- $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalResponse'
- $ref: '#/components/schemas/OpenAIResponseMessage'
title: Data
type: array
object:
const: list
default: list
title: Object
type: string
required:
- data
title: ListOpenAIResponseInputItem
type: object
ListOpenAIResponseObject:
description: Paginated list of OpenAI response objects with navigation metadata.
properties:
data:
items:
$ref: '#/components/schemas/OpenAIResponseObjectWithInput'
title: Data
type: array
has_more:
title: Has More
type: boolean
first_id:
title: First Id
type: string
last_id:
title: Last Id
type: string
object:
const: list
default: list
title: Object
type: string
required:
- data
- has_more
- first_id
- last_id
title: ListOpenAIResponseObject
type: object
MemoryRetrievalStep:
description: A memory retrieval step in an agent turn.
properties:
turn_id:
title: Turn Id
type: string
step_id:
title: Step Id
type: string
started_at:
title: Started At
format: date-time
type: string
nullable: true
completed_at:
title: Completed At
format: date-time
type: string
nullable: true
step_type:
const: memory_retrieval
default: memory_retrieval
title: Step Type
type: string
vector_store_ids:
title: Vector Store Ids
type: string
inserted_context:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/components/schemas/ImageContentItem'
- $ref: '#/components/schemas/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/components/schemas/ImageContentItem'
- $ref: '#/components/schemas/TextContentItem'
type: array
title: Inserted Context
required:
- turn_id
- step_id
- vector_store_ids
- inserted_context
title: MemoryRetrievalStep
type: object
OpenAIDeleteResponseObject:
description: Response object confirming deletion of an OpenAI response.
properties:
id:
title: Id
type: string
object:
const: response
default: response
title: Object
type: string
deleted:
default: true
title: Deleted
type: boolean
required:
- id
title: OpenAIDeleteResponseObject
type: object
PaginatedResponse:
description: A generic paginated response that follows a simple format.
properties:
data:
items:
additionalProperties: true
type: object
title: Data
type: array
has_more:
title: Has More
type: boolean
url:
title: Url
type: string
nullable: true
required:
- data
- has_more
title: PaginatedResponse
type: object
Session:
description: A single session of an interaction with an Agentic System.
properties:
session_id:
title: Session Id
type: string
session_name:
title: Session Name
type: string
turns:
items:
$ref: '#/components/schemas/Turn'
title: Turns
type: array
started_at:
format: date-time
title: Started At
type: string
required:
- session_id
- session_name
- turns
- started_at
title: Session
type: object
ShieldCallStep:
description: A shield call step in an agent turn.
properties:
turn_id:
title: Turn Id
type: string
step_id:
title: Step Id
type: string
started_at:
title: Started At
format: date-time
type: string
nullable: true
completed_at:
title: Completed At
format: date-time
type: string
nullable: true
step_type:
const: shield_call
default: shield_call
title: Step Type
type: string
violation:
$ref: '#/components/schemas/SafetyViolation'
required:
- turn_id
- step_id
- violation
title: ShieldCallStep
type: object
ToolExecutionStep:
description: A tool execution step in an agent turn.
properties:
turn_id:
title: Turn Id
type: string
step_id:
title: Step Id
type: string
started_at:
title: Started At
format: date-time
type: string
nullable: true
completed_at:
title: Completed At
format: date-time
type: string
nullable: true
step_type:
const: tool_execution
default: tool_execution
title: Step Type
type: string
tool_calls:
items:
$ref: '#/components/schemas/ToolCall'
title: Tool Calls
type: array
tool_responses:
items:
$ref: '#/components/schemas/ToolResponse'
title: Tool Responses
type: array
required:
- turn_id
- step_id
- tool_calls
- tool_responses
title: ToolExecutionStep
type: object
ToolResponse:
description: Response from a tool invocation.
properties:
call_id:
title: Call Id
type: string
tool_name:
anyOf:
- $ref: '#/components/schemas/BuiltinTool'
- type: string
title: Tool Name
content:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/components/schemas/ImageContentItem'
- $ref: '#/components/schemas/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/components/schemas/ImageContentItem'
- $ref: '#/components/schemas/TextContentItem'
type: array
title: Content
metadata:
title: Metadata
additionalProperties: true
type: object
nullable: true
required:
- call_id
- tool_name
- content
title: ToolResponse
type: object
ListBatchesResponse:
description: Response containing a list of batch objects.
properties:
object:
const: list
default: list
title: Object
type: string
data:
description: List of batch objects
items:
$ref: '#/components/schemas/Batch'
title: Data
type: array
first_id:
description: ID of the first batch in the list
title: First Id
type: string
nullable: true
last_id:
description: ID of the last batch in the list
title: Last Id
type: string
nullable: true
has_more:
default: false
description: Whether there are more batches available
title: Has More
type: boolean
required:
- data
title: ListBatchesResponse
type: object
ConversationDeletedResource:
description: Response for deleted conversation.
properties:
id:
description: The deleted conversation identifier
title: Id
type: string
object:
default: conversation.deleted
description: Object type
title: Object
type: string
deleted:
default: true
description: Whether the object was deleted
title: Deleted
type: boolean
required:
- id
title: ConversationDeletedResource
type: object
ConversationItemDeletedResource:
description: Response for deleted conversation item.
properties:
id:
description: The deleted item identifier
title: Id
type: string
object:
default: conversation.item.deleted
description: Object type
title: Object
type: string
deleted:
default: true
description: Whether the object was deleted
title: Deleted
type: boolean
required:
- id
title: ConversationItemDeletedResource
type: object
ListOpenAIFileResponse:
description: Response for listing files in OpenAI Files API.
properties:
data:
items:
$ref: '#/components/schemas/OpenAIFileObject'
title: Data
type: array
has_more:
title: Has More
type: boolean
first_id:
title: First Id
type: string
last_id:
title: Last Id
type: string
object:
const: list
default: list
title: Object
type: string
required:
- data
- has_more
- first_id
- last_id
title: ListOpenAIFileResponse
type: object
OpenAIFileDeleteResponse:
description: Response for deleting a file in OpenAI Files API.
properties:
id:
title: Id
type: string
object:
const: file
default: file
title: Object
type: string
deleted:
title: Deleted
type: boolean
required:
- id
- deleted
title: OpenAIFileDeleteResponse
type: object
ListOpenAIChatCompletionResponse:
description: Response from listing OpenAI-compatible chat completions.
properties:
data:
items:
$ref: '#/$defs/RouteInfo'
title: Data
type: array
required:
- data
title: ListRoutesResponse
description: >-
Response containing a list of all available API routes.
OpenAIModel:
type: object
properties:
id:
type: string
object:
type: string
const: model
default: model
created:
type: integer
owned_by:
type: string
custom_metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- id
- object
- created
- owned_by
title: OpenAIModel
description: A model from OpenAI.
OpenAIListModelsResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/OpenAIModel'
additionalProperties: false
required:
- data
title: OpenAIListModelsResponse
ModelType:
type: string
enum:
- llm
- embedding
- rerank
title: ModelType
description: >-
Enumeration of supported model types in Llama Stack.
RegisterModelRequest:
type: object
properties:
model_id:
type: string
description: The identifier of the model to register.
provider_model_id:
type: string
description: >-
The identifier of the model in the provider.
provider_id:
type: string
description: The identifier of the provider.
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: Any additional metadata for this model.
model_type:
$ref: '#/components/schemas/ModelType'
description: The type of model to register.
additionalProperties: false
required:
- model_id
title: RegisterModelRequest
Model:
type: object
properties:
identifier:
type: string
description: >-
Unique identifier for this resource in llama stack
provider_resource_id:
type: string
description: >-
Unique identifier for this resource in the provider
provider_id:
type: string
description: >-
ID of the provider that owns this resource
type:
type: string
enum:
- model
- shield
- vector_store
- dataset
- scoring_function
- benchmark
- tool
- tool_group
- prompt
const: model
default: model
description: >-
The resource type, always 'model' for model resources
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: Any additional metadata for this model
model_type:
$ref: '#/components/schemas/ModelType'
default: llm
description: >-
The type of model (LLM or embedding model)
additionalProperties: false
required:
- identifier
- provider_id
- type
- metadata
- model_type
title: Model
description: >-
A model resource representing an AI model registered in Llama Stack.
RunModerationRequest:
type: object
ModerationObject:
$defs:
ModerationObjectResults:
description: >-
A moderation object.
:param flagged: Whether any of the below categories are flagged.
:param categories: A list of the categories, and whether they are flagged
or not.
:param category_applied_input_types: A list of the categories along with
the input type(s) that the score applies to.
:param category_scores: A list of the categories along with their scores
as predicted by model.
properties:
flagged:
title: Flagged
type: boolean
categories:
anyOf:
- additionalProperties:
type: boolean
type: object
- type: 'null'
title: Categories
category_applied_input_types:
anyOf:
- additionalProperties:
items:
type: string
type: array
type: object
- type: 'null'
title: Category Applied Input Types
category_scores:
anyOf:
- additionalProperties:
type: number
type: object
- type: 'null'
title: Category Scores
user_message:
anyOf:
- type: string
- type: 'null'
title: User Message
metadata:
additionalProperties: true
title: Metadata
type: object
required:
- flagged
title: ModerationObjectResults
type: object
description: >-
A moderation object.
:param id: The unique identifier for the moderation request.
:param model: The model used to generate the moderation results.
:param results: A list of moderation objects
properties:
id:
title: Id
type: string
model:
title: Model
type: string
results:
items:
$ref: '#/$defs/ModerationObjectResults'
title: Results
type: array
required:
- id
- model
- results
title: ModerationObject
type: object
ListPromptsResponse:
$defs:
Prompt:
description: >-
A prompt resource representing a stored OpenAI Compatible prompt template
in Llama Stack.
:param prompt: The system prompt text with variable placeholders. Variables
are only supported when using the Responses API.
:param version: Version (integer starting at 1, incremented on save)
:param prompt_id: Unique identifier formatted as 'pmpt_<48-digit-hash>'
:param variables: List of prompt variable names that can be used in the
prompt template
:param is_default: Boolean indicating whether this version is the default
version for this prompt
properties:
prompt:
anyOf:
- type: string
- type: 'null'
description: >-
The system prompt with variable placeholders
title: Prompt
version:
description: >-
Version (integer starting at 1, incremented on save)
minimum: 1
title: Version
type: integer
prompt_id:
description: >-
Unique identifier in format 'pmpt_<48-digit-hash>'
title: Prompt Id
type: string
variables:
description: >-
List of variable names that can be used in the prompt template
items:
type: string
title: Variables
type: array
is_default:
default: false
description: >-
Boolean indicating whether this version is the default version
title: Is Default
type: boolean
required:
- version
- prompt_id
title: Prompt
type: object
description: Response model to list prompts.
properties:
data:
items:
$ref: '#/$defs/Prompt'
title: Data
type: array
required:
- data
title: ListPromptsResponse
type: object
CreatePromptRequest:
type: object
Prompt:
description: >-
A prompt resource representing a stored OpenAI Compatible prompt template
in Llama Stack.
:param prompt: The system prompt text with variable placeholders. Variables
are only supported when using the Responses API.
:param version: Version (integer starting at 1, incremented on save)
:param prompt_id: Unique identifier formatted as 'pmpt_<48-digit-hash>'
:param variables: List of prompt variable names that can be used in the prompt
template
:param is_default: Boolean indicating whether this version is the default
version for this prompt
properties:
prompt:
anyOf:
- type: string
- type: 'null'
description: >-
The system prompt with variable placeholders
title: Prompt
version:
description: >-
Version (integer starting at 1, incremented on save)
minimum: 1
title: Version
type: integer
prompt_id:
description: >-
Unique identifier in format 'pmpt_<48-digit-hash>'
title: Prompt Id
type: string
variables:
description: >-
List of variable names that can be used in the prompt template
items:
type: string
title: Variables
type: array
is_default:
default: false
description: >-
Boolean indicating whether this version is the default version
title: Is Default
type: boolean
required:
- version
- prompt_id
title: Prompt
type: object
UpdatePromptRequest:
type: object
SetDefaultVersionRequest:
type: object
ListProvidersResponse:
$defs:
ProviderInfo:
description: >-
Information about a registered provider including its configuration and
health status.
:param api: The API name this provider implements
:param provider_id: Unique identifier for the provider
:param provider_type: The type of provider implementation
:param config: Configuration parameters for the provider
:param health: Current health status of the provider
properties:
api:
title: Api
type: string
provider_id:
title: Provider Id
type: string
provider_type:
title: Provider Type
type: string
config:
additionalProperties: true
title: Config
type: object
health:
additionalProperties: true
title: Health
type: object
required:
- api
- provider_id
- provider_type
- config
- health
title: ProviderInfo
type: object
description: >-
Response containing a list of all available providers.
:param data: List of provider information objects
properties:
data:
items:
$ref: '#/$defs/ProviderInfo'
title: Data
type: array
required:
- data
title: ListProvidersResponse
type: object
ProviderInfo:
description: >-
Information about a registered provider including its configuration and health
status.
:param api: The API name this provider implements
:param provider_id: Unique identifier for the provider
:param provider_type: The type of provider implementation
:param config: Configuration parameters for the provider
:param health: Current health status of the provider
properties:
api:
title: Api
type: string
provider_id:
title: Provider Id
type: string
provider_type:
title: Provider Type
type: string
config:
additionalProperties: true
title: Config
type: object
health:
additionalProperties: true
title: Health
type: object
required:
- api
- provider_id
- provider_type
- config
- health
title: ProviderInfo
type: object
ListOpenAIResponseObject:
$defs:
AllowedToolsFilter:
description: >-
Filter configuration for restricting which MCP tools can be used.
:param tool_names: (Optional) List of specific tool names that are allowed
properties:
tool_names:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Tool Names
title: AllowedToolsFilter
type: object
MCPListToolsTool:
description: >-
Tool definition returned by MCP list tools operation.
:param input_schema: JSON schema defining the tool's input parameters
:param name: Name of the tool
:param description: (Optional) Description of what the tool does
properties:
input_schema:
additionalProperties: true
title: Input Schema
type: object
name:
title: Name
type: string
description:
anyOf:
- type: string
- type: 'null'
title: Description
required:
- input_schema
- name
title: MCPListToolsTool
type: object
OpenAIResponseAnnotationCitation:
description: >-
URL citation annotation for referencing external web resources.
:param type: Annotation type identifier, always "url_citation"
:param end_index: End position of the citation span in the content
:param start_index: Start position of the citation span in the content
:param title: Title of the referenced web resource
:param url: URL of the referenced web resource
properties:
type:
const: url_citation
default: url_citation
title: Type
type: string
end_index:
title: End Index
type: integer
start_index:
title: Start Index
type: integer
title:
title: Title
type: string
url:
title: Url
type: string
required:
- end_index
- start_index
- title
- url
title: OpenAIResponseAnnotationCitation
type: object
"OpenAIResponseAnnotationContainerFileCitation":
properties:
type:
const: container_file_citation
default: container_file_citation
title: Type
type: string
container_id:
title: Container Id
type: string
end_index:
title: End Index
type: integer
file_id:
title: File Id
type: string
filename:
title: Filename
type: string
start_index:
title: Start Index
type: integer
required:
- container_id
- end_index
- file_id
- filename
- start_index
title: >-
OpenAIResponseAnnotationContainerFileCitation
type: object
OpenAIResponseAnnotationFileCitation:
description: >-
File citation annotation for referencing specific files in response content.
:param type: Annotation type identifier, always "file_citation"
:param file_id: Unique identifier of the referenced file
:param filename: Name of the referenced file
:param index: Position index of the citation within the content
properties:
type:
const: file_citation
default: file_citation
title: Type
type: string
file_id:
title: File Id
type: string
filename:
title: Filename
type: string
index:
title: Index
type: integer
required:
- file_id
- filename
- index
title: OpenAIResponseAnnotationFileCitation
type: object
OpenAIResponseAnnotationFilePath:
properties:
type:
const: file_path
default: file_path
title: Type
type: string
file_id:
title: File Id
type: string
index:
title: Index
type: integer
required:
- file_id
- index
title: OpenAIResponseAnnotationFilePath
type: object
OpenAIResponseContentPartRefusal:
description: >-
Refusal content within a streamed response part.
:param type: Content part type identifier, always "refusal"
:param refusal: Refusal text supplied by the model
properties:
type:
const: refusal
default: refusal
title: Type
type: string
refusal:
title: Refusal
type: string
required:
- refusal
title: OpenAIResponseContentPartRefusal
type: object
OpenAIResponseError:
description: >-
Error details for failed OpenAI response requests.
:param code: Error code identifying the type of failure
:param message: Human-readable error message describing the failure
properties:
code:
title: Code
type: string
message:
title: Message
type: string
required:
- code
- message
title: OpenAIResponseError
type: object
"OpenAIResponseInputFunctionToolCallOutput":
description: >-
This represents the output of a function call that gets passed back to
the model.
properties:
call_id:
title: Call Id
type: string
output:
title: Output
type: string
type:
const: function_call_output
default: function_call_output
title: Type
type: string
id:
anyOf:
- type: string
- type: 'null'
title: Id
status:
anyOf:
- type: string
- type: 'null'
title: Status
required:
- call_id
- output
title: >-
OpenAIResponseInputFunctionToolCallOutput
type: object
OpenAIResponseInputMessageContentImage:
description: >-
Image content for input messages in OpenAI response format.
:param detail: Level of detail for image processing, can be "low", "high",
or "auto"
:param type: Content type identifier, always "input_image"
:param image_url: (Optional) URL of the image content
properties:
detail:
anyOf:
- const: low
type: string
- const: high
type: string
- const: auto
type: string
default: auto
title: Detail
type:
const: input_image
default: input_image
title: Type
type: string
image_url:
anyOf:
- type: string
- type: 'null'
title: Image Url
title: OpenAIResponseInputMessageContentImage
type: object
OpenAIResponseInputMessageContentText:
description: >-
Text content for input messages in OpenAI response format.
:param text: The text content of the input message
:param type: Content type identifier, always "input_text"
properties:
text:
title: Text
type: string
type:
const: input_text
default: input_text
title: Type
type: string
required:
- text
title: OpenAIResponseInputMessageContentText
type: object
OpenAIResponseInputToolFileSearch:
description: >-
File search tool configuration for OpenAI response inputs.
:param type: Tool type identifier, always "file_search"
:param vector_store_ids: List of vector store identifiers to search within
:param filters: (Optional) Additional filters to apply to the search
:param max_num_results: (Optional) Maximum number of search results to
return (1-50)
:param ranking_options: (Optional) Options for ranking and scoring search
results
properties:
type:
const: file_search
default: file_search
title: Type
type: string
vector_store_ids:
items:
type: string
title: Vector Store Ids
type: array
filters:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Filters
max_num_results:
anyOf:
- maximum: 50
minimum: 1
type: integer
- type: 'null'
default: 10
title: Max Num Results
ranking_options:
anyOf:
- $ref: '#/$defs/SearchRankingOptions'
- type: 'null'
required:
- vector_store_ids
title: OpenAIResponseInputToolFileSearch
type: object
OpenAIResponseInputToolFunction:
description: >-
Function tool configuration for OpenAI response inputs.
:param type: Tool type identifier, always "function"
:param name: Name of the function that can be called
:param description: (Optional) Description of what the function does
:param parameters: (Optional) JSON schema defining the function's parameters
:param strict: (Optional) Whether to enforce strict parameter validation
properties:
type:
const: function
default: function
title: Type
type: string
name:
title: Name
type: string
description:
anyOf:
- type: string
- type: 'null'
title: Description
parameters:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Parameters
strict:
anyOf:
- type: boolean
- type: 'null'
title: Strict
required:
- name
- parameters
title: OpenAIResponseInputToolFunction
type: object
OpenAIResponseInputToolWebSearch:
description: >-
Web search tool configuration for OpenAI response inputs.
:param type: Web search tool type variant to use
:param search_context_size: (Optional) Size of search context, must be
"low", "medium", or "high"
properties:
type:
anyOf:
- const: web_search
type: string
- const: web_search_preview
type: string
- const: web_search_preview_2025_03_11
type: string
default: web_search
title: Type
search_context_size:
anyOf:
- pattern: ^low|medium|high$
type: string
- type: 'null'
default: medium
title: Search Context Size
title: OpenAIResponseInputToolWebSearch
type: object
OpenAIResponseMCPApprovalRequest:
description: >-
A request for human approval of a tool invocation.
properties:
arguments:
title: Arguments
type: string
id:
title: Id
type: string
name:
title: Name
type: string
server_label:
title: Server Label
type: string
type:
const: mcp_approval_request
default: mcp_approval_request
title: Type
type: string
required:
- arguments
- id
- name
- server_label
title: OpenAIResponseMCPApprovalRequest
type: object
OpenAIResponseMCPApprovalResponse:
description: A response to an MCP approval request.
properties:
approval_request_id:
title: Approval Request Id
type: string
approve:
title: Approve
type: boolean
type:
const: mcp_approval_response
default: mcp_approval_response
title: Type
type: string
id:
anyOf:
- type: string
- type: 'null'
title: Id
reason:
anyOf:
- type: string
- type: 'null'
title: Reason
required:
- approval_request_id
- approve
title: OpenAIResponseMCPApprovalResponse
type: object
OpenAIResponseMessage:
description: >-
Corresponds to the various Message types in the Responses API.
They are all under one type because the Responses API gives them all
the same "type" value, and there is no way to tell them apart in certain
scenarios.
properties:
content:
anyOf:
- type: string
- items:
discriminator:
mapping:
input_image: >-
#/$defs/OpenAIResponseInputMessageContentImage
input_text: >-
#/$defs/OpenAIResponseInputMessageContentText
propertyName: type
oneOf:
- $ref: >-
#/$defs/OpenAIResponseInputMessageContentText
- $ref: >-
#/$defs/OpenAIResponseInputMessageContentImage
type: array
- items:
discriminator:
mapping:
output_text: >-
#/$defs/OpenAIResponseOutputMessageContentOutputText
refusal: '#/$defs/OpenAIResponseContentPartRefusal'
propertyName: type
oneOf:
- $ref: >-
#/$defs/OpenAIResponseOutputMessageContentOutputText
- $ref: '#/$defs/OpenAIResponseContentPartRefusal'
type: array
title: Content
role:
anyOf:
- const: system
type: string
- const: developer
type: string
- const: user
type: string
- const: assistant
type: string
title: Role
type:
const: message
default: message
title: Type
type: string
id:
anyOf:
- type: string
- type: 'null'
title: Id
status:
anyOf:
- type: string
- type: 'null'
title: Status
required:
- content
- role
title: OpenAIResponseMessage
type: object
OpenAIResponseObjectWithInput:
description: >-
OpenAI response object extended with input context information.
:param input: List of input items that led to this response
properties:
created_at:
title: Created At
type: integer
error:
anyOf:
- $ref: '#/$defs/OpenAIResponseError'
- type: 'null'
id:
title: Id
type: string
model:
title: Model
type: string
object:
const: response
default: response
title: Object
type: string
output:
items:
discriminator:
mapping:
file_search_call: >-
#/$defs/OpenAIResponseOutputMessageFileSearchToolCall
function_call: >-
#/$defs/OpenAIResponseOutputMessageFunctionToolCall
mcp_approval_request: '#/$defs/OpenAIResponseMCPApprovalRequest'
mcp_call: >-
#/$defs/OpenAIResponseOutputMessageMCPCall
mcp_list_tools: >-
#/$defs/OpenAIResponseOutputMessageMCPListTools
message: '#/$defs/OpenAIResponseMessage'
web_search_call: >-
#/$defs/OpenAIResponseOutputMessageWebSearchToolCall
propertyName: type
oneOf:
- $ref: '#/$defs/OpenAIResponseMessage'
- $ref: >-
#/$defs/OpenAIResponseOutputMessageWebSearchToolCall
- $ref: >-
#/$defs/OpenAIResponseOutputMessageFileSearchToolCall
- $ref: >-
#/$defs/OpenAIResponseOutputMessageFunctionToolCall
- $ref: >-
#/$defs/OpenAIResponseOutputMessageMCPCall
- $ref: >-
#/$defs/OpenAIResponseOutputMessageMCPListTools
- $ref: '#/$defs/OpenAIResponseMCPApprovalRequest'
title: Output
type: array
parallel_tool_calls:
default: false
title: Parallel Tool Calls
type: boolean
previous_response_id:
anyOf:
- type: string
- type: 'null'
title: Previous Response Id
status:
title: Status
type: string
temperature:
anyOf:
- type: number
- type: 'null'
title: Temperature
text:
$ref: '#/$defs/OpenAIResponseText'
default:
format:
type: text
top_p:
anyOf:
- type: number
- type: 'null'
title: Top P
tools:
anyOf:
- items:
discriminator:
mapping:
file_search: >-
#/$defs/OpenAIResponseInputToolFileSearch
function: '#/$defs/OpenAIResponseInputToolFunction'
mcp: '#/$defs/OpenAIResponseToolMCP'
web_search: '#/$defs/OpenAIResponseInputToolWebSearch'
web_search_preview: '#/$defs/OpenAIResponseInputToolWebSearch'
web_search_preview_2025_03_11: '#/$defs/OpenAIResponseInputToolWebSearch'
propertyName: type
oneOf:
- $ref: '#/$defs/OpenAIResponseInputToolWebSearch'
- $ref: >-
#/$defs/OpenAIResponseInputToolFileSearch
- $ref: '#/$defs/OpenAIResponseInputToolFunction'
- $ref: '#/$defs/OpenAIResponseToolMCP'
type: array
- type: 'null'
title: Tools
truncation:
anyOf:
- type: string
- type: 'null'
title: Truncation
usage:
anyOf:
- $ref: '#/$defs/OpenAIResponseUsage'
- type: 'null'
instructions:
anyOf:
- type: string
- type: 'null'
title: Instructions
input:
items:
anyOf:
- discriminator:
mapping:
file_search_call: >-
#/$defs/OpenAIResponseOutputMessageFileSearchToolCall
function_call: >-
#/$defs/OpenAIResponseOutputMessageFunctionToolCall
mcp_approval_request: '#/$defs/OpenAIResponseMCPApprovalRequest'
mcp_call: >-
#/$defs/OpenAIResponseOutputMessageMCPCall
mcp_list_tools: >-
#/$defs/OpenAIResponseOutputMessageMCPListTools
message: '#/$defs/OpenAIResponseMessage'
web_search_call: >-
#/$defs/OpenAIResponseOutputMessageWebSearchToolCall
propertyName: type
oneOf:
- $ref: '#/$defs/OpenAIResponseMessage'
- $ref: >-
#/$defs/OpenAIResponseOutputMessageWebSearchToolCall
- $ref: >-
#/$defs/OpenAIResponseOutputMessageFileSearchToolCall
- $ref: >-
#/$defs/OpenAIResponseOutputMessageFunctionToolCall
- $ref: >-
#/$defs/OpenAIResponseOutputMessageMCPCall
- $ref: >-
#/$defs/OpenAIResponseOutputMessageMCPListTools
- $ref: '#/$defs/OpenAIResponseMCPApprovalRequest'
- $ref: >-
#/$defs/OpenAIResponseInputFunctionToolCallOutput
- $ref: >-
#/$defs/OpenAIResponseMCPApprovalResponse
- $ref: '#/$defs/OpenAIResponseMessage'
title: Input
type: array
required:
- created_at
- id
- model
- output
- status
- input
title: OpenAIResponseObjectWithInput
type: object
"OpenAIResponseOutputMessageContentOutputText":
properties:
text:
title: Text
type: string
type:
const: output_text
default: output_text
title: Type
type: string
annotations:
items:
discriminator:
mapping:
container_file_citation: >-
#/$defs/OpenAIResponseAnnotationContainerFileCitation
file_citation: >-
#/$defs/OpenAIResponseAnnotationFileCitation
file_path: '#/$defs/OpenAIResponseAnnotationFilePath'
url_citation: '#/$defs/OpenAIResponseAnnotationCitation'
propertyName: type
oneOf:
- $ref: >-
#/$defs/OpenAIResponseAnnotationFileCitation
- $ref: '#/$defs/OpenAIResponseAnnotationCitation'
- $ref: >-
#/$defs/OpenAIResponseAnnotationContainerFileCitation
- $ref: '#/$defs/OpenAIResponseAnnotationFilePath'
title: Annotations
type: array
required:
- text
title: >-
OpenAIResponseOutputMessageContentOutputText
type: object
"OpenAIResponseOutputMessageFileSearchToolCall":
description: >-
File search tool call output message for OpenAI responses.
:param id: Unique identifier for this tool call
:param queries: List of search queries executed
:param status: Current status of the file search operation
:param type: Tool call type identifier, always "file_search_call"
:param results: (Optional) Search results returned by the file search
operation
properties:
id:
title: Id
type: string
queries:
items:
type: string
title: Queries
type: array
status:
title: Status
type: string
type:
const: file_search_call
default: file_search_call
title: Type
type: string
results:
anyOf:
- items:
$ref: >-
#/$defs/OpenAIResponseOutputMessageFileSearchToolCallResults
type: array
- type: 'null'
title: Results
required:
- id
- queries
- status
title: >-
OpenAIResponseOutputMessageFileSearchToolCall
type: object
"OpenAIResponseOutputMessageFileSearchToolCallResults":
description: >-
Search results returned by the file search operation.
:param attributes: (Optional) Key-value attributes associated with the
file
:param file_id: Unique identifier of the file containing the result
:param filename: Name of the file containing the result
:param score: Relevance score for this search result (between 0 and 1)
:param text: Text content of the search result
properties:
attributes:
additionalProperties: true
title: Attributes
type: object
file_id:
title: File Id
type: string
filename:
title: Filename
type: string
score:
title: Score
type: number
text:
title: Text
type: string
required:
- attributes
- file_id
- filename
- score
- text
title: >-
OpenAIResponseOutputMessageFileSearchToolCallResults
type: object
"OpenAIResponseOutputMessageFunctionToolCall":
description: >-
Function tool call output message for OpenAI responses.
:param call_id: Unique identifier for the function call
:param name: Name of the function being called
:param arguments: JSON string containing the function arguments
:param type: Tool call type identifier, always "function_call"
:param id: (Optional) Additional identifier for the tool call
:param status: (Optional) Current status of the function call execution
properties:
call_id:
title: Call Id
type: string
name:
title: Name
type: string
arguments:
title: Arguments
type: string
type:
const: function_call
default: function_call
title: Type
type: string
id:
anyOf:
- type: string
- type: 'null'
title: Id
status:
anyOf:
- type: string
- type: 'null'
title: Status
required:
- call_id
- name
- arguments
title: >-
OpenAIResponseOutputMessageFunctionToolCall
type: object
OpenAIResponseOutputMessageMCPCall:
description: >-
Model Context Protocol (MCP) call output message for OpenAI responses.
:param id: Unique identifier for this MCP call
:param type: Tool call type identifier, always "mcp_call"
:param arguments: JSON string containing the MCP call arguments
:param name: Name of the MCP method being called
:param server_label: Label identifying the MCP server handling the call
:param error: (Optional) Error message if the MCP call failed
:param output: (Optional) Output result from the successful MCP call
properties:
id:
title: Id
type: string
type:
const: mcp_call
default: mcp_call
title: Type
type: string
arguments:
title: Arguments
type: string
name:
title: Name
type: string
server_label:
title: Server Label
type: string
error:
anyOf:
- type: string
- type: 'null'
title: Error
output:
anyOf:
- type: string
- type: 'null'
title: Output
required:
- id
- arguments
- name
- server_label
title: OpenAIResponseOutputMessageMCPCall
type: object
OpenAIResponseOutputMessageMCPListTools:
description: >-
MCP list tools output message containing available tools from an MCP server.
:param id: Unique identifier for this MCP list tools operation
:param type: Tool call type identifier, always "mcp_list_tools"
:param server_label: Label identifying the MCP server providing the tools
:param tools: List of available tools provided by the MCP server
properties:
id:
title: Id
type: string
type:
const: mcp_list_tools
default: mcp_list_tools
title: Type
type: string
server_label:
title: Server Label
type: string
tools:
items:
$ref: '#/$defs/MCPListToolsTool'
title: Tools
type: array
required:
- id
- server_label
- tools
title: OpenAIResponseOutputMessageMCPListTools
type: object
"OpenAIResponseOutputMessageWebSearchToolCall":
description: >-
Web search tool call output message for OpenAI responses.
:param id: Unique identifier for this tool call
:param status: Current status of the web search operation
:param type: Tool call type identifier, always "web_search_call"
properties:
id:
title: Id
type: string
status:
title: Status
type: string
type:
const: web_search_call
default: web_search_call
title: Type
type: string
required:
- id
- status
title: >-
OpenAIResponseOutputMessageWebSearchToolCall
type: object
OpenAIResponseText:
description: >-
Text response configuration for OpenAI responses.
:param format: (Optional) Text format configuration specifying output
format requirements
properties:
format:
anyOf:
- $ref: '#/$defs/OpenAIResponseTextFormat'
- type: 'null'
title: OpenAIResponseText
type: object
OpenAIResponseTextFormat:
description: >-
Configuration for Responses API text format.
:param type: Must be "text", "json_schema", or "json_object" to identify
the format type
:param name: The name of the response format. Only used for json_schema.
:param schema: The JSON schema the response should conform to. In a Python
SDK, this is often a `pydantic` model. Only used for json_schema.
:param description: (Optional) A description of the response format. Only
used for json_schema.
:param strict: (Optional) Whether to strictly enforce the JSON schema.
If true, the response must match the schema exactly. Only used for json_schema.
properties:
type:
anyOf:
- const: text
type: string
- const: json_schema
type: string
- const: json_object
type: string
title: Type
name:
anyOf:
- type: string
- type: 'null'
title: Name
schema:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Schema
description:
anyOf:
- type: string
- type: 'null'
title: Description
strict:
anyOf:
- type: boolean
- type: 'null'
title: Strict
title: OpenAIResponseTextFormat
type: object
OpenAIResponseToolMCP:
description: >-
Model Context Protocol (MCP) tool configuration for OpenAI response object.
:param type: Tool type identifier, always "mcp"
:param server_label: Label to identify this MCP server
:param allowed_tools: (Optional) Restriction on which tools can be used
from this server
properties:
type:
const: mcp
default: mcp
title: Type
type: string
server_label:
title: Server Label
type: string
allowed_tools:
anyOf:
- items:
type: string
type: array
- $ref: '#/$defs/AllowedToolsFilter'
- type: 'null'
title: Allowed Tools
required:
- server_label
title: OpenAIResponseToolMCP
type: object
OpenAIResponseUsage:
description: >-
Usage information for OpenAI response.
:param input_tokens: Number of tokens in the input
:param output_tokens: Number of tokens in the output
:param total_tokens: Total tokens used (input + output)
:param input_tokens_details: Detailed breakdown of input token usage
:param output_tokens_details: Detailed breakdown of output token usage
properties:
input_tokens:
title: Input Tokens
type: integer
output_tokens:
title: Output Tokens
type: integer
total_tokens:
title: Total Tokens
type: integer
input_tokens_details:
anyOf:
- $ref: >-
#/$defs/OpenAIResponseUsageInputTokensDetails
- type: 'null'
output_tokens_details:
anyOf:
- $ref: >-
#/$defs/OpenAIResponseUsageOutputTokensDetails
- type: 'null'
required:
- input_tokens
- output_tokens
- total_tokens
title: OpenAIResponseUsage
type: object
OpenAIResponseUsageInputTokensDetails:
description: >-
Token details for input tokens in OpenAI response usage.
:param cached_tokens: Number of tokens retrieved from cache
properties:
cached_tokens:
anyOf:
- type: integer
- type: 'null'
title: Cached Tokens
title: OpenAIResponseUsageInputTokensDetails
type: object
OpenAIResponseUsageOutputTokensDetails:
description: >-
Token details for output tokens in OpenAI response usage.
:param reasoning_tokens: Number of tokens used for reasoning (o1/o3 models)
properties:
reasoning_tokens:
anyOf:
- type: integer
- type: 'null'
title: Reasoning Tokens
title: OpenAIResponseUsageOutputTokensDetails
type: object
SearchRankingOptions:
description: >-
Options for ranking and filtering search results.
:param ranker: (Optional) Name of the ranking algorithm to use
:param score_threshold: (Optional) Minimum relevance score threshold for
results
properties:
ranker:
anyOf:
- type: string
- type: 'null'
title: Ranker
score_threshold:
anyOf:
- type: number
- type: 'null'
default: 0.0
title: Score Threshold
title: SearchRankingOptions
type: object
description: >-
Paginated list of OpenAI response objects with navigation metadata.
:param data: List of response objects with their input context
:param has_more: Whether there are more results available beyond this page
:param first_id: Identifier of the first item in this page
:param last_id: Identifier of the last item in this page
:param object: Object type identifier, always "list"
properties:
data:
items:
$ref: '#/$defs/OpenAIResponseObjectWithInput'
title: Data
type: array
has_more:
title: Has More
type: boolean
first_id:
title: First Id
type: string
last_id:
title: Last Id
type: string
object:
const: list
default: list
title: Object
type: string
required:
- data
- has_more
- first_id
- last_id
title: ListOpenAIChatCompletionResponse
type: object
OpenAIAssistantMessageParam:
description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request.
properties:
role:
const: assistant
default: assistant
title: Role
type: string
content:
anyOf:
- type: string
- items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
type: array
title: Content
nullable: true
name:
title: Name
type: string
nullable: true
tool_calls:
title: Tool Calls
items:
$ref: '#/components/schemas/OpenAIChatCompletionToolCall'
type: array
nullable: true
title: OpenAIAssistantMessageParam
type: object
OpenAIChoice:
description: A choice from an OpenAI-compatible chat completion response.
properties:
message:
discriminator:
mapping:
assistant: '#/$defs/OpenAIAssistantMessageParam'
developer: '#/$defs/OpenAIDeveloperMessageParam'
system: '#/$defs/OpenAISystemMessageParam'
tool: '#/$defs/OpenAIToolMessageParam'
user: '#/$defs/OpenAIUserMessageParam'
propertyName: role
oneOf:
- $ref: '#/components/schemas/OpenAIUserMessageParam'
- $ref: '#/components/schemas/OpenAISystemMessageParam'
- $ref: '#/components/schemas/OpenAIAssistantMessageParam'
- $ref: '#/components/schemas/OpenAIToolMessageParam'
- $ref: '#/components/schemas/OpenAIDeveloperMessageParam'
title: Message
finish_reason:
title: Finish Reason
type: string
index:
title: Index
type: integer
logprobs:
$ref: '#/components/schemas/OpenAIChoiceLogprobs'
nullable: true
required:
- message
- finish_reason
- index
title: OpenAIChoice
type: object
OpenAIChoiceLogprobs:
description: The log probabilities for the tokens in the message from an OpenAI-compatible chat completion response.
properties:
content:
title: Content
items:
$ref: '#/components/schemas/OpenAITokenLogProb'
type: array
nullable: true
refusal:
title: Refusal
items:
$ref: '#/components/schemas/OpenAITokenLogProb'
type: array
nullable: true
title: OpenAIChoiceLogprobs
type: object
OpenAICompletionWithInputMessages:
properties:
id:
title: Id
type: string
choices:
items:
$ref: '#/components/schemas/OpenAIChoice'
title: Choices
type: array
object:
const: chat.completion
default: chat.completion
title: Object
type: string
created:
title: Created
type: integer
model:
title: Model
type: string
usage:
$ref: '#/components/schemas/OpenAIChatCompletionUsage'
nullable: true
input_messages:
items:
discriminator:
mapping:
assistant: '#/$defs/OpenAIAssistantMessageParam'
developer: '#/$defs/OpenAIDeveloperMessageParam'
system: '#/$defs/OpenAISystemMessageParam'
tool: '#/$defs/OpenAIToolMessageParam'
user: '#/$defs/OpenAIUserMessageParam'
propertyName: role
oneOf:
- $ref: '#/components/schemas/OpenAIUserMessageParam'
- $ref: '#/components/schemas/OpenAISystemMessageParam'
- $ref: '#/components/schemas/OpenAIAssistantMessageParam'
- $ref: '#/components/schemas/OpenAIToolMessageParam'
- $ref: '#/components/schemas/OpenAIDeveloperMessageParam'
title: Input Messages
type: array
required:
- id
- choices
- created
- model
- input_messages
title: OpenAICompletionWithInputMessages
type: object
OpenAIUserMessageParam:
description: A message from the user in an OpenAI-compatible chat completion request.
properties:
role:
const: user
default: user
title: Role
type: string
content:
anyOf:
- type: string
- items:
discriminator:
mapping:
file: '#/$defs/OpenAIFile'
image_url: '#/$defs/OpenAIChatCompletionContentPartImageParam'
text: '#/$defs/OpenAIChatCompletionContentPartTextParam'
propertyName: type
oneOf:
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
- $ref: '#/components/schemas/OpenAIFile'
type: array
title: Content
name:
title: Name
type: string
nullable: true
required:
- content
title: OpenAIUserMessageParam
type: object
Checkpoint:
description: Checkpoint created during training runs.
properties:
identifier:
title: Identifier
type: string
created_at:
format: date-time
title: Created At
type: string
epoch:
title: Epoch
type: integer
post_training_job_id:
title: Post Training Job Id
type: string
path:
title: Path
type: string
training_metrics:
$ref: '#/components/schemas/PostTrainingMetric'
nullable: true
required:
- identifier
- created_at
- epoch
- post_training_job_id
- path
title: Checkpoint
type: object
PostTrainingJobArtifactsResponse:
description: Artifacts of a finetuning job.
properties:
job_uuid:
title: Job Uuid
type: string
checkpoints:
items:
$ref: '#/components/schemas/Checkpoint'
title: Checkpoints
type: array
required:
- job_uuid
title: PostTrainingJobArtifactsResponse
type: object
PostTrainingJobStatusResponse:
description: Status of a finetuning job.
properties:
job_uuid:
title: Job Uuid
type: string
status:
$ref: '#/components/schemas/JobStatus'
scheduled_at:
title: Scheduled At
format: date-time
type: string
nullable: true
started_at:
title: Started At
format: date-time
type: string
nullable: true
completed_at:
title: Completed At
format: date-time
type: string
nullable: true
resources_allocated:
title: Resources Allocated
additionalProperties: true
type: object
nullable: true
checkpoints:
items:
$ref: '#/components/schemas/Checkpoint'
title: Checkpoints
type: array
required:
- job_uuid
- status
title: PostTrainingJobStatusResponse
type: object
ScoringFn:
description: A scoring function resource for evaluating model outputs.
properties:
identifier:
description: Unique identifier for this resource in llama stack
title: Identifier
type: string
provider_resource_id:
description: Unique identifier for this resource in the provider
title: Provider Resource Id
type: string
nullable: true
provider_id:
description: ID of the provider that owns this resource
title: Provider Id
type: string
type:
const: scoring_function
default: scoring_function
title: Type
type: string
description:
title: Description
type: string
nullable: true
metadata:
additionalProperties: true
description: Any additional metadata for this definition
title: Metadata
type: object
return_type:
description: The return type of the deterministic function
discriminator:
mapping:
agent_turn_input: '#/$defs/AgentTurnInputType'
array: '#/$defs/ArrayType'
boolean: '#/$defs/BooleanType'
chat_completion_input: '#/$defs/ChatCompletionInputType'
completion_input: '#/$defs/CompletionInputType'
json: '#/$defs/JsonType'
number: '#/$defs/NumberType'
object: '#/$defs/ObjectType'
string: '#/$defs/StringType'
union: '#/$defs/UnionType'
propertyName: type
oneOf:
- $ref: '#/components/schemas/StringType'
- $ref: '#/components/schemas/NumberType'
- $ref: '#/components/schemas/BooleanType'
- $ref: '#/components/schemas/ArrayType'
- $ref: '#/components/schemas/ObjectType'
- $ref: '#/components/schemas/JsonType'
- $ref: '#/components/schemas/UnionType'
- $ref: '#/components/schemas/ChatCompletionInputType'
- $ref: '#/components/schemas/CompletionInputType'
- $ref: '#/components/schemas/AgentTurnInputType'
title: Return Type
params:
description: The parameters for the scoring function for benchmark eval, these can be overridden for app eval
title: Params
discriminator:
mapping:
basic: '#/$defs/BasicScoringFnParams'
llm_as_judge: '#/$defs/LLMAsJudgeScoringFnParams'
regex_parser: '#/$defs/RegexParserScoringFnParams'
propertyName: type
oneOf:
- $ref: '#/components/schemas/LLMAsJudgeScoringFnParams'
- $ref: '#/components/schemas/RegexParserScoringFnParams'
- $ref: '#/components/schemas/BasicScoringFnParams'
nullable: true
required:
- identifier
- provider_id
- return_type
title: ScoringFn
type: object
ScoreRequest:
type: object
ScoreResponse:
$defs:
ScoringResult:
description: >-
A scoring result for a single row.
:param score_rows: The scoring result for each row. Each row is a map
of column name to value.
:param aggregated_results: Map of metric name to aggregated value
properties:
score_rows:
items:
additionalProperties: true
type: object
title: Score Rows
type: array
aggregated_results:
additionalProperties: true
title: Aggregated Results
type: object
required:
- score_rows
- aggregated_results
title: ScoringResult
type: object
description: >-
The response from scoring.
:param results: A map of scoring function name to ScoringResult.
properties:
results:
additionalProperties:
$ref: '#/$defs/ScoringResult'
title: Results
type: object
required:
- results
title: ScoreResponse
type: object
ScoreBatchRequest:
type: object
ScoreBatchResponse:
$defs:
ScoringResult:
description: >-
A scoring result for a single row.
:param score_rows: The scoring result for each row. Each row is a map
of column name to value.
:param aggregated_results: Map of metric name to aggregated value
properties:
score_rows:
items:
additionalProperties: true
type: object
title: Score Rows
type: array
aggregated_results:
additionalProperties: true
title: Aggregated Results
type: object
required:
- score_rows
- aggregated_results
title: ScoringResult
type: object
description: >-
Response from batch scoring operations on datasets.
:param dataset_id: (Optional) The identifier of the dataset that was scored
:param results: A map of scoring function name to ScoringResult
properties:
dataset_id:
anyOf:
- type: string
- type: 'null'
title: Dataset Id
results:
additionalProperties:
$ref: '#/$defs/ScoringResult'
title: Results
type: object
required:
- results
title: ScoreBatchResponse
type: object
ListShieldsResponse:
$defs:
Shield:
description: >-
A safety shield resource that can be used to check content.
:param params: (Optional) Configuration parameters for the shield
:param type: The resource type, always shield
properties:
identifier:
description: >-
Unique identifier for this resource in llama stack
title: Identifier
type: string
provider_resource_id:
anyOf:
- type: string
- type: 'null'
description: >-
Unique identifier for this resource in the provider
title: Provider Resource Id
provider_id:
description: >-
ID of the provider that owns this resource
title: Provider Id
type: string
type:
const: shield
default: shield
title: Type
type: string
params:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Params
required:
- identifier
- provider_id
title: Shield
type: object
properties:
data:
items:
$ref: '#/$defs/Shield'
title: Data
type: array
required:
- data
title: ListShieldsResponse
type: object
RegisterShieldRequest:
type: object
properties:
shield_id:
type: string
description: >-
The identifier of the shield to register.
provider_shield_id:
type: string
description: >-
The identifier of the shield in the provider.
provider_id:
type: string
description: The identifier of the provider.
params:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: The parameters of the shield.
additionalProperties: false
required:
- shield_id
title: RegisterShieldRequest
InvokeToolRequest:
type: object
properties:
tool_name:
type: string
description: The name of the tool to invoke.
kwargs:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
A dictionary of arguments to pass to the tool.
additionalProperties: false
required:
- tool_name
- kwargs
title: InvokeToolRequest
ImageContentItem:
type: object
properties:
type:
type: string
const: image
default: image
description: >-
Discriminator type of the content item. Always "image"
image:
type: object
properties:
url:
$ref: '#/components/schemas/URL'
description: >-
A URL of the image or data URL in the format of data:image/{type};base64,{data}.
Note that URL could have length limits.
data:
type: string
contentEncoding: base64
description: base64 encoded image data as string
additionalProperties: false
description: >-
Image as a base64 encoded string or an URL
additionalProperties: false
required:
- type
- image
title: ImageContentItem
description: A image content item
InterleavedContent:
oneOf:
- type: string
- $ref: '#/components/schemas/InterleavedContentItem'
- type: array
items:
$ref: '#/components/schemas/InterleavedContentItem'
InterleavedContentItem:
oneOf:
- $ref: '#/components/schemas/ImageContentItem'
- $ref: '#/components/schemas/TextContentItem'
discriminator:
propertyName: type
mapping:
image: '#/components/schemas/ImageContentItem'
text: '#/components/schemas/TextContentItem'
TextContentItem:
type: object
properties:
type:
type: string
const: text
default: text
description: >-
Discriminator type of the content item. Always "text"
text:
type: string
description: Text content
additionalProperties: false
required:
- type
- text
title: TextContentItem
description: A text content item
ToolInvocationResult:
type: object
properties:
content:
$ref: '#/components/schemas/InterleavedContent'
description: >-
(Optional) The output content from the tool execution
error_message:
type: string
description: >-
(Optional) Error message if the tool execution failed
error_code:
type: integer
description: >-
(Optional) Numeric error code if the tool execution failed
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
(Optional) Additional metadata about the tool execution
additionalProperties: false
title: ToolInvocationResult
description: Result of a tool invocation.
URL:
type: object
properties:
uri:
type: string
description: The URL string pointing to the resource
additionalProperties: false
required:
- uri
title: URL
description: A URL reference to external content.
ToolDef:
type: object
properties:
toolgroup_id:
type: string
description: >-
(Optional) ID of the tool group this tool belongs to
name:
type: string
description: Name of the tool
description:
type: string
description: >-
(Optional) Human-readable description of what the tool does
input_schema:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
(Optional) JSON Schema for tool inputs (MCP inputSchema)
output_schema:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
(Optional) JSON Schema for tool outputs (MCP outputSchema)
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
(Optional) Additional metadata about the tool
additionalProperties: false
required:
- name
title: ToolDef
description: >-
Tool definition used in runtime contexts.
ListToolDefsResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/ToolDef'
description: List of tool definitions
additionalProperties: false
required:
- data
title: ListToolDefsResponse
description: >-
Response containing a list of tool definitions.
RAGDocument:
type: object
properties:
document_id:
type: string
description: The unique identifier for the document.
content:
oneOf:
- type: string
- $ref: '#/components/schemas/InterleavedContentItem'
- type: array
items:
$ref: '#/components/schemas/InterleavedContentItem'
- $ref: '#/components/schemas/URL'
description: The content of the document.
mime_type:
type: string
description: The MIME type of the document.
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: Additional metadata for the document.
additionalProperties: false
required:
- document_id
- content
- metadata
title: RAGDocument
description: >-
A document to be used for document ingestion in the RAG Tool.
InsertRequest:
type: object
properties:
documents:
type: array
items:
$ref: '#/components/schemas/RAGDocument'
description: >-
List of documents to index in the RAG system
vector_store_id:
type: string
description: >-
ID of the vector database to store the document embeddings
chunk_size_in_tokens:
type: integer
description: >-
(Optional) Size in tokens for document chunking during indexing
additionalProperties: false
required:
- documents
- vector_store_id
- chunk_size_in_tokens
title: InsertRequest
DefaultRAGQueryGeneratorConfig:
type: object
properties:
type:
type: string
const: default
default: default
description: >-
Type of query generator, always 'default'
separator:
type: string
default: ' '
description: >-
String separator used to join query terms
additionalProperties: false
required:
- type
- separator
title: DefaultRAGQueryGeneratorConfig
description: >-
Configuration for the default RAG query generator.
LLMRAGQueryGeneratorConfig:
type: object
properties:
type:
type: string
const: llm
default: llm
description: Type of query generator, always 'llm'
model:
type: string
description: >-
Name of the language model to use for query generation
template:
type: string
description: >-
Template string for formatting the query generation prompt
additionalProperties: false
required:
- type
- model
- template
title: LLMRAGQueryGeneratorConfig
description: >-
Configuration for the LLM-based RAG query generator.
RAGQueryConfig:
type: object
properties:
query_generator_config:
oneOf:
- $ref: '#/components/schemas/DefaultRAGQueryGeneratorConfig'
- $ref: '#/components/schemas/LLMRAGQueryGeneratorConfig'
discriminator:
propertyName: type
mapping:
default: '#/components/schemas/DefaultRAGQueryGeneratorConfig'
llm: '#/components/schemas/LLMRAGQueryGeneratorConfig'
description: Configuration for the query generator.
max_tokens_in_context:
type: integer
default: 4096
description: Maximum number of tokens in the context.
max_chunks:
type: integer
default: 5
description: Maximum number of chunks to retrieve.
chunk_template:
type: string
default: >
Result {index}
:param params: (Optional) Configuration parameters for the shield
:param type: The resource type, always shield
properties:
identifier:
description: >-
Unique identifier for this resource in llama stack
title: Identifier
type: string
provider_resource_id:
anyOf:
- type: string
- type: 'null'
description: >-
Unique identifier for this resource in the provider
title: Provider Resource Id
provider_id:
description: >-
ID of the provider that owns this resource
title: Provider Id
type: string
type:
const: shield
default: shield
title: Type
type: string
params:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Params
required:
- identifier
- provider_id
title: Shield
type: object
SyntheticDataGenerateRequest:
type: object
SyntheticDataGenerationResponse:
description: >-
Response from the synthetic data generation. Batch of (prompt, response, score)
tuples that pass the threshold.
:param synthetic_data: List of generated synthetic data samples that passed
the filtering criteria
:param statistics: (Optional) Statistical information about the generation
process and filtering results
properties:
synthetic_data:
items:
additionalProperties: true
type: object
title: Synthetic Data
type: array
statistics:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Statistics
required:
- synthetic_data
title: SyntheticDataGenerationResponse
type: object
InvokeToolRequest:
type: object
ToolInvocationResult:
$defs:
ImageContentItem:
description: >-
A image content item
:param type: Discriminator type of the content item. Always "image"
:param image: Image as a base64 encoded string or an URL
properties:
type:
const: image
default: image
title: Type
type: string
image:
$ref: '#/$defs/_URLOrData'
required:
- image
title: ImageContentItem
type: object
TextContentItem:
description: >-
A text content item
:param type: Discriminator type of the content item. Always "text"
:param text: Text content
properties:
type:
const: text
default: text
title: Type
type: string
text:
title: Text
type: string
required:
- text
title: TextContentItem
type: object
URL:
description: >-
A URL reference to external content.
:param uri: The URL string pointing to the resource
properties:
uri:
title: Uri
type: string
required:
- uri
title: URL
type: object
_URLOrData:
description: >-
A URL or a base64 encoded string
:param url: A URL of the image or data URL in the format of data:image/{type};base64,{data}.
Note that URL could have length limits.
:param data: base64 encoded image data as string
properties:
url:
anyOf:
- $ref: '#/$defs/URL'
- type: 'null'
data:
anyOf:
- type: string
- type: 'null'
contentEncoding: base64
title: Data
title: _URLOrData
type: object
description: >-
Result of a tool invocation.
:param content: (Optional) The output content from the tool execution
:param error_message: (Optional) Error message if the tool execution failed
:param error_code: (Optional) Numeric error code if the tool execution failed
:param metadata: (Optional) Additional metadata about the tool execution
properties:
content:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
- type: 'null'
title: Content
error_message:
anyOf:
- type: string
- type: 'null'
title: Error Message
error_code:
anyOf:
- type: integer
- type: 'null'
title: Error Code
metadata:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Metadata
title: ToolInvocationResult
type: object
URL:
description: >-
A URL reference to external content.
:param uri: The URL string pointing to the resource
properties:
uri:
title: Uri
type: string
required:
- uri
title: URL
type: object
ListToolDefsResponse:
description: Response containing a list of tool definitions.
properties:
data:
items:
$ref: '#/components/schemas/ToolDef'
title: Data
type: array
required:
- data
title: ListToolDefsResponse
type: object
VectorStoreDeleteResponse:
description: Response from deleting a vector store.
properties:
id:
title: Id
type: string
object:
default: vector_store.deleted
title: Object
type: string
deleted:
default: true
title: Deleted
type: boolean
required:
- id
title: VectorStoreDeleteResponse
type: object
VectorStoreFileContentsResponse:
description: Response from retrieving the contents of a vector store file.
properties:
file_id:
title: File Id
type: string
filename:
title: Filename
type: string
attributes:
additionalProperties: true
title: Attributes
type: object
content:
items:
$ref: '#/components/schemas/VectorStoreContent'
title: Content
type: array
required:
- file_id
- filename
- attributes
- content
title: VectorStoreFileContentsResponse
type: object
VectorStoreFileDeleteResponse:
description: Response from deleting a vector store file.
properties:
id:
title: Id
type: string
object:
default: vector_store.file.deleted
title: Object
type: string
deleted:
default: true
title: Deleted
type: boolean
required:
- id
title: VectorStoreFileDeleteResponse
type: object
VectorStoreFilesListInBatchResponse:
description: Response from listing files in a vector store file batch.
properties:
object:
default: list
title: Object
type: string
data:
items:
$ref: '#/components/schemas/VectorStoreFileObject'
title: Data
type: array
first_id:
title: First Id
type: string
nullable: true
last_id:
title: Last Id
type: string
nullable: true
has_more:
default: false
title: Has More
type: boolean
required:
- data
title: VectorStoreFilesListInBatchResponse
type: object
VectorStoreListFilesResponse:
description: Response from listing files in a vector store.
properties:
object:
default: list
title: Object
type: string
data:
items:
$ref: '#/components/schemas/VectorStoreFileObject'
title: Data
type: array
first_id:
title: First Id
type: string
nullable: true
last_id:
title: Last Id
type: string
nullable: true
has_more:
default: false
title: Has More
type: boolean
required:
- data
title: VectorStoreListFilesResponse
type: object
VectorStoreListResponse:
description: Response from listing vector stores.
properties:
object:
default: list
title: Object
type: string
data:
items:
$ref: '#/components/schemas/VectorStoreObject'
title: Data
type: array
first_id:
title: First Id
type: string
nullable: true
last_id:
title: Last Id
type: string
nullable: true
has_more:
default: false
title: Has More
type: boolean
required:
- data
title: VectorStoreListResponse
type: object
OpenAIResponseMessage:
description: "Corresponds to the various Message types in the Responses API.\nThey are all under one type because the Responses API gives them all\nthe same \"type\" value, and there is no way to tell them apart in certain\nscenarios."
properties:
content:
anyOf:
- type: string
- items:
discriminator:
mapping:
input_file: '#/$defs/OpenAIResponseInputMessageContentFile'
input_image: '#/$defs/OpenAIResponseInputMessageContentImage'
input_text: '#/$defs/OpenAIResponseInputMessageContentText'
propertyName: type
oneOf:
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentText'
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentImage'
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentFile'
type: array
- items:
discriminator:
mapping:
output_text: '#/$defs/OpenAIResponseOutputMessageContentOutputText'
refusal: '#/$defs/OpenAIResponseContentPartRefusal'
propertyName: type
oneOf:
- $ref: '#/components/schemas/OpenAIResponseOutputMessageContentOutputText'
- $ref: '#/components/schemas/OpenAIResponseContentPartRefusal'
type: array
title: Content
role:
anyOf:
- const: system
type: string
- const: developer
type: string
- const: user
type: string
- const: assistant
type: string
title: Role
type:
const: message
default: message
title: Type
type: string
id:
title: Id
type: string
nullable: true
status:
title: Status
type: string
nullable: true
required:
- content
- role
title: OpenAIResponseMessage
type: object
OpenAIResponseObjectWithInput:
description: OpenAI response object extended with input context information.
properties:
created_at:
title: Created At
type: integer
error:
$ref: '#/components/schemas/OpenAIResponseError'
nullable: true
id:
title: Id
type: string
model:
title: Model
type: string
required:
- session_id
title: AgentSessionCreateResponse
description: >-
Response returned when creating a new agent session.
CompletionMessage:
type: object
properties:
role:
type: string
const: assistant
default: assistant
description: >-
Must be "assistant" to identify this as the model's response
content:
$ref: '#/components/schemas/InterleavedContent'
description: The content of the model's response
stop_reason:
type: string
enum:
- end_of_turn
- end_of_message
- out_of_tokens
description: >-
Reason why the model stopped generating. Options are: - `StopReason.end_of_turn`:
The model finished generating the entire response. - `StopReason.end_of_message`:
The model finished generating but generated a partial response -- usually,
a tool call. The user may call the tool and continue the conversation
with the tool's response. - `StopReason.out_of_tokens`: The model ran
out of token budget.
tool_calls:
type: array
items:
$ref: '#/components/schemas/ToolCall'
description: >-
List of tool calls. Each tool call is a ToolCall object.
additionalProperties: false
required:
- role
- content
- stop_reason
title: CompletionMessage
description: >-
A message containing the model's (assistant) response in a chat conversation.
InferenceStep:
type: object
Session:
$defs:
Attachment:
description: >-
An attachment to an agent turn.
:param content: The content of the attachment.
:param mime_type: The MIME type of the attachment.
properties:
content:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
- $ref: '#/$defs/URL'
title: Content
mime_type:
title: Mime Type
type: string
required:
- content
- mime_type
title: Attachment
type: object
BuiltinTool:
enum:
- brave_search
- wolfram_alpha
- photogen
- code_interpreter
title: BuiltinTool
type: string
CompletionMessage:
description: >-
A message containing the model's (assistant) response in a chat conversation.
:param role: Must be "assistant" to identify this as the model's response
:param content: The content of the model's response
:param stop_reason: Reason why the model stopped generating. Options are:
- `StopReason.end_of_turn`: The model finished generating the entire
response.
- `StopReason.end_of_message`: The model finished generating but generated
a partial response -- usually, a tool call. The user may call the tool
and continue the conversation with the tool's response.
- `StopReason.out_of_tokens`: The model ran out of token budget.
:param tool_calls: List of tool calls. Each tool call is a ToolCall object.
properties:
role:
const: assistant
default: assistant
title: Role
type: string
content:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
title: Content
stop_reason:
$ref: '#/$defs/StopReason'
tool_calls:
anyOf:
- items:
$ref: '#/$defs/ToolCall'
type: array
- type: 'null'
title: Tool Calls
required:
- content
- stop_reason
title: CompletionMessage
type: object
ImageContentItem:
description: >-
A image content item
:param type: Discriminator type of the content item. Always "image"
:param image: Image as a base64 encoded string or an URL
properties:
type:
const: image
default: image
title: Type
type: string
image:
$ref: '#/$defs/_URLOrData'
required:
- image
title: ImageContentItem
type: object
InferenceStep:
description: >-
An inference step in an agent turn.
:param model_response: The response from the LLM.
properties:
turn_id:
title: Turn Id
type: string
step_id:
title: Step Id
type: string
started_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Started At
completed_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Completed At
step_type:
const: inference
default: inference
title: Step Type
type: string
model_response:
$ref: '#/$defs/CompletionMessage'
required:
- turn_id
- step_id
- model_response
title: InferenceStep
type: object
MemoryRetrievalStep:
description: >-
A memory retrieval step in an agent turn.
:param vector_store_ids: The IDs of the vector databases to retrieve context
from.
:param inserted_context: The context retrieved from the vector databases.
properties:
turn_id:
title: Turn Id
type: string
step_id:
title: Step Id
type: string
started_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Started At
completed_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Completed At
step_type:
const: memory_retrieval
default: memory_retrieval
title: Step Type
type: string
vector_store_ids:
title: Vector Store Ids
type: string
inserted_context:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
title: Inserted Context
required:
- turn_id
- step_id
- vector_store_ids
- inserted_context
title: MemoryRetrievalStep
type: object
SafetyViolation:
description: >-
Details of a safety violation detected by content moderation.
:param violation_level: Severity level of the violation
:param user_message: (Optional) Message to convey to the user about the
violation
:param metadata: Additional metadata including specific violation codes
for debugging and telemetry
properties:
violation_level:
$ref: '#/$defs/ViolationLevel'
user_message:
anyOf:
- type: string
- type: 'null'
title: User Message
metadata:
additionalProperties: true
title: Metadata
type: object
required:
- violation_level
title: SafetyViolation
type: object
ShieldCallStep:
description: >-
A shield call step in an agent turn.
:param violation: The violation from the shield call.
properties:
turn_id:
title: Turn Id
type: string
step_id:
title: Step Id
type: string
started_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Started At
completed_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Completed At
step_type:
const: shield_call
default: shield_call
title: Step Type
type: string
violation:
anyOf:
- $ref: '#/$defs/SafetyViolation'
- type: 'null'
required:
- turn_id
- step_id
- violation
title: ShieldCallStep
type: object
StopReason:
enum:
- end_of_turn
- end_of_message
- out_of_tokens
title: StopReason
type: string
TextContentItem:
description: >-
A text content item
:param type: Discriminator type of the content item. Always "text"
:param text: Text content
properties:
type:
const: text
default: text
title: Type
type: string
text:
title: Text
type: string
required:
- text
title: TextContentItem
type: object
ToolCall:
properties:
call_id:
title: Call Id
type: string
tool_name:
anyOf:
- $ref: '#/$defs/BuiltinTool'
- type: string
title: Tool Name
arguments:
title: Arguments
type: string
required:
- call_id
- tool_name
- arguments
title: ToolCall
type: object
ToolExecutionStep:
description: >-
A tool execution step in an agent turn.
:param tool_calls: The tool calls to execute.
:param tool_responses: The tool responses from the tool calls.
properties:
turn_id:
title: Turn Id
type: string
step_id:
title: Step Id
type: string
started_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Started At
completed_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Completed At
step_type:
const: tool_execution
default: tool_execution
title: Step Type
type: string
tool_calls:
items:
$ref: '#/$defs/ToolCall'
title: Tool Calls
type: array
tool_responses:
items:
$ref: '#/$defs/ToolResponse'
title: Tool Responses
type: array
required:
- turn_id
- step_id
- tool_calls
- tool_responses
title: ToolExecutionStep
type: object
ToolResponse:
description: >-
Response from a tool invocation.
:param call_id: Unique identifier for the tool call this response is for
:param tool_name: Name of the tool that was invoked
:param content: The response content from the tool
:param metadata: (Optional) Additional metadata about the tool response
properties:
call_id:
title: Call Id
type: string
tool_name:
anyOf:
- $ref: '#/$defs/BuiltinTool'
- type: string
title: Tool Name
content:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
title: Content
metadata:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Metadata
required:
- call_id
- tool_name
- content
title: ToolResponse
type: object
ToolResponseMessage:
description: >-
A message representing the result of a tool invocation.
:param role: Must be "tool" to identify this as a tool response
:param call_id: Unique identifier for the tool call this response is for
:param content: The response content from the tool
properties:
role:
const: tool
default: tool
title: Role
type: string
call_id:
title: Call Id
type: string
content:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
title: Content
required:
- call_id
- content
title: ToolResponseMessage
type: object
Turn:
description: >-
A single turn in an interaction with an Agentic System.
:param turn_id: Unique identifier for the turn within a session
:param session_id: Unique identifier for the conversation session
:param input_messages: List of messages that initiated this turn
:param steps: Ordered list of processing steps executed during this turn
:param output_message: The model's generated response containing content
and metadata
:param output_attachments: (Optional) Files or media attached to the agent's
response
:param started_at: Timestamp when the turn began
:param completed_at: (Optional) Timestamp when the turn finished, if completed
properties:
turn_id:
title: Turn Id
type: string
session_id:
title: Session Id
type: string
input_messages:
items:
anyOf:
- $ref: '#/$defs/UserMessage'
- $ref: '#/$defs/ToolResponseMessage'
title: Input Messages
type: array
steps:
items:
discriminator:
mapping:
inference: '#/$defs/InferenceStep'
memory_retrieval: '#/$defs/MemoryRetrievalStep'
shield_call: '#/$defs/ShieldCallStep'
tool_execution: '#/$defs/ToolExecutionStep'
propertyName: step_type
oneOf:
- $ref: '#/$defs/InferenceStep'
- $ref: '#/$defs/ToolExecutionStep'
- $ref: '#/$defs/ShieldCallStep'
- $ref: '#/$defs/MemoryRetrievalStep'
title: Steps
type: array
output_message:
$ref: '#/$defs/CompletionMessage'
output_attachments:
anyOf:
- items:
$ref: '#/$defs/Attachment'
type: array
- type: 'null'
title: Output Attachments
started_at:
format: date-time
title: Started At
type: string
completed_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Completed At
required:
- turn_id
- session_id
- input_messages
- steps
- output_message
- started_at
title: Turn
type: object
URL:
description: >-
A URL reference to external content.
:param uri: The URL string pointing to the resource
properties:
uri:
title: Uri
type: string
required:
- uri
title: URL
type: object
UserMessage:
description: >-
A message from the user in a chat conversation.
:param role: Must be "user" to identify this as a user message
:param content: The content of the message, which can include text and
other media
:param context: (Optional) This field is used internally by Llama Stack
to pass RAG context. This field may be removed in the API in the future.
properties:
role:
const: user
default: user
title: Role
type: string
content:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
title: Content
context:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
- type: 'null'
title: Context
required:
- content
title: UserMessage
type: object
ViolationLevel:
description: >-
Severity level of a safety violation.
:cvar INFO: Informational level violation that does not require action
:cvar WARN: Warning level violation that suggests caution but allows continuation
:cvar ERROR: Error level violation that requires blocking or intervention
enum:
- info
- warn
- error
title: ViolationLevel
type: string
_URLOrData:
description: >-
A URL or a base64 encoded string
:param url: A URL of the image or data URL in the format of data:image/{type};base64,{data}.
Note that URL could have length limits.
:param data: base64 encoded image data as string
properties:
url:
anyOf:
- $ref: '#/$defs/URL'
- type: 'null'
data:
anyOf:
- type: string
- type: 'null'
contentEncoding: base64
title: Data
title: _URLOrData
type: object
description: >-
A single session of an interaction with an Agentic System.
:param session_id: Unique identifier for the conversation session
:param session_name: Human-readable name for the session
:param turns: List of all turns that have occurred in this session
:param started_at: Timestamp when the session was created
properties:
session_id:
title: Session Id
type: string
session_name:
title: Session Name
type: string
turns:
items:
$ref: '#/$defs/Turn'
title: Turns
type: array
started_at:
format: date-time
title: Started At
type: string
required:
- session_id
- session_name
- turns
- started_at
title: Session
type: object
properties:
turn_id:
type: string
description: The ID of the turn.
step_id:
type: string
description: The ID of the step.
started_at:
type: string
format: date-time
description: The time the step started.
completed_at:
type: string
format: date-time
description: The time the step completed.
step_type:
type: string
enum:
- inference
- tool_execution
- shield_call
- memory_retrieval
title: StepType
description: Type of the step in an agent turn.
const: shield_call
default: shield_call
violation:
$ref: '#/components/schemas/SafetyViolation'
description: The violation from the shield call.
additionalProperties: false
required:
- turn_id
- step_id
- step_type
title: ShieldCallStep
description: A shield call step in an agent turn.
ToolCall:
type: object
properties:
call_id:
type: string
tool_name:
oneOf:
- type: string
enum:
- brave_search
- wolfram_alpha
- photogen
- code_interpreter
title: BuiltinTool
- type: string
arguments:
type: string
additionalProperties: false
required:
- call_id
- tool_name
- arguments
title: ToolCall
ToolExecutionStep:
type: object
properties:
turn_id:
type: string
description: The ID of the turn.
step_id:
type: string
description: The ID of the step.
started_at:
type: string
format: date-time
description: The time the step started.
completed_at:
type: string
format: date-time
description: The time the step completed.
step_type:
type: string
enum:
- inference
- tool_execution
- shield_call
- memory_retrieval
title: StepType
description: Type of the step in an agent turn.
const: tool_execution
default: tool_execution
tool_calls:
type: array
items:
$ref: '#/components/schemas/ToolCall'
description: The tool calls to execute.
tool_responses:
type: array
items:
$ref: '#/components/schemas/ToolResponse'
description: The tool responses from the tool calls.
additionalProperties: false
required:
- turn_id
- step_id
- step_type
- tool_calls
- tool_responses
title: ToolExecutionStep
description: A tool execution step in an agent turn.
ToolResponse:
type: object
properties:
call_id:
type: string
description: >-
Unique identifier for the tool call this response is for
tool_name:
oneOf:
- type: string
enum:
- brave_search
- wolfram_alpha
- photogen
- code_interpreter
title: BuiltinTool
- type: string
description: Name of the tool that was invoked
content:
$ref: '#/components/schemas/InterleavedContent'
description: The response content from the tool
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
(Optional) Additional metadata about the tool response
additionalProperties: false
required:
- call_id
- tool_name
- content
title: ToolResponse
description: Response from a tool invocation.
ToolResponseMessage:
type: object
properties:
role:
type: string
const: tool
default: tool
description: >-
Must be "tool" to identify this as a tool response
call_id:
type: string
description: >-
Unique identifier for the tool call this response is for
content:
$ref: '#/components/schemas/InterleavedContent'
description: The response content from the tool
additionalProperties: false
required:
- role
- call_id
- content
title: ToolResponseMessage
description: >-
A message representing the result of a tool invocation.
Turn:
$defs:
Attachment:
description: >-
An attachment to an agent turn.
:param content: The content of the attachment.
:param mime_type: The MIME type of the attachment.
properties:
content:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
- $ref: '#/$defs/URL'
title: Content
mime_type:
title: Mime Type
type: string
required:
- content
- mime_type
title: Attachment
type: object
BuiltinTool:
enum:
- brave_search
- wolfram_alpha
- photogen
- code_interpreter
title: BuiltinTool
type: string
CompletionMessage:
description: >-
A message containing the model's (assistant) response in a chat conversation.
:param role: Must be "assistant" to identify this as the model's response
:param content: The content of the model's response
:param stop_reason: Reason why the model stopped generating. Options are:
- `StopReason.end_of_turn`: The model finished generating the entire
response.
- `StopReason.end_of_message`: The model finished generating but generated
a partial response -- usually, a tool call. The user may call the tool
and continue the conversation with the tool's response.
- `StopReason.out_of_tokens`: The model ran out of token budget.
:param tool_calls: List of tool calls. Each tool call is a ToolCall object.
properties:
role:
const: assistant
default: assistant
title: Role
type: string
content:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
title: Content
stop_reason:
$ref: '#/$defs/StopReason'
tool_calls:
anyOf:
- items:
$ref: '#/$defs/ToolCall'
type: array
- type: 'null'
title: Tool Calls
required:
- content
- stop_reason
title: CompletionMessage
type: object
ImageContentItem:
description: >-
A image content item
:param type: Discriminator type of the content item. Always "image"
:param image: Image as a base64 encoded string or an URL
properties:
type:
const: image
default: image
title: Type
type: string
image:
$ref: '#/$defs/_URLOrData'
required:
- image
title: ImageContentItem
type: object
InferenceStep:
description: >-
An inference step in an agent turn.
:param model_response: The response from the LLM.
properties:
turn_id:
title: Turn Id
type: string
step_id:
title: Step Id
type: string
started_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Started At
completed_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Completed At
step_type:
const: inference
default: inference
title: Step Type
type: string
model_response:
$ref: '#/$defs/CompletionMessage'
required:
- turn_id
- step_id
- model_response
title: InferenceStep
type: object
MemoryRetrievalStep:
description: >-
A memory retrieval step in an agent turn.
:param vector_store_ids: The IDs of the vector databases to retrieve context
from.
:param inserted_context: The context retrieved from the vector databases.
properties:
turn_id:
title: Turn Id
type: string
step_id:
title: Step Id
type: string
started_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Started At
completed_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Completed At
step_type:
const: memory_retrieval
default: memory_retrieval
title: Step Type
type: string
vector_store_ids:
title: Vector Store Ids
type: string
inserted_context:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
title: Inserted Context
required:
- turn_id
- step_id
- vector_store_ids
- inserted_context
title: MemoryRetrievalStep
type: object
SafetyViolation:
description: >-
Details of a safety violation detected by content moderation.
:param violation_level: Severity level of the violation
:param user_message: (Optional) Message to convey to the user about the
violation
:param metadata: Additional metadata including specific violation codes
for debugging and telemetry
properties:
violation_level:
$ref: '#/$defs/ViolationLevel'
user_message:
anyOf:
- type: string
- type: 'null'
title: User Message
metadata:
additionalProperties: true
title: Metadata
type: object
required:
- violation_level
title: SafetyViolation
type: object
ShieldCallStep:
description: >-
A shield call step in an agent turn.
:param violation: The violation from the shield call.
properties:
turn_id:
title: Turn Id
type: string
step_id:
title: Step Id
type: string
started_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Started At
completed_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Completed At
step_type:
const: shield_call
default: shield_call
title: Step Type
type: string
violation:
anyOf:
- $ref: '#/$defs/SafetyViolation'
- type: 'null'
required:
- turn_id
- step_id
- violation
title: ShieldCallStep
type: object
StopReason:
enum:
- end_of_turn
- end_of_message
- out_of_tokens
title: StopReason
type: string
TextContentItem:
description: >-
A text content item
:param type: Discriminator type of the content item. Always "text"
:param text: Text content
properties:
type:
const: text
default: text
title: Type
type: string
text:
title: Text
type: string
required:
- text
title: TextContentItem
type: object
ToolCall:
properties:
call_id:
title: Call Id
type: string
tool_name:
anyOf:
- $ref: '#/$defs/BuiltinTool'
- type: string
title: Tool Name
arguments:
title: Arguments
type: string
required:
- call_id
- tool_name
- arguments
title: ToolCall
type: object
ToolExecutionStep:
description: >-
A tool execution step in an agent turn.
:param tool_calls: The tool calls to execute.
:param tool_responses: The tool responses from the tool calls.
properties:
turn_id:
title: Turn Id
type: string
step_id:
title: Step Id
type: string
started_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Started At
completed_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Completed At
step_type:
const: tool_execution
default: tool_execution
title: Step Type
type: string
tool_calls:
items:
$ref: '#/$defs/ToolCall'
title: Tool Calls
type: array
tool_responses:
items:
$ref: '#/$defs/ToolResponse'
title: Tool Responses
type: array
required:
- turn_id
- step_id
- tool_calls
- tool_responses
title: ToolExecutionStep
type: object
ToolResponse:
description: >-
Response from a tool invocation.
:param call_id: Unique identifier for the tool call this response is for
:param tool_name: Name of the tool that was invoked
:param content: The response content from the tool
:param metadata: (Optional) Additional metadata about the tool response
properties:
call_id:
title: Call Id
type: string
tool_name:
anyOf:
- $ref: '#/$defs/BuiltinTool'
- type: string
title: Tool Name
content:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
title: Content
metadata:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Metadata
required:
- call_id
- tool_name
- content
title: ToolResponse
type: object
ToolResponseMessage:
description: >-
A message representing the result of a tool invocation.
:param role: Must be "tool" to identify this as a tool response
:param call_id: Unique identifier for the tool call this response is for
:param content: The response content from the tool
properties:
role:
const: tool
default: tool
title: Role
type: string
call_id:
title: Call Id
type: string
content:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
title: Content
required:
- call_id
- content
title: ToolResponseMessage
type: object
URL:
description: >-
A URL reference to external content.
:param uri: The URL string pointing to the resource
properties:
uri:
title: Uri
type: string
required:
- uri
title: URL
type: object
UserMessage:
description: >-
A message from the user in a chat conversation.
:param role: Must be "user" to identify this as a user message
:param content: The content of the message, which can include text and
other media
:param context: (Optional) This field is used internally by Llama Stack
to pass RAG context. This field may be removed in the API in the future.
properties:
role:
const: user
default: user
title: Role
type: string
content:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
title: Content
context:
anyOf:
- type: string
- discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
- items:
discriminator:
mapping:
image: '#/$defs/ImageContentItem'
text: '#/$defs/TextContentItem'
propertyName: type
oneOf:
- $ref: '#/$defs/ImageContentItem'
- $ref: '#/$defs/TextContentItem'
type: array
- type: 'null'
title: Context
required:
- content
title: UserMessage
type: object
ViolationLevel:
description: >-
Severity level of a safety violation.
:cvar INFO: Informational level violation that does not require action
:cvar WARN: Warning level violation that suggests caution but allows continuation
:cvar ERROR: Error level violation that requires blocking or intervention
enum:
- info
- warn
- error
title: ViolationLevel
type: string
_URLOrData:
description: >-
A URL or a base64 encoded string
:param url: A URL of the image or data URL in the format of data:image/{type};base64,{data}.
Note that URL could have length limits.
:param data: base64 encoded image data as string
properties:
url:
anyOf:
- $ref: '#/$defs/URL'
- type: 'null'
data:
anyOf:
- type: string
- type: 'null'
contentEncoding: base64
title: Data
title: _URLOrData
type: object
description: >-
A single turn in an interaction with an Agentic System.
:param turn_id: Unique identifier for the turn within a session
:param session_id: Unique identifier for the conversation session
:param input_messages: List of messages that initiated this turn
:param steps: Ordered list of processing steps executed during this turn
:param output_message: The model's generated response containing content and
metadata
:param output_attachments: (Optional) Files or media attached to the agent's
response
:param started_at: Timestamp when the turn began
:param completed_at: (Optional) Timestamp when the turn finished, if completed
properties:
turn_id:
title: Turn Id
type: string
session_id:
title: Session Id
type: string
input_messages:
items:
anyOf:
- $ref: '#/$defs/UserMessage'
- $ref: '#/$defs/ToolResponseMessage'
title: Input Messages
type: array
steps:
items:
discriminator:
mapping:
file_search_call: '#/$defs/OpenAIResponseOutputMessageFileSearchToolCall'
function_call: '#/$defs/OpenAIResponseOutputMessageFunctionToolCall'
mcp_approval_request: '#/$defs/OpenAIResponseMCPApprovalRequest'
mcp_call: '#/$defs/OpenAIResponseOutputMessageMCPCall'
mcp_list_tools: '#/$defs/OpenAIResponseOutputMessageMCPListTools'
message: '#/$defs/OpenAIResponseMessage'
web_search_call: '#/$defs/OpenAIResponseOutputMessageWebSearchToolCall'
propertyName: type
oneOf:
- $ref: '#/components/schemas/OpenAIResponseMessage'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
title: Output
type: array
parallel_tool_calls:
default: false
title: Parallel Tool Calls
type: boolean
previous_response_id:
title: Previous Response Id
type: string
completed_at:
anyOf:
- format: date-time
type: string
- type: 'null'
title: Completed At
required:
- turn_id
- session_id
- input_messages
- steps
- output_message
- started_at
title: Turn
description: >-
A single turn in an interaction with an Agentic System.
UserMessage:
type: object
properties:
role:
type: string
const: user
default: user
description: >-
Must be "user" to identify this as a user message
content:
$ref: '#/components/schemas/InterleavedContent'
description: >-
The content of the message, which can include text and other media
context:
$ref: '#/components/schemas/InterleavedContent'
description: >-
(Optional) This field is used internally by Llama Stack to pass RAG context.
This field may be removed in the API in the future.
additionalProperties: false
required:
- role
- content
title: UserMessage
description: >-
A message from the user in a chat conversation.
CreateAgentTurnRequest:
type: object
ResumeAgentTurnRequest:
type: object
AgentStepResponse:
$defs:
BuiltinTool:
enum:
- brave_search
- wolfram_alpha
- photogen
- code_interpreter
title: BuiltinTool
type: string
temperature:
title: Temperature
type: number
nullable: true
text:
$ref: '#/components/schemas/OpenAIResponseText'
default:
format:
type: text
top_p:
title: Top P
type: number
nullable: true
tools:
title: Tools
items:
discriminator:
mapping:
file_search: '#/$defs/OpenAIResponseInputToolFileSearch'
function: '#/$defs/OpenAIResponseInputToolFunction'
mcp: '#/$defs/OpenAIResponseToolMCP'
web_search: '#/$defs/OpenAIResponseInputToolWebSearch'
web_search_preview: '#/$defs/OpenAIResponseInputToolWebSearch'
web_search_preview_2025_03_11: '#/$defs/OpenAIResponseInputToolWebSearch'
propertyName: type
oneOf:
- $ref: '#/components/schemas/OpenAIResponseInputToolWebSearch'
- $ref: '#/components/schemas/OpenAIResponseInputToolFileSearch'
- $ref: '#/components/schemas/OpenAIResponseInputToolFunction'
- $ref: '#/components/schemas/OpenAIResponseToolMCP'
type: array
nullable: true
truncation:
title: Truncation
type: string
nullable: true
usage:
$ref: '#/components/schemas/OpenAIResponseUsage'
nullable: true
instructions:
title: Instructions
type: string
nullable: true
input:
items:
anyOf:
- discriminator:
mapping:
file_search_call: '#/$defs/OpenAIResponseOutputMessageFileSearchToolCall'
function_call: '#/$defs/OpenAIResponseOutputMessageFunctionToolCall'
mcp_approval_request: '#/$defs/OpenAIResponseMCPApprovalRequest'
mcp_call: '#/$defs/OpenAIResponseOutputMessageMCPCall'
mcp_list_tools: '#/$defs/OpenAIResponseOutputMessageMCPListTools'
message: '#/$defs/OpenAIResponseMessage'
web_search_call: '#/$defs/OpenAIResponseOutputMessageWebSearchToolCall'
propertyName: type
oneOf:
- $ref: '#/components/schemas/OpenAIResponseMessage'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalRequest'
- $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
- $ref: '#/components/schemas/OpenAIResponseMCPApprovalResponse'
- $ref: '#/components/schemas/OpenAIResponseMessage'
title: Input
type: array
required:
- created_at
- id
- model
- output
- status
- input
title: OpenAIResponseObjectWithInput
type: object
ImageContentItem:
description: A image content item
properties:
type:
const: image
default: image
title: Type
type: string
image:
$ref: '#/components/schemas/_URLOrData'
required:
- image
title: ImageContentItem
type: object
properties:
type:
type: string
const: agent
default: agent
config:
$ref: '#/components/schemas/AgentConfig'
description: >-
The configuration for the agent candidate.
additionalProperties: false
required:
- type
- config
title: AgentCandidate
description: An agent candidate for evaluation.
BenchmarkConfig:
type: object
properties:
eval_candidate:
oneOf:
- $ref: '#/components/schemas/ModelCandidate'
- $ref: '#/components/schemas/AgentCandidate'
discriminator:
propertyName: type
mapping:
model: '#/components/schemas/ModelCandidate'
agent: '#/components/schemas/AgentCandidate'
description: The candidate to evaluate.
scoring_params:
type: object
additionalProperties:
$ref: '#/components/schemas/ScoringFnParams'
description: >-
Map between scoring function id and parameters for each scoring function
you want to run
num_examples:
type: integer
description: >-
(Optional) The number of examples to evaluate. If not provided, all examples
in the dataset will be evaluated
additionalProperties: false
required:
- eval_candidate
- scoring_params
title: BenchmarkConfig
description: >-
A benchmark configuration for evaluation.
ModelCandidate:
type: object
properties:
type:
type: string
const: model
default: model
model:
type: string
description: The model ID to evaluate.
sampling_params:
$ref: '#/components/schemas/SamplingParams'
description: The sampling parameters for the model.
system_message:
$ref: '#/components/schemas/SystemMessage'
description: >-
(Optional) The system message providing instructions or context to the
model.
additionalProperties: false
required:
- type
- model
- sampling_params
title: ModelCandidate
description: A model candidate for evaluation.
SystemMessage:
type: object
properties:
role:
type: string
const: system
default: system
description: >-
Must be "system" to identify this as a system message
content:
$ref: '#/components/schemas/InterleavedContent'
description: >-
The content of the "system prompt". If multiple system messages are provided,
they are concatenated. The underlying Llama Stack code may also add other
system messages (for example, for formatting tool definitions).
additionalProperties: false
required:
- role
- content
title: SystemMessage
description: >-
A system message providing instructions or context to the model.
EvaluateRowsRequest:
type: object
EvaluateResponse:
$defs:
ScoringResult:
description: >-
A scoring result for a single row.
:param score_rows: The scoring result for each row. Each row is a map
of column name to value.
:param aggregated_results: Map of metric name to aggregated value
properties:
score_rows:
items:
additionalProperties: true
type: object
title: Score Rows
type: array
aggregated_results:
additionalProperties: true
title: Aggregated Results
type: object
required:
- score_rows
- aggregated_results
title: ScoringResult
type: object
description: >-
The response from an evaluation.
:param generations: The generations from the evaluation.
:param scores: The scores from the evaluation.
properties:
epoch:
title: Epoch
type: integer
train_loss:
title: Train Loss
type: number
validation_loss:
title: Validation Loss
type: number
perplexity:
title: Perplexity
type: number
required:
- epoch
- train_loss
- validation_loss
- perplexity
title: PostTrainingMetric
type: object
_safety_run_shield_Request:
properties:
shield_id:
title: Shield Id
type: string
messages:
anyOf:
- $ref: '#/components/schemas/OpenAIUserMessageParam'
- $ref: '#/components/schemas/OpenAISystemMessageParam'
- $ref: '#/components/schemas/OpenAIAssistantMessageParam'
- $ref: '#/components/schemas/OpenAIToolMessageParam'
- $ref: '#/components/schemas/OpenAIDeveloperMessageParam'
title: Messages
params:
title: Params
type: string
required:
- shield_id
- messages
- params
title: _safety_run_shield_Request
type: object
responses:
BadRequest400:
description: The request was invalid or malformed
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
example:
status: 400
title: Bad Request
detail: The request was invalid or malformed
TooManyRequests429:
description: The client has sent too many requests in a given amount of time
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
example:
status: 429
title: Too Many Requests
detail: You have exceeded the rate limit. Please try again later.
InternalServerError500:
description: The server encountered an unexpected error
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
example:
status: 500
title: Internal Server Error
detail: An unexpected error occurred. Our team has been notified.
DefaultError:
description: An unexpected error occurred
content:
application/json:
schema:
$ref: '#/components/schemas/Error'
example:
status: 0
title: Error
detail: An unexpected error occurred
security:
- Default: []
tags:
- name: Agents
description: >-
APIs for creating and interacting with agentic systems.
x-displayName: Agents
- name: Batches
description: >-
The API is designed to allow use of openai client libraries for seamless integration.
This API provides the following extensions:
- idempotent batch creation
Note: This API is currently under active development and may undergo changes.
x-displayName: >-
The Batches API enables efficient processing of multiple requests in a single
operation, particularly useful for processing large datasets, batch evaluation
workflows, and cost-effective inference at scale.
- name: Benchmarks
description: ''
- name: Conversations
description: >-
Protocol for conversation management operations.
x-displayName: Conversations
- name: DatasetIO
description: ''
- name: Datasets
description: ''
- name: Eval
description: >-
Llama Stack Evaluation API for running evaluations on model and agent candidates.
x-displayName: Evaluations
- name: Files
description: >-
This API is used to upload documents that can be used with other Llama Stack
APIs.
x-displayName: Files
- name: Inference
description: >-
Llama Stack Inference API for generating completions, chat completions, and
embeddings.
This API provides the raw interface to the underlying models. Three kinds
of models are supported:
- LLM models: these models generate "raw" and "chat" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic
search.
- Rerank models: these models reorder the documents based on their relevance
to a query.
x-displayName: Inference
- name: Inspect
description: >-
APIs for inspecting the Llama Stack service, including health status, available
API routes with methods and implementing providers.
x-displayName: Inspect
- name: Models
description: ''
- name: PostTraining (Coming Soon)
description: ''
- name: Prompts
description: >-
Protocol for prompt management operations.
x-displayName: Prompts
- name: Providers
description: >-
Providers API for inspecting, listing, and modifying providers and their configurations.
x-displayName: Providers
- name: Safety
description: OpenAI-compatible Moderations API.
x-displayName: Safety
- name: Scoring
description: ''
- name: ScoringFunctions
description: ''
- name: Shields
description: ''
- name: ToolGroups
description: ''
- name: ToolRuntime
description: ''
- name: VectorIO
description: ''
x-tagGroups:
- name: Operations
tags:
- Agents
- Batches
- Benchmarks
- Conversations
- DatasetIO
- Datasets
- Eval
- Files
- Inference
- Inspect
- Models
- PostTraining (Coming Soon)
- Prompts
- Providers
- Safety
- Scoring
- ScoringFunctions
- Shields
- ToolGroups
- ToolRuntime
- VectorIO