phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
llama-stack-mirror/docs/_static/llama-stack-spec.yaml
Francisco Arceo 82f13fe83e
feat: Add ChunkMetadata to Chunk (#2497) 
# What does this PR do?
Adding `ChunkMetadata` so we can properly delete embeddings later.

More specifically, this PR refactors and extends the chunk metadata
handling in the vector database and introduces a distinction between
metadata used for model context and backend-only metadata required for
chunk management, storage, and retrieval. It also improves chunk ID
generation and propagation throughout the stack, enhances test coverage,
and adds new utility modules.

```python
class ChunkMetadata(BaseModel):
    """
    `ChunkMetadata` is backend metadata for a `Chunk` that is used to store additional information about the chunk that
        will NOT be inserted into the context during inference, but is required for backend functionality.
        Use `metadata` in `Chunk` for metadata that will be used during inference.
    """
    document_id: str | None = None
    chunk_id: str | None = None
    source: str | None = None
    created_timestamp: int | None = None
    updated_timestamp: int | None = None
    chunk_window: str | None = None
    chunk_tokenizer: str | None = None
    chunk_embedding_model: str | None = None
    chunk_embedding_dimension: int | None = None
    content_token_count: int | None = None
    metadata_token_count: int | None = None
```
Eventually we can migrate the document_id out of the `metadata` field.
I've introduced the changes so that `ChunkMetadata` is backwards
compatible with `metadata`.

<!-- If resolving an issue, uncomment and update the line below -->
Closes https://github.com/meta-llama/llama-stack/issues/2501 

## Test Plan
Added unit tests

---------

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
2025-06-25 15:55:23 -04:00

11230 lines
322 KiB
YAML
Raw Blame History

openapi: 3.1.0
info:
title: Llama Stack Specification
version: v1
description: >-
This is the specification of the Llama Stack that provides
a set of endpoints and their corresponding interfaces that are
tailored to
best leverage Llama Models.
servers:
- url: http://any-hosted-llama-stack.com
paths:
/v1/datasetio/append-rows/{dataset_id}:
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:
- DatasetIO
description: Append rows to a dataset.
parameters:
- name: dataset_id
in: path
description: >-
The ID of the dataset to append the rows to.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/AppendRowsRequest'
required: true
/v1/inference/batch-chat-completion:
post:
responses:
'200':
description: >-
A BatchChatCompletionResponse with the full completions.
content:
application/json:
schema:
$ref: '#/components/schemas/BatchChatCompletionResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inference
description: >-
Generate chat completions for a batch of messages using the specified model.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/BatchChatCompletionRequest'
required: true
/v1/inference/batch-completion:
post:
responses:
'200':
description: >-
A BatchCompletionResponse with the full completions.
content:
application/json:
schema:
$ref: '#/components/schemas/BatchCompletionResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inference
description: >-
Generate completions for a batch of content using the specified model.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/BatchCompletionRequest'
required: true
/v1/post-training/job/cancel:
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:
- PostTraining (Coming Soon)
description: Cancel a training job.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CancelTrainingJobRequest'
required: true
/v1/inference/chat-completion:
post:
responses:
'200':
description: >-
If stream=False, returns a ChatCompletionResponse with the full completion.
If stream=True, returns an SSE event stream of ChatCompletionResponseStreamChunk.
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionResponse'
text/event-stream:
schema:
$ref: '#/components/schemas/ChatCompletionResponseStreamChunk'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- BatchInference (Coming Soon)
description: >-
Generate a chat completion for the given messages using the specified model.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionRequest'
required: true
/v1/inference/completion:
post:
responses:
'200':
description: >-
If stream=False, returns a CompletionResponse with the full completion.
If stream=True, returns an SSE event stream of CompletionResponseStreamChunk.
content:
application/json:
schema:
$ref: '#/components/schemas/CompletionResponse'
text/event-stream:
schema:
$ref: '#/components/schemas/CompletionResponseStreamChunk'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- BatchInference (Coming Soon)
description: >-
Generate a completion for the given content using the specified model.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CompletionRequest'
required: true
/v1/agents:
get:
responses:
'200':
description: A PaginatedResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/PaginatedResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
description: List all agents.
parameters:
- name: start_index
in: query
description: The index to start the pagination from.
required: false
schema:
type: integer
- name: limit
in: query
description: The number of agents to return.
required: false
schema:
type: integer
post:
responses:
'200':
description: >-
An AgentCreateResponse with the agent ID.
content:
application/json:
schema:
$ref: '#/components/schemas/AgentCreateResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
description: >-
Create an agent with the given configuration.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CreateAgentRequest'
required: true
/v1/agents/{agent_id}/session:
post:
responses:
'200':
description: An AgentSessionCreateResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/AgentSessionCreateResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
description: Create a new session for an agent.
parameters:
- name: agent_id
in: path
description: >-
The ID of the agent to create the session for.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CreateAgentSessionRequest'
required: true
/v1/agents/{agent_id}/session/{session_id}/turn:
post:
responses:
'200':
description: >-
If stream=False, returns a Turn object. If stream=True, returns an SSE
event stream of AgentTurnResponseStreamChunk.
content:
application/json:
schema:
$ref: '#/components/schemas/Turn'
text/event-stream:
schema:
$ref: '#/components/schemas/AgentTurnResponseStreamChunk'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
description: Create a new turn for an agent.
parameters:
- name: agent_id
in: path
description: >-
The ID of the agent to create the turn for.
required: true
schema:
type: string
- name: session_id
in: path
description: >-
The ID of the session to create the turn for.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CreateAgentTurnRequest'
required: true
/v1/openai/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
description: List all OpenAI responses.
parameters:
- name: after
in: query
description: The ID of the last response to return.
required: false
schema:
type: string
- name: limit
in: query
description: The number of responses to return.
required: false
schema:
type: integer
- name: model
in: query
description: The model to filter responses by.
required: false
schema:
type: string
- name: order
in: query
description: >-
The order to sort responses by when sorted by created_at ('asc' or 'desc').
required: false
schema:
$ref: '#/components/schemas/Order'
post:
responses:
'200':
description: An OpenAIResponseObject.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIResponseObject'
text/event-stream:
schema:
$ref: '#/components/schemas/OpenAIResponseObjectStream'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
description: Create a new OpenAI response.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/CreateOpenaiResponseRequest'
required: true
/v1/agents/{agent_id}:
get:
responses:
'200':
description: An Agent of the agent.
content:
application/json:
schema:
$ref: '#/components/schemas/Agent'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
description: Describe an agent by its ID.
parameters:
- name: agent_id
in: path
description: ID of the agent.
required: true
schema:
type: string
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:
- Agents
description: >-
Delete an agent by its ID and its associated sessions and turns.
parameters:
- name: agent_id
in: path
description: The ID of the agent to delete.
required: true
schema:
type: string
/v1/agents/{agent_id}/session/{session_id}:
get:
responses:
'200':
description: A Session.
content:
application/json:
schema:
$ref: '#/components/schemas/Session'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
description: Retrieve an agent session by its ID.
parameters:
- name: session_id
in: path
description: The ID of the session to get.
required: true
schema:
type: string
- name: agent_id
in: path
description: >-
The ID of the agent to get the session for.
required: true
schema:
type: string
- name: turn_ids
in: query
description: >-
(Optional) List of turn IDs to filter the session by.
required: false
schema:
type: array
items:
type: string
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:
- Agents
description: >-
Delete an agent session by its ID and its associated turns.
parameters:
- name: session_id
in: path
description: The ID of the session to delete.
required: true
schema:
type: string
- name: agent_id
in: path
description: >-
The ID of the agent to delete the session for.
required: true
schema:
type: string
/v1/inference/embeddings:
post:
responses:
'200':
description: >-
An array of embeddings, one for each content. Each embedding is a list
of floats. The dimensionality of the embedding is model-specific; you
can check model metadata using /models/{model_id}.
content:
application/json:
schema:
$ref: '#/components/schemas/EmbeddingsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inference
description: >-
Generate embeddings for content pieces using the specified model.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/EmbeddingsRequest'
required: true
/v1/eval/benchmarks/{benchmark_id}/evaluations:
post:
responses:
'200':
description: >-
EvaluateResponse object containing generations and scores.
content:
application/json:
schema:
$ref: '#/components/schemas/EvaluateResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Eval
description: Evaluate a list of rows on a benchmark.
parameters:
- name: benchmark_id
in: path
description: >-
The ID of the benchmark to run the evaluation on.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/EvaluateRowsRequest'
required: true
/v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/step/{step_id}:
get:
responses:
'200':
description: An AgentStepResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/AgentStepResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
description: Retrieve an agent step by its ID.
parameters:
- name: agent_id
in: path
description: The ID of the agent to get the step for.
required: true
schema:
type: string
- name: session_id
in: path
description: >-
The ID of the session to get the step for.
required: true
schema:
type: string
- name: turn_id
in: path
description: The ID of the turn to get the step for.
required: true
schema:
type: string
- name: step_id
in: path
description: The ID of the step to get.
required: true
schema:
type: string
/v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}:
get:
responses:
'200':
description: A Turn.
content:
application/json:
schema:
$ref: '#/components/schemas/Turn'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
description: Retrieve an agent turn by its ID.
parameters:
- name: agent_id
in: path
description: The ID of the agent to get the turn for.
required: true
schema:
type: string
- name: session_id
in: path
description: >-
The ID of the session to get the turn for.
required: true
schema:
type: string
- name: turn_id
in: path
description: The ID of the turn to get.
required: true
schema:
type: string
/v1/eval/benchmarks/{benchmark_id}:
get:
responses:
'200':
description: A Benchmark.
content:
application/json:
schema:
$ref: '#/components/schemas/Benchmark'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Benchmarks
description: Get a benchmark by its ID.
parameters:
- name: benchmark_id
in: path
description: The ID of the benchmark to get.
required: true
schema:
type: string
/v1/openai/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
description: Describe a chat completion by its ID.
parameters:
- name: completion_id
in: path
description: ID of the chat completion.
required: true
schema:
type: string
/v1/datasets/{dataset_id}:
get:
responses:
'200':
description: A Dataset.
content:
application/json:
schema:
$ref: '#/components/schemas/Dataset'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Datasets
description: Get a dataset by its ID.
parameters:
- name: dataset_id
in: path
description: The ID of the dataset to get.
required: true
schema:
type: string
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:
- Datasets
description: Unregister a dataset by its ID.
parameters:
- name: dataset_id
in: path
description: The ID of the dataset to unregister.
required: true
schema:
type: string
/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
description: Get a model by its identifier.
parameters:
- name: model_id
in: path
description: The identifier of the model to get.
required: true
schema:
type: string
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
description: Unregister a model.
parameters:
- name: model_id
in: path
description: >-
The identifier of the model to unregister.
required: true
schema:
type: string
/v1/openai/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
description: Retrieve an OpenAI response by its ID.
parameters:
- name: response_id
in: path
description: >-
The ID of the OpenAI response to retrieve.
required: true
schema:
type: string
/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
description: Get a scoring function by its ID.
parameters:
- name: scoring_fn_id
in: path
description: The ID of the scoring function to get.
required: true
schema:
type: string
/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
description: Get a shield by its identifier.
parameters:
- name: identifier
in: path
description: The identifier of the shield to get.
required: true
schema:
type: string
/v1/telemetry/traces/{trace_id}/spans/{span_id}:
get:
responses:
'200':
description: A Span.
content:
application/json:
schema:
$ref: '#/components/schemas/Span'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Telemetry
description: Get a span by its ID.
parameters:
- name: trace_id
in: path
description: >-
The ID of the trace to get the span from.
required: true
schema:
type: string
- name: span_id
in: path
description: The ID of the span to get.
required: true
schema:
type: string
/v1/telemetry/spans/{span_id}/tree:
post:
responses:
'200':
description: A QuerySpanTreeResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/QuerySpanTreeResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Telemetry
description: Get a span tree by its ID.
parameters:
- name: span_id
in: path
description: The ID of the span to get the tree from.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/GetSpanTreeRequest'
required: true
/v1/tools/{tool_name}:
get:
responses:
'200':
description: A Tool.
content:
application/json:
schema:
$ref: '#/components/schemas/Tool'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ToolGroups
description: Get a tool by its name.
parameters:
- name: tool_name
in: path
description: The name of the tool to get.
required: true
schema:
type: string
/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
description: Get a tool group by its ID.
parameters:
- name: toolgroup_id
in: path
description: The ID of the tool group to get.
required: true
schema:
type: string
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
description: Unregister a tool group.
parameters:
- name: toolgroup_id
in: path
description: The ID of the tool group to unregister.
required: true
schema:
type: string
/v1/telemetry/traces/{trace_id}:
get:
responses:
'200':
description: A Trace.
content:
application/json:
schema:
$ref: '#/components/schemas/Trace'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Telemetry
description: Get a trace by its ID.
parameters:
- name: trace_id
in: path
description: The ID of the trace to get.
required: true
schema:
type: string
/v1/post-training/job/artifacts:
get:
responses:
'200':
description: A PostTrainingJobArtifactsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/PostTrainingJobArtifactsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- PostTraining (Coming Soon)
description: Get the artifacts of a training job.
parameters:
- name: job_uuid
in: query
description: >-
The UUID of the job to get the artifacts of.
required: true
schema:
type: string
/v1/post-training/job/status:
get:
responses:
'200':
description: A PostTrainingJobStatusResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/PostTrainingJobStatusResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- PostTraining (Coming Soon)
description: Get the status of a training job.
parameters:
- name: job_uuid
in: query
description: >-
The UUID of the job to get the status of.
required: true
schema:
type: string
/v1/post-training/jobs:
get:
responses:
'200':
description: A ListPostTrainingJobsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListPostTrainingJobsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- PostTraining (Coming Soon)
description: Get all training jobs.
parameters: []
/v1/vector-dbs/{vector_db_id}:
get:
responses:
'200':
description: A VectorDB.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorDB'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorDBs
description: Get a vector database by its identifier.
parameters:
- name: vector_db_id
in: path
description: >-
The identifier of the vector database to get.
required: true
schema:
type: string
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:
- VectorDBs
description: Unregister a vector database.
parameters:
- name: vector_db_id
in: path
description: >-
The identifier of the vector database to unregister.
required: true
schema:
type: string
/v1/health:
get:
responses:
'200':
description: A HealthInfo.
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
description: Get the health of the service.
parameters: []
/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
description: >-
Index documents so they can be used by the RAG system
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/InsertRequest'
required: true
/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
description: Insert chunks into a vector database.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/InsertChunksRequest'
required: true
/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
description: >-
Get detailed information about a specific provider.
parameters:
- name: provider_id
in: path
description: The ID of the provider to inspect.
required: true
schema:
type: string
/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
description: Run a tool with the given arguments.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/InvokeToolRequest'
required: true
/v1/datasetio/iterrows/{dataset_id}:
get:
responses:
'200':
description: A PaginatedResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/PaginatedResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- DatasetIO
description: >-
Get a paginated list of rows from a dataset.
Uses offset-based pagination where:
- start_index: The starting index (0-based). If None, starts from beginning.
- limit: Number of items to return. If None or -1, returns all items.
The response includes:
- data: List of items for the current page.
- has_more: Whether there are more items available after this set.
parameters:
- name: dataset_id
in: path
description: >-
The ID of the dataset to get the rows from.
required: true
schema:
type: string
- name: start_index
in: query
description: >-
Index into dataset for the first row to get. Get all rows if None.
required: false
schema:
type: integer
- name: limit
in: query
description: The number of rows to get.
required: false
schema:
type: integer
/v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}:
get:
responses:
'200':
description: The status of the evaluation job.
content:
application/json:
schema:
$ref: '#/components/schemas/Job'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Eval
description: Get the status of a job.
parameters:
- name: benchmark_id
in: path
description: >-
The ID of the benchmark to run the evaluation on.
required: true
schema:
type: string
- name: job_id
in: path
description: The ID of the job to get the status of.
required: true
schema:
type: string
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:
- Eval
description: Cancel a job.
parameters:
- name: benchmark_id
in: path
description: >-
The ID of the benchmark to run the evaluation on.
required: true
schema:
type: string
- name: job_id
in: path
description: The ID of the job to cancel.
required: true
schema:
type: string
/v1/eval/benchmarks/{benchmark_id}/jobs/{job_id}/result:
get:
responses:
'200':
description: The result of the job.
content:
application/json:
schema:
$ref: '#/components/schemas/EvaluateResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Eval
description: Get the result of a job.
parameters:
- name: benchmark_id
in: path
description: >-
The ID of the benchmark to run the evaluation on.
required: true
schema:
type: string
- name: job_id
in: path
description: The ID of the job to get the result of.
required: true
schema:
type: string
/v1/agents/{agent_id}/sessions:
get:
responses:
'200':
description: A PaginatedResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/PaginatedResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
description: List all session(s) of a given agent.
parameters:
- name: agent_id
in: path
description: >-
The ID of the agent to list sessions for.
required: true
schema:
type: string
- name: start_index
in: query
description: The index to start the pagination from.
required: false
schema:
type: integer
- name: limit
in: query
description: The number of sessions to return.
required: false
schema:
type: integer
/v1/eval/benchmarks:
get:
responses:
'200':
description: A ListBenchmarksResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListBenchmarksResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Benchmarks
description: List all benchmarks.
parameters: []
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:
- Benchmarks
description: Register a benchmark.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RegisterBenchmarkRequest'
required: true
/v1/openai/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
description: List all chat completions.
parameters:
- name: after
in: query
description: >-
The ID of the last chat completion to return.
required: false
schema:
type: string
- name: limit
in: query
description: >-
The maximum number of chat completions to return.
required: false
schema:
type: integer
- name: model
in: query
description: The model to filter by.
required: false
schema:
type: string
- name: order
in: query
description: >-
The order to sort the chat completions by: "asc" or "desc". Defaults to
"desc".
required: false
schema:
$ref: '#/components/schemas/Order'
post:
responses:
'200':
description: An OpenAIChatCompletion.
content:
application/json:
schema:
oneOf:
- $ref: '#/components/schemas/OpenAIChatCompletion'
- $ref: '#/components/schemas/OpenAIChatCompletionChunk'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inference
description: >-
Generate an OpenAI-compatible chat completion for the given messages using
the specified model.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiChatCompletionRequest'
required: true
/v1/datasets:
get:
responses:
'200':
description: A ListDatasetsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListDatasetsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Datasets
description: List all datasets.
parameters: []
post:
responses:
'200':
description: A Dataset.
content:
application/json:
schema:
$ref: '#/components/schemas/Dataset'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Datasets
description: Register a new dataset.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RegisterDatasetRequest'
required: true
/v1/models:
get:
responses:
'200':
description: A ListModelsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListModelsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Models
description: List all models.
parameters: []
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
description: Register a model.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RegisterModelRequest'
required: true
/v1/openai/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
description: >-
List input items for a given OpenAI response.
parameters:
- name: response_id
in: path
description: >-
The ID of the response to retrieve input items for.
required: true
schema:
type: string
- name: after
in: query
description: >-
An item ID to list items after, used for pagination.
required: false
schema:
type: string
- name: before
in: query
description: >-
An item ID to list items before, used for pagination.
required: false
schema:
type: string
- name: include
in: query
description: >-
Additional fields to include in the response.
required: false
schema:
type: array
items:
type: string
- name: limit
in: query
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
- name: order
in: query
description: >-
The order to return the input items in. Default is desc.
required: false
schema:
$ref: '#/components/schemas/Order'
/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
description: List all available providers.
parameters: []
/v1/inspect/routes:
get:
responses:
'200':
description: A ListRoutesResponse.
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
description: List all routes.
parameters: []
/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
description: List all tools in the runtime.
parameters:
- name: tool_group_id
in: query
description: >-
The ID of the tool group to list tools for.
required: false
schema:
type: string
- name: mcp_endpoint
in: query
description: >-
The MCP endpoint to use for the tool group.
required: false
schema:
$ref: '#/components/schemas/URL'
/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
description: List all scoring functions.
parameters: []
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
description: Register a scoring function.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RegisterScoringFunctionRequest'
required: true
/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
description: List all shields.
parameters: []
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
description: Register a shield.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RegisterShieldRequest'
required: true
/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
description: List tool groups with optional provider.
parameters: []
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
description: Register a tool group.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RegisterToolGroupRequest'
required: true
/v1/tools:
get:
responses:
'200':
description: A ListToolsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListToolsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- ToolGroups
description: List tools with optional tool group.
parameters:
- name: toolgroup_id
in: query
description: >-
The ID of the tool group to list tools for.
required: false
schema:
type: string
/v1/vector-dbs:
get:
responses:
'200':
description: A ListVectorDBsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/ListVectorDBsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorDBs
description: List all vector databases.
parameters: []
post:
responses:
'200':
description: A VectorDB.
content:
application/json:
schema:
$ref: '#/components/schemas/VectorDB'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- VectorDBs
description: Register a vector database.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RegisterVectorDbRequest'
required: true
/v1/telemetry/events:
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:
- Telemetry
description: Log an event.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/LogEventRequest'
required: true
/v1/openai/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
description: List files in a vector store.
parameters:
- name: vector_store_id
in: path
description: >-
The ID of the vector store to list files from.
required: true
schema:
type: string
- name: limit
in: query
required: false
schema:
type: integer
- name: order
in: query
required: false
schema:
type: string
- name: after
in: query
required: false
schema:
type: string
- name: before
in: query
required: false
schema:
type: string
- name: filter
in: query
required: false
schema:
$ref: '#/components/schemas/VectorStoreFileStatus'
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
description: Attach a file to a vector store.
parameters:
- name: vector_store_id
in: path
description: >-
The ID of the vector store to attach the file to.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiAttachFileToVectorStoreRequest'
required: true
/v1/openai/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
description: >-
Generate an OpenAI-compatible completion for the given prompt using the specified
model.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiCompletionRequest'
required: true
/v1/openai/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
description: Returns a list of vector stores.
parameters:
- name: limit
in: query
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
- name: order
in: query
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
- name: after
in: query
description: >-
A cursor for use in pagination. `after` is an object ID that defines your
place in the list.
required: false
schema:
type: string
- name: before
in: query
description: >-
A cursor for use in pagination. `before` is an object ID that defines
your place in the list.
required: false
schema:
type: string
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
description: Creates a vector store.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiCreateVectorStoreRequest'
required: true
/v1/openai/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
description: >-
Returns information about a specific file.
parameters:
- name: file_id
in: path
description: >-
The ID of the file to use for this request.
required: true
schema:
type: string
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
description: Delete a file.
parameters:
- name: file_id
in: path
description: >-
The ID of the file to use for this request.
required: true
schema:
type: string
/v1/openai/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
description: Retrieves a vector store.
parameters:
- name: vector_store_id
in: path
description: The ID of the vector store to retrieve.
required: true
schema:
type: string
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
description: Updates a vector store.
parameters:
- name: vector_store_id
in: path
description: The ID of the vector store to update.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiUpdateVectorStoreRequest'
required: true
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
description: Delete a vector store.
parameters:
- name: vector_store_id
in: path
description: The ID of the vector store to delete.
required: true
schema:
type: string
/v1/openai/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
description: Retrieves a vector store file.
parameters:
- name: vector_store_id
in: path
description: >-
The ID of the vector store containing the file to retrieve.
required: true
schema:
type: string
- name: file_id
in: path
description: The ID of the file to retrieve.
required: true
schema:
type: string
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
description: Updates a vector store file.
parameters:
- name: vector_store_id
in: path
description: >-
The ID of the vector store containing the file to update.
required: true
schema:
type: string
- name: file_id
in: path
description: The ID of the file to update.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiUpdateVectorStoreFileRequest'
required: true
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
description: Delete a vector store file.
parameters:
- name: vector_store_id
in: path
description: >-
The ID of the vector store containing the file to delete.
required: true
schema:
type: string
- name: file_id
in: path
description: The ID of the file to delete.
required: true
schema:
type: string
/v1/openai/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
description: >-
Generate OpenAI-compatible embeddings for the given input using the specified
model.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiEmbeddingsRequest'
required: true
/v1/openai/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
description: >-
Returns a list of files that belong to the user's organization.
parameters:
- name: after
in: query
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
- name: limit
in: query
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
- name: order
in: query
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'
- name: purpose
in: query
description: >-
Only return files with the given purpose.
required: false
schema:
$ref: '#/components/schemas/OpenAIFilePurpose'
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
description: >-
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.
parameters: []
requestBody:
content:
multipart/form-data:
schema:
type: object
properties:
file:
type: string
format: binary
purpose:
$ref: '#/components/schemas/OpenAIFilePurpose'
required:
- file
- purpose
required: true
/v1/openai/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
description: List models using the OpenAI API.
parameters: []
/v1/openai/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
description: >-
Returns the contents of the specified file.
parameters:
- name: file_id
in: path
description: >-
The ID of the file to use for this request.
required: true
schema:
type: string
/v1/openai/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
description: >-
Retrieves the contents of a vector store file.
parameters:
- name: vector_store_id
in: path
description: >-
The ID of the vector store containing the file to retrieve.
required: true
schema:
type: string
- name: file_id
in: path
description: The ID of the file to retrieve.
required: true
schema:
type: string
/v1/openai/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
description: >-
Search for chunks in a vector store.
Searches a vector store for relevant chunks based on a query and optional
file attribute filters.
parameters:
- name: vector_store_id
in: path
description: The ID of the vector store to search.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiSearchVectorStoreRequest'
required: true
/v1/post-training/preference-optimize:
post:
responses:
'200':
description: A PostTrainingJob.
content:
application/json:
schema:
$ref: '#/components/schemas/PostTrainingJob'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- PostTraining (Coming Soon)
description: Run preference optimization of a model.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/PreferenceOptimizeRequest'
required: true
/v1/tool-runtime/rag-tool/query:
post:
responses:
'200':
description: OK
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
description: >-
Query the RAG system for context; typically invoked by the agent
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/QueryRequest'
required: true
/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
description: Query chunks from a vector database.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/QueryChunksRequest'
required: true
/v1/telemetry/metrics/{metric_name}:
post:
responses:
'200':
description: A QueryMetricsResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/QueryMetricsResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Telemetry
description: Query metrics.
parameters:
- name: metric_name
in: path
description: The name of the metric to query.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/QueryMetricsRequest'
required: true
/v1/telemetry/spans:
post:
responses:
'200':
description: A QuerySpansResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/QuerySpansResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Telemetry
description: Query spans.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/QuerySpansRequest'
required: true
/v1/telemetry/traces:
post:
responses:
'200':
description: A QueryTracesResponse.
content:
application/json:
schema:
$ref: '#/components/schemas/QueryTracesResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Telemetry
description: Query traces.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/QueryTracesRequest'
required: true
/v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/resume:
post:
responses:
'200':
description: >-
A Turn object if stream is False, otherwise an AsyncIterator of AgentTurnResponseStreamChunk
objects.
content:
application/json:
schema:
$ref: '#/components/schemas/Turn'
text/event-stream:
schema:
$ref: '#/components/schemas/AgentTurnResponseStreamChunk'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
description: >-
Resume an agent turn with executed tool call responses.
When a Turn has the status `awaiting_input` due to pending input from client
side tool calls, this endpoint can be used to submit the outputs from the
tool calls once they are ready.
parameters:
- name: agent_id
in: path
description: The ID of the agent to resume.
required: true
schema:
type: string
- name: session_id
in: path
description: The ID of the session to resume.
required: true
schema:
type: string
- name: turn_id
in: path
description: The ID of the turn to resume.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ResumeAgentTurnRequest'
required: true
/v1/eval/benchmarks/{benchmark_id}/jobs:
post:
responses:
'200':
description: >-
The job that was created to run the evaluation.
content:
application/json:
schema:
$ref: '#/components/schemas/Job'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- Eval
description: Run an evaluation on a benchmark.
parameters:
- name: benchmark_id
in: path
description: >-
The ID of the benchmark to run the evaluation on.
required: true
schema:
type: string
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RunEvalRequest'
required: true
/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
description: Run a shield.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/RunShieldRequest'
required: true
/v1/telemetry/spans/export:
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:
- Telemetry
description: Save spans to a dataset.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/SaveSpansToDatasetRequest'
required: true
/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
description: Score a list of rows.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ScoreRequest'
required: true
/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
description: Score a batch of rows.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ScoreBatchRequest'
required: true
/v1/post-training/supervised-fine-tune:
post:
responses:
'200':
description: A PostTrainingJob.
content:
application/json:
schema:
$ref: '#/components/schemas/PostTrainingJob'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- PostTraining (Coming Soon)
description: Run supervised fine-tuning of a model.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/SupervisedFineTuneRequest'
required: true
/v1/synthetic-data-generation/generate:
post:
responses:
'200':
description: OK
content:
application/json:
schema:
$ref: '#/components/schemas/SyntheticDataGenerationResponse'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
$ref: >-
#/components/responses/TooManyRequests429
'500':
$ref: >-
#/components/responses/InternalServerError500
default:
$ref: '#/components/responses/DefaultError'
tags:
- SyntheticDataGeneration (Coming Soon)
description: ''
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/SyntheticDataGenerateRequest'
required: true
/v1/version:
get:
responses:
'200':
description: A VersionInfo.
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
description: Get the version of the service.
parameters: []
jsonSchemaDialect: >-
https://json-schema.org/draft/2020-12/schema
components:
schemas:
Error:
type: object
properties:
status:
type: integer
description: HTTP status code
title:
type: string
description: >-
Error title, a short summary of the error which is invariant for an error
type
detail:
type: string
description: >-
Error detail, a longer human-readable description of the error
instance:
type: string
description: >-
(Optional) A URL which can be used to retrieve more information about
the specific occurrence of the error
additionalProperties: false
required:
- status
- title
- detail
title: Error
description: >-
Error response from the API. Roughly follows RFC 7807.
AppendRowsRequest:
type: object
properties:
rows:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: The rows to append to the dataset.
additionalProperties: false
required:
- rows
title: AppendRowsRequest
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.
GrammarResponseFormat:
type: object
properties:
type:
type: string
enum:
- json_schema
- grammar
description: >-
Must be "grammar" to identify this format type
const: grammar
default: grammar
bnf:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
The BNF grammar specification the response should conform to
additionalProperties: false
required:
- type
- bnf
title: GrammarResponseFormat
description: >-
Configuration for grammar-guided response generation.
GreedySamplingStrategy:
type: object
properties:
type:
type: string
const: greedy
default: greedy
additionalProperties: false
required:
- type
title: GreedySamplingStrategy
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'
JsonSchemaResponseFormat:
type: object
properties:
type:
type: string
enum:
- json_schema
- grammar
description: >-
Must be "json_schema" to identify this format type
const: json_schema
default: json_schema
json_schema:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
The JSON schema the response should conform to. In a Python SDK, this
is often a `pydantic` model.
additionalProperties: false
required:
- type
- json_schema
title: JsonSchemaResponseFormat
description: >-
Configuration for JSON schema-guided response generation.
Message:
oneOf:
- $ref: '#/components/schemas/UserMessage'
- $ref: '#/components/schemas/SystemMessage'
- $ref: '#/components/schemas/ToolResponseMessage'
- $ref: '#/components/schemas/CompletionMessage'
discriminator:
propertyName: role
mapping:
user: '#/components/schemas/UserMessage'
system: '#/components/schemas/SystemMessage'
tool: '#/components/schemas/ToolResponseMessage'
assistant: '#/components/schemas/CompletionMessage'
ResponseFormat:
oneOf:
- $ref: '#/components/schemas/JsonSchemaResponseFormat'
- $ref: '#/components/schemas/GrammarResponseFormat'
discriminator:
propertyName: type
mapping:
json_schema: '#/components/schemas/JsonSchemaResponseFormat'
grammar: '#/components/schemas/GrammarResponseFormat'
SamplingParams:
type: object
properties:
strategy:
$ref: '#/components/schemas/SamplingStrategy'
description: The sampling strategy.
max_tokens:
type: integer
default: 0
description: >-
The maximum number of tokens that can be generated in the completion.
The token count of your prompt plus max_tokens cannot exceed the model's
context length.
repetition_penalty:
type: number
default: 1.0
description: >-
Number between -2.0 and 2.0. Positive values penalize new tokens based
on whether they appear in the text so far, increasing the model's likelihood
to talk about new topics.
stop:
type: array
items:
type: string
description: >-
Up to 4 sequences where the API will stop generating further tokens. The
returned text will not contain the stop sequence.
additionalProperties: false
required:
- strategy
title: SamplingParams
description: Sampling parameters.
SamplingStrategy:
oneOf:
- $ref: '#/components/schemas/GreedySamplingStrategy'
- $ref: '#/components/schemas/TopPSamplingStrategy'
- $ref: '#/components/schemas/TopKSamplingStrategy'
discriminator:
propertyName: type
mapping:
greedy: '#/components/schemas/GreedySamplingStrategy'
top_p: '#/components/schemas/TopPSamplingStrategy'
top_k: '#/components/schemas/TopKSamplingStrategy'
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.
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
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:
oneOf:
- type: string
- type: object
additionalProperties:
oneOf:
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
- type: array
items:
oneOf:
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
- type: object
additionalProperties:
oneOf:
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
arguments_json:
type: string
additionalProperties: false
required:
- call_id
- tool_name
- arguments
title: ToolCall
ToolConfig:
type: object
properties:
tool_choice:
oneOf:
- 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.
- type: string
default: auto
description: >-
(Optional) Whether tool use is automatic, required, or none. Can also
specify a tool name to use a specific tool. Defaults to ToolChoice.auto.
tool_prompt_format:
type: string
enum:
- json
- function_tag
- python_list
description: >-
(Optional) Instructs the model how to format tool calls. By default, Llama
Stack will attempt to use a format that is best adapted to the model.
- `ToolPromptFormat.json`: The tool calls are formatted as a JSON object.
- `ToolPromptFormat.function_tag`: The tool calls are enclosed in a <function=function_name>
tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python
syntax -- a list of function calls.
system_message_behavior:
type: string
enum:
- append
- replace
description: >-
(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`:
Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`:
Replaces the default system prompt with the provided system message. The
system message can include the string '{{function_definitions}}' to indicate
where the function definitions should be inserted.
default: append
additionalProperties: false
title: ToolConfig
description: Configuration for tool use.
ToolDefinition:
type: object
properties:
tool_name:
oneOf:
- type: string
enum:
- brave_search
- wolfram_alpha
- photogen
- code_interpreter
title: BuiltinTool
- type: string
description:
type: string
parameters:
type: object
additionalProperties:
$ref: '#/components/schemas/ToolParamDefinition'
additionalProperties: false
required:
- tool_name
title: ToolDefinition
ToolParamDefinition:
type: object
properties:
param_type:
type: string
description:
type: string
required:
type: boolean
default: true
default:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- param_type
title: ToolParamDefinition
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.
TopKSamplingStrategy:
type: object
properties:
type:
type: string
const: top_k
default: top_k
top_k:
type: integer
additionalProperties: false
required:
- type
- top_k
title: TopKSamplingStrategy
TopPSamplingStrategy:
type: object
properties:
type:
type: string
const: top_p
default: top_p
temperature:
type: number
top_p:
type: number
default: 0.95
additionalProperties: false
required:
- type
title: TopPSamplingStrategy
URL:
type: object
properties:
uri:
type: string
additionalProperties: false
required:
- uri
title: URL
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.
BatchChatCompletionRequest:
type: object
properties:
model_id:
type: string
description: >-
The identifier of the model to use. The model must be registered with
Llama Stack and available via the /models endpoint.
messages_batch:
type: array
items:
type: array
items:
$ref: '#/components/schemas/Message'
description: >-
The messages to generate completions for.
sampling_params:
$ref: '#/components/schemas/SamplingParams'
description: >-
(Optional) Parameters to control the sampling strategy.
tools:
type: array
items:
$ref: '#/components/schemas/ToolDefinition'
description: >-
(Optional) List of tool definitions available to the model.
tool_config:
$ref: '#/components/schemas/ToolConfig'
description: (Optional) Configuration for tool use.
response_format:
$ref: '#/components/schemas/ResponseFormat'
description: >-
(Optional) Grammar specification for guided (structured) decoding.
logprobs:
type: object
properties:
top_k:
type: integer
default: 0
description: >-
How many tokens (for each position) to return log probabilities for.
additionalProperties: false
description: >-
(Optional) If specified, log probabilities for each token position will
be returned.
additionalProperties: false
required:
- model_id
- messages_batch
title: BatchChatCompletionRequest
BatchChatCompletionResponse:
type: object
properties:
batch:
type: array
items:
$ref: '#/components/schemas/ChatCompletionResponse'
additionalProperties: false
required:
- batch
title: BatchChatCompletionResponse
ChatCompletionResponse:
type: object
properties:
metrics:
type: array
items:
$ref: '#/components/schemas/MetricInResponse'
completion_message:
$ref: '#/components/schemas/CompletionMessage'
description: The complete response message
logprobs:
type: array
items:
$ref: '#/components/schemas/TokenLogProbs'
description: >-
Optional log probabilities for generated tokens
additionalProperties: false
required:
- completion_message
title: ChatCompletionResponse
description: Response from a chat completion request.
MetricInResponse:
type: object
properties:
metric:
type: string
value:
oneOf:
- type: integer
- type: number
unit:
type: string
additionalProperties: false
required:
- metric
- value
title: MetricInResponse
TokenLogProbs:
type: object
properties:
logprobs_by_token:
type: object
additionalProperties:
type: number
description: >-
Dictionary mapping tokens to their log probabilities
additionalProperties: false
required:
- logprobs_by_token
title: TokenLogProbs
description: Log probabilities for generated tokens.
BatchCompletionRequest:
type: object
properties:
model_id:
type: string
description: >-
The identifier of the model to use. The model must be registered with
Llama Stack and available via the /models endpoint.
content_batch:
type: array
items:
$ref: '#/components/schemas/InterleavedContent'
description: The content to generate completions for.
sampling_params:
$ref: '#/components/schemas/SamplingParams'
description: >-
(Optional) Parameters to control the sampling strategy.
response_format:
$ref: '#/components/schemas/ResponseFormat'
description: >-
(Optional) Grammar specification for guided (structured) decoding.
logprobs:
type: object
properties:
top_k:
type: integer
default: 0
description: >-
How many tokens (for each position) to return log probabilities for.
additionalProperties: false
description: >-
(Optional) If specified, log probabilities for each token position will
be returned.
additionalProperties: false
required:
- model_id
- content_batch
title: BatchCompletionRequest
BatchCompletionResponse:
type: object
properties:
batch:
type: array
items:
$ref: '#/components/schemas/CompletionResponse'
additionalProperties: false
required:
- batch
title: BatchCompletionResponse
CompletionResponse:
type: object
properties:
metrics:
type: array
items:
$ref: '#/components/schemas/MetricInResponse'
content:
type: string
description: The generated completion text
stop_reason:
type: string
enum:
- end_of_turn
- end_of_message
- out_of_tokens
description: Reason why generation stopped
logprobs:
type: array
items:
$ref: '#/components/schemas/TokenLogProbs'
description: >-
Optional log probabilities for generated tokens
additionalProperties: false
required:
- content
- stop_reason
title: CompletionResponse
description: Response from a completion request.
CancelTrainingJobRequest:
type: object
properties:
job_uuid:
type: string
description: The UUID of the job to cancel.
additionalProperties: false
required:
- job_uuid
title: CancelTrainingJobRequest
ChatCompletionRequest:
type: object
properties:
model_id:
type: string
description: >-
The identifier of the model to use. The model must be registered with
Llama Stack and available via the /models endpoint.
messages:
type: array
items:
$ref: '#/components/schemas/Message'
description: List of messages in the conversation.
sampling_params:
$ref: '#/components/schemas/SamplingParams'
description: >-
Parameters to control the sampling strategy.
tools:
type: array
items:
$ref: '#/components/schemas/ToolDefinition'
description: >-
(Optional) List of tool definitions available to the model.
tool_choice:
type: string
enum:
- auto
- required
- none
description: >-
(Optional) Whether tool use is required or automatic. Defaults to ToolChoice.auto.
.. deprecated:: Use tool_config instead.
tool_prompt_format:
type: string
enum:
- json
- function_tag
- python_list
description: >-
(Optional) Instructs the model how to format tool calls. By default, Llama
Stack will attempt to use a format that is best adapted to the model.
- `ToolPromptFormat.json`: The tool calls are formatted as a JSON object.
- `ToolPromptFormat.function_tag`: The tool calls are enclosed in a <function=function_name>
tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python
syntax -- a list of function calls. .. deprecated:: Use tool_config instead.
response_format:
$ref: '#/components/schemas/ResponseFormat'
description: >-
(Optional) Grammar specification for guided (structured) decoding. There
are two options: - `ResponseFormat.json_schema`: The grammar is a JSON
schema. Most providers support this format. - `ResponseFormat.grammar`:
The grammar is a BNF grammar. This format is more flexible, but not all
providers support it.
stream:
type: boolean
description: >-
(Optional) If True, generate an SSE event stream of the response. Defaults
to False.
logprobs:
type: object
properties:
top_k:
type: integer
default: 0
description: >-
How many tokens (for each position) to return log probabilities for.
additionalProperties: false
description: >-
(Optional) If specified, log probabilities for each token position will
be returned.
tool_config:
$ref: '#/components/schemas/ToolConfig'
description: (Optional) Configuration for tool use.
additionalProperties: false
required:
- model_id
- messages
title: ChatCompletionRequest
ChatCompletionResponseEvent:
type: object
properties:
event_type:
type: string
enum:
- start
- complete
- progress
description: Type of the event
delta:
$ref: '#/components/schemas/ContentDelta'
description: >-
Content generated since last event. This can be one or more tokens, or
a tool call.
logprobs:
type: array
items:
$ref: '#/components/schemas/TokenLogProbs'
description: >-
Optional log probabilities for generated tokens
stop_reason:
type: string
enum:
- end_of_turn
- end_of_message
- out_of_tokens
description: >-
Optional reason why generation stopped, if complete
additionalProperties: false
required:
- event_type
- delta
title: ChatCompletionResponseEvent
description: >-
An event during chat completion generation.
ChatCompletionResponseStreamChunk:
type: object
properties:
metrics:
type: array
items:
$ref: '#/components/schemas/MetricInResponse'
event:
$ref: '#/components/schemas/ChatCompletionResponseEvent'
description: The event containing the new content
additionalProperties: false
required:
- event
title: ChatCompletionResponseStreamChunk
description: >-
A chunk of a streamed chat completion response.
ContentDelta:
oneOf:
- $ref: '#/components/schemas/TextDelta'
- $ref: '#/components/schemas/ImageDelta'
- $ref: '#/components/schemas/ToolCallDelta'
discriminator:
propertyName: type
mapping:
text: '#/components/schemas/TextDelta'
image: '#/components/schemas/ImageDelta'
tool_call: '#/components/schemas/ToolCallDelta'
ImageDelta:
type: object
properties:
type:
type: string
const: image
default: image
image:
type: string
contentEncoding: base64
additionalProperties: false
required:
- type
- image
title: ImageDelta
TextDelta:
type: object
properties:
type:
type: string
const: text
default: text
text:
type: string
additionalProperties: false
required:
- type
- text
title: TextDelta
ToolCallDelta:
type: object
properties:
type:
type: string
const: tool_call
default: tool_call
tool_call:
oneOf:
- type: string
- $ref: '#/components/schemas/ToolCall'
parse_status:
type: string
enum:
- started
- in_progress
- failed
- succeeded
title: ToolCallParseStatus
additionalProperties: false
required:
- type
- tool_call
- parse_status
title: ToolCallDelta
CompletionRequest:
type: object
properties:
model_id:
type: string
description: >-
The identifier of the model to use. The model must be registered with
Llama Stack and available via the /models endpoint.
content:
$ref: '#/components/schemas/InterleavedContent'
description: >-
The content to generate a completion for.
sampling_params:
$ref: '#/components/schemas/SamplingParams'
description: >-
(Optional) Parameters to control the sampling strategy.
response_format:
$ref: '#/components/schemas/ResponseFormat'
description: >-
(Optional) Grammar specification for guided (structured) decoding.
stream:
type: boolean
description: >-
(Optional) If True, generate an SSE event stream of the response. Defaults
to False.
logprobs:
type: object
properties:
top_k:
type: integer
default: 0
description: >-
How many tokens (for each position) to return log probabilities for.
additionalProperties: false
description: >-
(Optional) If specified, log probabilities for each token position will
be returned.
additionalProperties: false
required:
- model_id
- content
title: CompletionRequest
CompletionResponseStreamChunk:
type: object
properties:
metrics:
type: array
items:
$ref: '#/components/schemas/MetricInResponse'
delta:
type: string
description: >-
New content generated since last chunk. This can be one or more tokens.
stop_reason:
type: string
enum:
- end_of_turn
- end_of_message
- out_of_tokens
description: >-
Optional reason why generation stopped, if complete
logprobs:
type: array
items:
$ref: '#/components/schemas/TokenLogProbs'
description: >-
Optional log probabilities for generated tokens
additionalProperties: false
required:
- delta
title: CompletionResponseStreamChunk
description: >-
A chunk of a streamed completion response.
AgentConfig:
type: object
properties:
sampling_params:
$ref: '#/components/schemas/SamplingParams'
input_shields:
type: array
items:
type: string
output_shields:
type: array
items:
type: string
toolgroups:
type: array
items:
$ref: '#/components/schemas/AgentTool'
client_tools:
type: array
items:
$ref: '#/components/schemas/ToolDef'
tool_choice:
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.
deprecated: true
tool_prompt_format:
type: string
enum:
- json
- function_tag
- python_list
title: ToolPromptFormat
description: >-
Prompt format for calling custom / zero shot tools.
deprecated: true
tool_config:
$ref: '#/components/schemas/ToolConfig'
max_infer_iters:
type: integer
default: 10
model:
type: string
description: >-
The model identifier to use for the agent
instructions:
type: string
description: The system instructions for the agent
name:
type: string
description: >-
Optional name for the agent, used in telemetry and identification
enable_session_persistence:
type: boolean
default: false
description: >-
Optional flag indicating whether session data has to be persisted
response_format:
$ref: '#/components/schemas/ResponseFormat'
description: Optional response format configuration
additionalProperties: false
required:
- model
- instructions
title: AgentConfig
description: Configuration for an agent.
AgentTool:
oneOf:
- type: string
- type: object
properties:
name:
type: string
args:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- name
- args
title: AgentToolGroupWithArgs
ToolDef:
type: object
properties:
name:
type: string
description:
type: string
parameters:
type: array
items:
$ref: '#/components/schemas/ToolParameter'
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- name
title: ToolDef
ToolParameter:
type: object
properties:
name:
type: string
parameter_type:
type: string
description:
type: string
required:
type: boolean
default: true
default:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- name
- parameter_type
- description
- required
title: ToolParameter
CreateAgentRequest:
type: object
properties:
agent_config:
$ref: '#/components/schemas/AgentConfig'
description: The configuration for the agent.
additionalProperties: false
required:
- agent_config
title: CreateAgentRequest
AgentCreateResponse:
type: object
properties:
agent_id:
type: string
additionalProperties: false
required:
- agent_id
title: AgentCreateResponse
CreateAgentSessionRequest:
type: object
properties:
session_name:
type: string
description: The name of the session to create.
additionalProperties: false
required:
- session_name
title: CreateAgentSessionRequest
AgentSessionCreateResponse:
type: object
properties:
session_id:
type: string
additionalProperties: false
required:
- session_id
title: AgentSessionCreateResponse
CreateAgentTurnRequest:
type: object
properties:
messages:
type: array
items:
oneOf:
- $ref: '#/components/schemas/UserMessage'
- $ref: '#/components/schemas/ToolResponseMessage'
description: List of messages to start the turn with.
stream:
type: boolean
description: >-
(Optional) If True, generate an SSE event stream of the response. Defaults
to False.
documents:
type: array
items:
type: object
properties:
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.
additionalProperties: false
required:
- content
- mime_type
title: Document
description: A document to be used by an agent.
description: >-
(Optional) List of documents to create the turn with.
toolgroups:
type: array
items:
$ref: '#/components/schemas/AgentTool'
description: >-
(Optional) List of toolgroups to create the turn with, will be used in
addition to the agent's config toolgroups for the request.
tool_config:
$ref: '#/components/schemas/ToolConfig'
description: >-
(Optional) The tool configuration to create the turn with, will be used
to override the agent's tool_config.
additionalProperties: false
required:
- messages
title: CreateAgentTurnRequest
InferenceStep:
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: inference
default: inference
model_response:
$ref: '#/components/schemas/CompletionMessage'
description: The response from the LLM.
additionalProperties: false
required:
- turn_id
- step_id
- step_type
- model_response
title: InferenceStep
description: An inference step in an agent turn.
MemoryRetrievalStep:
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: memory_retrieval
default: memory_retrieval
vector_db_ids:
type: string
description: >-
The IDs of the vector databases to retrieve context from.
inserted_context:
$ref: '#/components/schemas/InterleavedContent'
description: >-
The context retrieved from the vector databases.
additionalProperties: false
required:
- turn_id
- step_id
- step_type
- vector_db_ids
- inserted_context
title: MemoryRetrievalStep
description: >-
A memory retrieval step in an agent turn.
SafetyViolation:
type: object
properties:
violation_level:
$ref: '#/components/schemas/ViolationLevel'
user_message:
type: string
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- violation_level
- metadata
title: SafetyViolation
ShieldCallStep:
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.
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
tool_name:
oneOf:
- type: string
enum:
- brave_search
- wolfram_alpha
- photogen
- code_interpreter
title: BuiltinTool
- type: string
content:
$ref: '#/components/schemas/InterleavedContent'
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- call_id
- tool_name
- content
title: ToolResponse
Turn:
type: object
properties:
turn_id:
type: string
session_id:
type: string
input_messages:
type: array
items:
oneOf:
- $ref: '#/components/schemas/UserMessage'
- $ref: '#/components/schemas/ToolResponseMessage'
steps:
type: array
items:
oneOf:
- $ref: '#/components/schemas/InferenceStep'
- $ref: '#/components/schemas/ToolExecutionStep'
- $ref: '#/components/schemas/ShieldCallStep'
- $ref: '#/components/schemas/MemoryRetrievalStep'
discriminator:
propertyName: step_type
mapping:
inference: '#/components/schemas/InferenceStep'
tool_execution: '#/components/schemas/ToolExecutionStep'
shield_call: '#/components/schemas/ShieldCallStep'
memory_retrieval: '#/components/schemas/MemoryRetrievalStep'
output_message:
$ref: '#/components/schemas/CompletionMessage'
output_attachments:
type: array
items:
type: object
properties:
content:
oneOf:
- type: string
- $ref: '#/components/schemas/InterleavedContentItem'
- type: array
items:
$ref: '#/components/schemas/InterleavedContentItem'
- $ref: '#/components/schemas/URL'
description: The content of the attachment.
mime_type:
type: string
description: The MIME type of the attachment.
additionalProperties: false
required:
- content
- mime_type
title: Attachment
description: An attachment to an agent turn.
started_at:
type: string
format: date-time
completed_at:
type: string
format: date-time
additionalProperties: false
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.
ViolationLevel:
type: string
enum:
- info
- warn
- error
title: ViolationLevel
AgentTurnResponseEvent:
type: object
properties:
payload:
$ref: '#/components/schemas/AgentTurnResponseEventPayload'
additionalProperties: false
required:
- payload
title: AgentTurnResponseEvent
AgentTurnResponseEventPayload:
oneOf:
- $ref: '#/components/schemas/AgentTurnResponseStepStartPayload'
- $ref: '#/components/schemas/AgentTurnResponseStepProgressPayload'
- $ref: '#/components/schemas/AgentTurnResponseStepCompletePayload'
- $ref: '#/components/schemas/AgentTurnResponseTurnStartPayload'
- $ref: '#/components/schemas/AgentTurnResponseTurnCompletePayload'
- $ref: '#/components/schemas/AgentTurnResponseTurnAwaitingInputPayload'
discriminator:
propertyName: event_type
mapping:
step_start: '#/components/schemas/AgentTurnResponseStepStartPayload'
step_progress: '#/components/schemas/AgentTurnResponseStepProgressPayload'
step_complete: '#/components/schemas/AgentTurnResponseStepCompletePayload'
turn_start: '#/components/schemas/AgentTurnResponseTurnStartPayload'
turn_complete: '#/components/schemas/AgentTurnResponseTurnCompletePayload'
turn_awaiting_input: '#/components/schemas/AgentTurnResponseTurnAwaitingInputPayload'
AgentTurnResponseStepCompletePayload:
type: object
properties:
event_type:
type: string
enum:
- step_start
- step_complete
- step_progress
- turn_start
- turn_complete
- turn_awaiting_input
title: AgentTurnResponseEventType
const: step_complete
default: step_complete
step_type:
type: string
enum:
- inference
- tool_execution
- shield_call
- memory_retrieval
title: StepType
description: Type of the step in an agent turn.
step_id:
type: string
step_details:
oneOf:
- $ref: '#/components/schemas/InferenceStep'
- $ref: '#/components/schemas/ToolExecutionStep'
- $ref: '#/components/schemas/ShieldCallStep'
- $ref: '#/components/schemas/MemoryRetrievalStep'
discriminator:
propertyName: step_type
mapping:
inference: '#/components/schemas/InferenceStep'
tool_execution: '#/components/schemas/ToolExecutionStep'
shield_call: '#/components/schemas/ShieldCallStep'
memory_retrieval: '#/components/schemas/MemoryRetrievalStep'
additionalProperties: false
required:
- event_type
- step_type
- step_id
- step_details
title: AgentTurnResponseStepCompletePayload
AgentTurnResponseStepProgressPayload:
type: object
properties:
event_type:
type: string
enum:
- step_start
- step_complete
- step_progress
- turn_start
- turn_complete
- turn_awaiting_input
title: AgentTurnResponseEventType
const: step_progress
default: step_progress
step_type:
type: string
enum:
- inference
- tool_execution
- shield_call
- memory_retrieval
title: StepType
description: Type of the step in an agent turn.
step_id:
type: string
delta:
$ref: '#/components/schemas/ContentDelta'
additionalProperties: false
required:
- event_type
- step_type
- step_id
- delta
title: AgentTurnResponseStepProgressPayload
AgentTurnResponseStepStartPayload:
type: object
properties:
event_type:
type: string
enum:
- step_start
- step_complete
- step_progress
- turn_start
- turn_complete
- turn_awaiting_input
title: AgentTurnResponseEventType
const: step_start
default: step_start
step_type:
type: string
enum:
- inference
- tool_execution
- shield_call
- memory_retrieval
title: StepType
description: Type of the step in an agent turn.
step_id:
type: string
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- event_type
- step_type
- step_id
title: AgentTurnResponseStepStartPayload
AgentTurnResponseStreamChunk:
type: object
properties:
event:
$ref: '#/components/schemas/AgentTurnResponseEvent'
additionalProperties: false
required:
- event
title: AgentTurnResponseStreamChunk
description: streamed agent turn completion response.
"AgentTurnResponseTurnAwaitingInputPayload":
type: object
properties:
event_type:
type: string
enum:
- step_start
- step_complete
- step_progress
- turn_start
- turn_complete
- turn_awaiting_input
title: AgentTurnResponseEventType
const: turn_awaiting_input
default: turn_awaiting_input
turn:
$ref: '#/components/schemas/Turn'
additionalProperties: false
required:
- event_type
- turn
title: >-
AgentTurnResponseTurnAwaitingInputPayload
AgentTurnResponseTurnCompletePayload:
type: object
properties:
event_type:
type: string
enum:
- step_start
- step_complete
- step_progress
- turn_start
- turn_complete
- turn_awaiting_input
title: AgentTurnResponseEventType
const: turn_complete
default: turn_complete
turn:
$ref: '#/components/schemas/Turn'
additionalProperties: false
required:
- event_type
- turn
title: AgentTurnResponseTurnCompletePayload
AgentTurnResponseTurnStartPayload:
type: object
properties:
event_type:
type: string
enum:
- step_start
- step_complete
- step_progress
- turn_start
- turn_complete
- turn_awaiting_input
title: AgentTurnResponseEventType
const: turn_start
default: turn_start
turn_id:
type: string
additionalProperties: false
required:
- event_type
- turn_id
title: AgentTurnResponseTurnStartPayload
OpenAIResponseInput:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
- $ref: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
- $ref: '#/components/schemas/OpenAIResponseInputFunctionToolCallOutput'
- $ref: '#/components/schemas/OpenAIResponseMessage'
"OpenAIResponseInputFunctionToolCallOutput":
type: object
properties:
call_id:
type: string
output:
type: string
type:
type: string
const: function_call_output
default: function_call_output
id:
type: string
status:
type: string
additionalProperties: false
required:
- call_id
- output
- type
title: >-
OpenAIResponseInputFunctionToolCallOutput
description: >-
This represents the output of a function call that gets passed back to the
model.
OpenAIResponseInputMessageContent:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentText'
- $ref: '#/components/schemas/OpenAIResponseInputMessageContentImage'
discriminator:
propertyName: type
mapping:
input_text: '#/components/schemas/OpenAIResponseInputMessageContentText'
input_image: '#/components/schemas/OpenAIResponseInputMessageContentImage'
OpenAIResponseInputMessageContentImage:
type: object
properties:
detail:
oneOf:
- type: string
const: low
- type: string
const: high
- type: string
const: auto
default: auto
type:
type: string
const: input_image
default: input_image
image_url:
type: string
additionalProperties: false
required:
- detail
- type
title: OpenAIResponseInputMessageContentImage
OpenAIResponseInputMessageContentText:
type: object
properties:
text:
type: string
type:
type: string
const: input_text
default: input_text
additionalProperties: false
required:
- text
- type
title: OpenAIResponseInputMessageContentText
OpenAIResponseInputTool:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseInputToolWebSearch'
- $ref: '#/components/schemas/OpenAIResponseInputToolFileSearch'
- $ref: '#/components/schemas/OpenAIResponseInputToolFunction'
- $ref: '#/components/schemas/OpenAIResponseInputToolMCP'
discriminator:
propertyName: type
mapping:
web_search: '#/components/schemas/OpenAIResponseInputToolWebSearch'
file_search: '#/components/schemas/OpenAIResponseInputToolFileSearch'
function: '#/components/schemas/OpenAIResponseInputToolFunction'
mcp: '#/components/schemas/OpenAIResponseInputToolMCP'
OpenAIResponseInputToolFileSearch:
type: object
properties:
type:
type: string
const: file_search
default: file_search
vector_store_ids:
type: array
items:
type: string
filters:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
max_num_results:
type: integer
default: 10
ranking_options:
type: object
properties:
ranker:
type: string
score_threshold:
type: number
default: 0.0
additionalProperties: false
title: SearchRankingOptions
additionalProperties: false
required:
- type
- vector_store_ids
title: OpenAIResponseInputToolFileSearch
OpenAIResponseInputToolFunction:
type: object
properties:
type:
type: string
const: function
default: function
name:
type: string
description:
type: string
parameters:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
strict:
type: boolean
additionalProperties: false
required:
- type
- name
title: OpenAIResponseInputToolFunction
OpenAIResponseInputToolMCP:
type: object
properties:
type:
type: string
const: mcp
default: mcp
server_label:
type: string
server_url:
type: string
headers:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
require_approval:
oneOf:
- type: string
const: always
- type: string
const: never
- type: object
properties:
always:
type: array
items:
type: string
never:
type: array
items:
type: string
additionalProperties: false
title: ApprovalFilter
default: never
allowed_tools:
oneOf:
- type: array
items:
type: string
- type: object
properties:
tool_names:
type: array
items:
type: string
additionalProperties: false
title: AllowedToolsFilter
additionalProperties: false
required:
- type
- server_label
- server_url
- require_approval
title: OpenAIResponseInputToolMCP
OpenAIResponseInputToolWebSearch:
type: object
properties:
type:
oneOf:
- type: string
const: web_search
- type: string
const: web_search_preview_2025_03_11
default: web_search
search_context_size:
type: string
default: medium
additionalProperties: false
required:
- type
title: OpenAIResponseInputToolWebSearch
OpenAIResponseMessage:
type: object
properties:
content:
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIResponseInputMessageContent'
- type: array
items:
$ref: '#/components/schemas/OpenAIResponseOutputMessageContent'
role:
oneOf:
- type: string
const: system
- type: string
const: developer
- type: string
const: user
- type: string
const: assistant
type:
type: string
const: message
default: message
id:
type: string
status:
type: string
additionalProperties: false
required:
- content
- role
- type
title: 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.
OpenAIResponseOutputMessageContent:
type: object
properties:
text:
type: string
type:
type: string
const: output_text
default: output_text
additionalProperties: false
required:
- text
- type
title: >-
OpenAIResponseOutputMessageContentOutputText
"OpenAIResponseOutputMessageFileSearchToolCall":
type: object
properties:
id:
type: string
queries:
type: array
items:
type: string
status:
type: string
type:
type: string
const: file_search_call
default: file_search_call
results:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- id
- queries
- status
- type
title: >-
OpenAIResponseOutputMessageFileSearchToolCall
"OpenAIResponseOutputMessageFunctionToolCall":
type: object
properties:
call_id:
type: string
name:
type: string
arguments:
type: string
type:
type: string
const: function_call
default: function_call
id:
type: string
status:
type: string
additionalProperties: false
required:
- call_id
- name
- arguments
- type
title: >-
OpenAIResponseOutputMessageFunctionToolCall
"OpenAIResponseOutputMessageWebSearchToolCall":
type: object
properties:
id:
type: string
status:
type: string
type:
type: string
const: web_search_call
default: web_search_call
additionalProperties: false
required:
- id
- status
- type
title: >-
OpenAIResponseOutputMessageWebSearchToolCall
OpenAIResponseText:
type: object
properties:
format:
type: object
properties:
type:
oneOf:
- type: string
const: text
- type: string
const: json_schema
- type: string
const: json_object
description: >-
Must be "text", "json_schema", or "json_object" to identify the format
type
name:
type: string
description: >-
The name of the response format. Only used for json_schema.
schema:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
The JSON schema the response should conform to. In a Python SDK, this
is often a `pydantic` model. Only used for json_schema.
description:
type: string
description: >-
(Optional) A description of the response format. Only used for json_schema.
strict:
type: boolean
description: >-
(Optional) Whether to strictly enforce the JSON schema. If true, the
response must match the schema exactly. Only used for json_schema.
additionalProperties: false
required:
- type
title: OpenAIResponseTextFormat
description: >-
Configuration for Responses API text format.
additionalProperties: false
title: OpenAIResponseText
CreateOpenaiResponseRequest:
type: object
properties:
input:
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIResponseInput'
description: Input message(s) to create the response.
model:
type: string
description: The underlying LLM used for completions.
instructions:
type: string
previous_response_id:
type: string
description: >-
(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.
store:
type: boolean
stream:
type: boolean
temperature:
type: number
text:
$ref: '#/components/schemas/OpenAIResponseText'
tools:
type: array
items:
$ref: '#/components/schemas/OpenAIResponseInputTool'
max_infer_iters:
type: integer
additionalProperties: false
required:
- input
- model
title: CreateOpenaiResponseRequest
OpenAIResponseError:
type: object
properties:
code:
type: string
message:
type: string
additionalProperties: false
required:
- code
- message
title: OpenAIResponseError
OpenAIResponseObject:
type: object
properties:
created_at:
type: integer
error:
$ref: '#/components/schemas/OpenAIResponseError'
id:
type: string
model:
type: string
object:
type: string
const: response
default: response
output:
type: array
items:
$ref: '#/components/schemas/OpenAIResponseOutput'
parallel_tool_calls:
type: boolean
default: false
previous_response_id:
type: string
status:
type: string
temperature:
type: number
text:
$ref: '#/components/schemas/OpenAIResponseText'
top_p:
type: number
truncation:
type: string
user:
type: string
additionalProperties: false
required:
- created_at
- id
- model
- object
- output
- parallel_tool_calls
- status
- text
title: OpenAIResponseObject
OpenAIResponseOutput:
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'
discriminator:
propertyName: type
mapping:
message: '#/components/schemas/OpenAIResponseMessage'
web_search_call: '#/components/schemas/OpenAIResponseOutputMessageWebSearchToolCall'
file_search_call: '#/components/schemas/OpenAIResponseOutputMessageFileSearchToolCall'
function_call: '#/components/schemas/OpenAIResponseOutputMessageFunctionToolCall'
mcp_call: '#/components/schemas/OpenAIResponseOutputMessageMCPCall'
mcp_list_tools: '#/components/schemas/OpenAIResponseOutputMessageMCPListTools'
OpenAIResponseOutputMessageMCPCall:
type: object
properties:
id:
type: string
type:
type: string
const: mcp_call
default: mcp_call
arguments:
type: string
name:
type: string
server_label:
type: string
error:
type: string
output:
type: string
additionalProperties: false
required:
- id
- type
- arguments
- name
- server_label
title: OpenAIResponseOutputMessageMCPCall
OpenAIResponseOutputMessageMCPListTools:
type: object
properties:
id:
type: string
type:
type: string
const: mcp_list_tools
default: mcp_list_tools
server_label:
type: string
tools:
type: array
items:
type: object
properties:
input_schema:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
name:
type: string
description:
type: string
additionalProperties: false
required:
- input_schema
- name
title: MCPListToolsTool
additionalProperties: false
required:
- id
- type
- server_label
- tools
title: OpenAIResponseOutputMessageMCPListTools
OpenAIResponseObjectStream:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseCreated'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputItemAdded'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputItemDone'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputTextDelta'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputTextDone'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseFunctionCallArgumentsDelta'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseFunctionCallArgumentsDone'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallInProgress'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallSearching'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallCompleted'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsInProgress'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsFailed'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsCompleted'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallArgumentsDelta'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallArgumentsDone'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallInProgress'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallFailed'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallCompleted'
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseCompleted'
discriminator:
propertyName: type
mapping:
response.created: '#/components/schemas/OpenAIResponseObjectStreamResponseCreated'
response.output_item.added: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputItemAdded'
response.output_item.done: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputItemDone'
response.output_text.delta: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputTextDelta'
response.output_text.done: '#/components/schemas/OpenAIResponseObjectStreamResponseOutputTextDone'
response.function_call_arguments.delta: '#/components/schemas/OpenAIResponseObjectStreamResponseFunctionCallArgumentsDelta'
response.function_call_arguments.done: '#/components/schemas/OpenAIResponseObjectStreamResponseFunctionCallArgumentsDone'
response.web_search_call.in_progress: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallInProgress'
response.web_search_call.searching: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallSearching'
response.web_search_call.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseWebSearchCallCompleted'
response.mcp_list_tools.in_progress: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsInProgress'
response.mcp_list_tools.failed: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsFailed'
response.mcp_list_tools.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpListToolsCompleted'
response.mcp_call.arguments.delta: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallArgumentsDelta'
response.mcp_call.arguments.done: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallArgumentsDone'
response.mcp_call.in_progress: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallInProgress'
response.mcp_call.failed: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallFailed'
response.mcp_call.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallCompleted'
response.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseCompleted'
"OpenAIResponseObjectStreamResponseCompleted":
type: object
properties:
response:
$ref: '#/components/schemas/OpenAIResponseObject'
type:
type: string
const: response.completed
default: response.completed
additionalProperties: false
required:
- response
- type
title: >-
OpenAIResponseObjectStreamResponseCompleted
"OpenAIResponseObjectStreamResponseCreated":
type: object
properties:
response:
$ref: '#/components/schemas/OpenAIResponseObject'
type:
type: string
const: response.created
default: response.created
additionalProperties: false
required:
- response
- type
title: >-
OpenAIResponseObjectStreamResponseCreated
"OpenAIResponseObjectStreamResponseFunctionCallArgumentsDelta":
type: object
properties:
delta:
type: string
item_id:
type: string
output_index:
type: integer
sequence_number:
type: integer
type:
type: string
const: response.function_call_arguments.delta
default: response.function_call_arguments.delta
additionalProperties: false
required:
- delta
- item_id
- output_index
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseFunctionCallArgumentsDelta
"OpenAIResponseObjectStreamResponseFunctionCallArgumentsDone":
type: object
properties:
arguments:
type: string
item_id:
type: string
output_index:
type: integer
sequence_number:
type: integer
type:
type: string
const: response.function_call_arguments.done
default: response.function_call_arguments.done
additionalProperties: false
required:
- arguments
- item_id
- output_index
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseFunctionCallArgumentsDone
"OpenAIResponseObjectStreamResponseMcpCallArgumentsDelta":
type: object
properties:
delta:
type: string
item_id:
type: string
output_index:
type: integer
sequence_number:
type: integer
type:
type: string
const: response.mcp_call.arguments.delta
default: response.mcp_call.arguments.delta
additionalProperties: false
required:
- delta
- item_id
- output_index
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseMcpCallArgumentsDelta
"OpenAIResponseObjectStreamResponseMcpCallArgumentsDone":
type: object
properties:
arguments:
type: string
item_id:
type: string
output_index:
type: integer
sequence_number:
type: integer
type:
type: string
const: response.mcp_call.arguments.done
default: response.mcp_call.arguments.done
additionalProperties: false
required:
- arguments
- item_id
- output_index
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseMcpCallArgumentsDone
"OpenAIResponseObjectStreamResponseMcpCallCompleted":
type: object
properties:
sequence_number:
type: integer
type:
type: string
const: response.mcp_call.completed
default: response.mcp_call.completed
additionalProperties: false
required:
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseMcpCallCompleted
"OpenAIResponseObjectStreamResponseMcpCallFailed":
type: object
properties:
sequence_number:
type: integer
type:
type: string
const: response.mcp_call.failed
default: response.mcp_call.failed
additionalProperties: false
required:
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseMcpCallFailed
"OpenAIResponseObjectStreamResponseMcpCallInProgress":
type: object
properties:
item_id:
type: string
output_index:
type: integer
sequence_number:
type: integer
type:
type: string
const: response.mcp_call.in_progress
default: response.mcp_call.in_progress
additionalProperties: false
required:
- item_id
- output_index
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseMcpCallInProgress
"OpenAIResponseObjectStreamResponseMcpListToolsCompleted":
type: object
properties:
sequence_number:
type: integer
type:
type: string
const: response.mcp_list_tools.completed
default: response.mcp_list_tools.completed
additionalProperties: false
required:
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseMcpListToolsCompleted
"OpenAIResponseObjectStreamResponseMcpListToolsFailed":
type: object
properties:
sequence_number:
type: integer
type:
type: string
const: response.mcp_list_tools.failed
default: response.mcp_list_tools.failed
additionalProperties: false
required:
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseMcpListToolsFailed
"OpenAIResponseObjectStreamResponseMcpListToolsInProgress":
type: object
properties:
sequence_number:
type: integer
type:
type: string
const: response.mcp_list_tools.in_progress
default: response.mcp_list_tools.in_progress
additionalProperties: false
required:
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseMcpListToolsInProgress
"OpenAIResponseObjectStreamResponseOutputItemAdded":
type: object
properties:
response_id:
type: string
item:
$ref: '#/components/schemas/OpenAIResponseOutput'
output_index:
type: integer
sequence_number:
type: integer
type:
type: string
const: response.output_item.added
default: response.output_item.added
additionalProperties: false
required:
- response_id
- item
- output_index
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseOutputItemAdded
"OpenAIResponseObjectStreamResponseOutputItemDone":
type: object
properties:
response_id:
type: string
item:
$ref: '#/components/schemas/OpenAIResponseOutput'
output_index:
type: integer
sequence_number:
type: integer
type:
type: string
const: response.output_item.done
default: response.output_item.done
additionalProperties: false
required:
- response_id
- item
- output_index
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseOutputItemDone
"OpenAIResponseObjectStreamResponseOutputTextDelta":
type: object
properties:
content_index:
type: integer
delta:
type: string
item_id:
type: string
output_index:
type: integer
sequence_number:
type: integer
type:
type: string
const: response.output_text.delta
default: response.output_text.delta
additionalProperties: false
required:
- content_index
- delta
- item_id
- output_index
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseOutputTextDelta
"OpenAIResponseObjectStreamResponseOutputTextDone":
type: object
properties:
content_index:
type: integer
text:
type: string
item_id:
type: string
output_index:
type: integer
sequence_number:
type: integer
type:
type: string
const: response.output_text.done
default: response.output_text.done
additionalProperties: false
required:
- content_index
- text
- item_id
- output_index
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseOutputTextDone
"OpenAIResponseObjectStreamResponseWebSearchCallCompleted":
type: object
properties:
item_id:
type: string
output_index:
type: integer
sequence_number:
type: integer
type:
type: string
const: response.web_search_call.completed
default: response.web_search_call.completed
additionalProperties: false
required:
- item_id
- output_index
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseWebSearchCallCompleted
"OpenAIResponseObjectStreamResponseWebSearchCallInProgress":
type: object
properties:
item_id:
type: string
output_index:
type: integer
sequence_number:
type: integer
type:
type: string
const: response.web_search_call.in_progress
default: response.web_search_call.in_progress
additionalProperties: false
required:
- item_id
- output_index
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseWebSearchCallInProgress
"OpenAIResponseObjectStreamResponseWebSearchCallSearching":
type: object
properties:
item_id:
type: string
output_index:
type: integer
sequence_number:
type: integer
type:
type: string
const: response.web_search_call.searching
default: response.web_search_call.searching
additionalProperties: false
required:
- item_id
- output_index
- sequence_number
- type
title: >-
OpenAIResponseObjectStreamResponseWebSearchCallSearching
EmbeddingsRequest:
type: object
properties:
model_id:
type: string
description: >-
The identifier of the model to use. The model must be an embedding model
registered with Llama Stack and available via the /models endpoint.
contents:
oneOf:
- type: array
items:
type: string
- type: array
items:
$ref: '#/components/schemas/InterleavedContentItem'
description: >-
List of contents to generate embeddings for. Each content can be a string
or an InterleavedContentItem (and hence can be multimodal). The behavior
depends on the model and provider. Some models may only support text.
text_truncation:
type: string
enum:
- none
- start
- end
description: >-
(Optional) Config for how to truncate text for embedding when text is
longer than the model's max sequence length.
output_dimension:
type: integer
description: >-
(Optional) Output dimensionality for the embeddings. Only supported by
Matryoshka models.
task_type:
type: string
enum:
- query
- document
description: >-
(Optional) How is the embedding being used? This is only supported by
asymmetric embedding models.
additionalProperties: false
required:
- model_id
- contents
title: EmbeddingsRequest
EmbeddingsResponse:
type: object
properties:
embeddings:
type: array
items:
type: array
items:
type: number
description: >-
List of embedding vectors, one per input content. Each embedding is a
list of floats. The dimensionality of the embedding is model-specific;
you can check model metadata using /models/{model_id}
additionalProperties: false
required:
- embeddings
title: EmbeddingsResponse
description: >-
Response containing generated embeddings.
AgentCandidate:
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.
AggregationFunctionType:
type: string
enum:
- average
- weighted_average
- median
- categorical_count
- accuracy
title: AggregationFunctionType
BasicScoringFnParams:
type: object
properties:
type:
$ref: '#/components/schemas/ScoringFnParamsType'
const: basic
default: basic
aggregation_functions:
type: array
items:
$ref: '#/components/schemas/AggregationFunctionType'
additionalProperties: false
required:
- type
- aggregation_functions
title: BasicScoringFnParams
BenchmarkConfig:
type: object
properties:
eval_candidate:
$ref: '#/components/schemas/EvalCandidate'
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.
EvalCandidate:
oneOf:
- $ref: '#/components/schemas/ModelCandidate'
- $ref: '#/components/schemas/AgentCandidate'
discriminator:
propertyName: type
mapping:
model: '#/components/schemas/ModelCandidate'
agent: '#/components/schemas/AgentCandidate'
LLMAsJudgeScoringFnParams:
type: object
properties:
type:
$ref: '#/components/schemas/ScoringFnParamsType'
const: llm_as_judge
default: llm_as_judge
judge_model:
type: string
prompt_template:
type: string
judge_score_regexes:
type: array
items:
type: string
aggregation_functions:
type: array
items:
$ref: '#/components/schemas/AggregationFunctionType'
additionalProperties: false
required:
- type
- judge_model
- judge_score_regexes
- aggregation_functions
title: LLMAsJudgeScoringFnParams
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.
RegexParserScoringFnParams:
type: object
properties:
type:
$ref: '#/components/schemas/ScoringFnParamsType'
const: regex_parser
default: regex_parser
parsing_regexes:
type: array
items:
type: string
aggregation_functions:
type: array
items:
$ref: '#/components/schemas/AggregationFunctionType'
additionalProperties: false
required:
- type
- parsing_regexes
- aggregation_functions
title: RegexParserScoringFnParams
ScoringFnParams:
oneOf:
- $ref: '#/components/schemas/LLMAsJudgeScoringFnParams'
- $ref: '#/components/schemas/RegexParserScoringFnParams'
- $ref: '#/components/schemas/BasicScoringFnParams'
discriminator:
propertyName: type
mapping:
llm_as_judge: '#/components/schemas/LLMAsJudgeScoringFnParams'
regex_parser: '#/components/schemas/RegexParserScoringFnParams'
basic: '#/components/schemas/BasicScoringFnParams'
ScoringFnParamsType:
type: string
enum:
- llm_as_judge
- regex_parser
- basic
title: ScoringFnParamsType
EvaluateRowsRequest:
type: object
properties:
input_rows:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: The rows to evaluate.
scoring_functions:
type: array
items:
type: string
description: >-
The scoring functions to use for the evaluation.
benchmark_config:
$ref: '#/components/schemas/BenchmarkConfig'
description: The configuration for the benchmark.
additionalProperties: false
required:
- input_rows
- scoring_functions
- benchmark_config
title: EvaluateRowsRequest
EvaluateResponse:
type: object
properties:
generations:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: The generations from the evaluation.
scores:
type: object
additionalProperties:
$ref: '#/components/schemas/ScoringResult'
description: The scores from the evaluation.
additionalProperties: false
required:
- generations
- scores
title: EvaluateResponse
description: The response from an evaluation.
ScoringResult:
type: object
properties:
score_rows:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
The scoring result for each row. Each row is a map of column name to value.
aggregated_results:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: Map of metric name to aggregated value
additionalProperties: false
required:
- score_rows
- aggregated_results
title: ScoringResult
description: A scoring result for a single row.
Agent:
type: object
properties:
agent_id:
type: string
agent_config:
$ref: '#/components/schemas/AgentConfig'
created_at:
type: string
format: date-time
additionalProperties: false
required:
- agent_id
- agent_config
- created_at
title: Agent
Session:
type: object
properties:
session_id:
type: string
session_name:
type: string
turns:
type: array
items:
$ref: '#/components/schemas/Turn'
started_at:
type: string
format: date-time
additionalProperties: false
required:
- session_id
- session_name
- turns
- started_at
title: Session
description: >-
A single session of an interaction with an Agentic System.
AgentStepResponse:
type: object
properties:
step:
oneOf:
- $ref: '#/components/schemas/InferenceStep'
- $ref: '#/components/schemas/ToolExecutionStep'
- $ref: '#/components/schemas/ShieldCallStep'
- $ref: '#/components/schemas/MemoryRetrievalStep'
discriminator:
propertyName: step_type
mapping:
inference: '#/components/schemas/InferenceStep'
tool_execution: '#/components/schemas/ToolExecutionStep'
shield_call: '#/components/schemas/ShieldCallStep'
memory_retrieval: '#/components/schemas/MemoryRetrievalStep'
additionalProperties: false
required:
- step
title: AgentStepResponse
Benchmark:
type: object
properties:
identifier:
type: string
provider_resource_id:
type: string
provider_id:
type: string
type:
type: string
enum:
- model
- shield
- vector_db
- dataset
- scoring_function
- benchmark
- tool
- tool_group
title: ResourceType
const: benchmark
default: benchmark
dataset_id:
type: string
scoring_functions:
type: array
items:
type: string
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- identifier
- provider_id
- type
- dataset_id
- scoring_functions
- metadata
title: Benchmark
OpenAIAssistantMessageParam:
type: object
properties:
role:
type: string
const: assistant
default: assistant
description: >-
Must be "assistant" to identify this as the model's response
content:
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
description: The content of the model's response
name:
type: string
description: >-
(Optional) The name of the assistant message participant.
tool_calls:
type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionToolCall'
description: >-
List of tool calls. Each tool call is an OpenAIChatCompletionToolCall
object.
additionalProperties: false
required:
- role
title: OpenAIAssistantMessageParam
description: >-
A message containing the model's (assistant) response in an OpenAI-compatible
chat completion request.
"OpenAIChatCompletionContentPartImageParam":
type: object
properties:
type:
type: string
const: image_url
default: image_url
image_url:
$ref: '#/components/schemas/OpenAIImageURL'
additionalProperties: false
required:
- type
- image_url
title: >-
OpenAIChatCompletionContentPartImageParam
OpenAIChatCompletionContentPartParam:
oneOf:
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
discriminator:
propertyName: type
mapping:
text: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
image_url: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
OpenAIChatCompletionContentPartTextParam:
type: object
properties:
type:
type: string
const: text
default: text
text:
type: string
additionalProperties: false
required:
- type
- text
title: OpenAIChatCompletionContentPartTextParam
OpenAIChatCompletionToolCall:
type: object
properties:
index:
type: integer
id:
type: string
type:
type: string
const: function
default: function
function:
$ref: '#/components/schemas/OpenAIChatCompletionToolCallFunction'
additionalProperties: false
required:
- type
title: OpenAIChatCompletionToolCall
OpenAIChatCompletionToolCallFunction:
type: object
properties:
name:
type: string
arguments:
type: string
additionalProperties: false
title: OpenAIChatCompletionToolCallFunction
OpenAIChoice:
type: object
properties:
message:
$ref: '#/components/schemas/OpenAIMessageParam'
description: The message from the model
finish_reason:
type: string
description: The reason the model stopped generating
index:
type: integer
description: The index of the choice
logprobs:
$ref: '#/components/schemas/OpenAIChoiceLogprobs'
description: >-
(Optional) The log probabilities for the tokens in the message
additionalProperties: false
required:
- message
- finish_reason
- index
title: OpenAIChoice
description: >-
A choice from an OpenAI-compatible chat completion response.
OpenAIChoiceLogprobs:
type: object
properties:
content:
type: array
items:
$ref: '#/components/schemas/OpenAITokenLogProb'
description: >-
(Optional) The log probabilities for the tokens in the message
refusal:
type: array
items:
$ref: '#/components/schemas/OpenAITokenLogProb'
description: >-
(Optional) The log probabilities for the tokens in the message
additionalProperties: false
title: OpenAIChoiceLogprobs
description: >-
The log probabilities for the tokens in the message from an OpenAI-compatible
chat completion response.
OpenAIDeveloperMessageParam:
type: object
properties:
role:
type: string
const: developer
default: developer
description: >-
Must be "developer" to identify this as a developer message
content:
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
description: The content of the developer message
name:
type: string
description: >-
(Optional) The name of the developer message participant.
additionalProperties: false
required:
- role
- content
title: OpenAIDeveloperMessageParam
description: >-
A message from the developer in an OpenAI-compatible chat completion request.
OpenAIImageURL:
type: object
properties:
url:
type: string
detail:
type: string
additionalProperties: false
required:
- url
title: OpenAIImageURL
OpenAIMessageParam:
oneOf:
- $ref: '#/components/schemas/OpenAIUserMessageParam'
- $ref: '#/components/schemas/OpenAISystemMessageParam'
- $ref: '#/components/schemas/OpenAIAssistantMessageParam'
- $ref: '#/components/schemas/OpenAIToolMessageParam'
- $ref: '#/components/schemas/OpenAIDeveloperMessageParam'
discriminator:
propertyName: role
mapping:
user: '#/components/schemas/OpenAIUserMessageParam'
system: '#/components/schemas/OpenAISystemMessageParam'
assistant: '#/components/schemas/OpenAIAssistantMessageParam'
tool: '#/components/schemas/OpenAIToolMessageParam'
developer: '#/components/schemas/OpenAIDeveloperMessageParam'
OpenAISystemMessageParam:
type: object
properties:
role:
type: string
const: system
default: system
description: >-
Must be "system" to identify this as a system message
content:
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
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).
name:
type: string
description: >-
(Optional) The name of the system message participant.
additionalProperties: false
required:
- role
- content
title: OpenAISystemMessageParam
description: >-
A system message providing instructions or context to the model.
OpenAITokenLogProb:
type: object
properties:
token:
type: string
bytes:
type: array
items:
type: integer
logprob:
type: number
top_logprobs:
type: array
items:
$ref: '#/components/schemas/OpenAITopLogProb'
additionalProperties: false
required:
- token
- logprob
- top_logprobs
title: OpenAITokenLogProb
description: >-
The log probability for a token from an OpenAI-compatible chat completion
response.
OpenAIToolMessageParam:
type: object
properties:
role:
type: string
const: tool
default: tool
description: >-
Must be "tool" to identify this as a tool response
tool_call_id:
type: string
description: >-
Unique identifier for the tool call this response is for
content:
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
description: The response content from the tool
additionalProperties: false
required:
- role
- tool_call_id
- content
title: OpenAIToolMessageParam
description: >-
A message representing the result of a tool invocation in an OpenAI-compatible
chat completion request.
OpenAITopLogProb:
type: object
properties:
token:
type: string
bytes:
type: array
items:
type: integer
logprob:
type: number
additionalProperties: false
required:
- token
- logprob
title: OpenAITopLogProb
description: >-
The top log probability for a token from an OpenAI-compatible chat completion
response.
OpenAIUserMessageParam:
type: object
properties:
role:
type: string
const: user
default: user
description: >-
Must be "user" to identify this as a user message
content:
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
description: >-
The content of the message, which can include text and other media
name:
type: string
description: >-
(Optional) The name of the user message participant.
additionalProperties: false
required:
- role
- content
title: OpenAIUserMessageParam
description: >-
A message from the user in an OpenAI-compatible chat completion request.
OpenAICompletionWithInputMessages:
type: object
properties:
id:
type: string
description: The ID of the chat completion
choices:
type: array
items:
$ref: '#/components/schemas/OpenAIChoice'
description: List of choices
object:
type: string
const: chat.completion
default: chat.completion
description: >-
The object type, which will be "chat.completion"
created:
type: integer
description: >-
The Unix timestamp in seconds when the chat completion was created
model:
type: string
description: >-
The model that was used to generate the chat completion
input_messages:
type: array
items:
$ref: '#/components/schemas/OpenAIMessageParam'
additionalProperties: false
required:
- id
- choices
- object
- created
- model
- input_messages
title: OpenAICompletionWithInputMessages
DataSource:
oneOf:
- $ref: '#/components/schemas/URIDataSource'
- $ref: '#/components/schemas/RowsDataSource'
discriminator:
propertyName: type
mapping:
uri: '#/components/schemas/URIDataSource'
rows: '#/components/schemas/RowsDataSource'
Dataset:
type: object
properties:
identifier:
type: string
provider_resource_id:
type: string
provider_id:
type: string
type:
type: string
enum:
- model
- shield
- vector_db
- dataset
- scoring_function
- benchmark
- tool
- tool_group
title: ResourceType
const: dataset
default: dataset
purpose:
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.
source:
$ref: '#/components/schemas/DataSource'
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- identifier
- provider_id
- type
- purpose
- source
- metadata
title: Dataset
RowsDataSource:
type: object
properties:
type:
type: string
const: rows
default: rows
rows:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
The dataset is stored in rows. E.g. - [ {"messages": [{"role": "user",
"content": "Hello, world!"}, {"role": "assistant", "content": "Hello,
world!"}]} ]
additionalProperties: false
required:
- type
- rows
title: RowsDataSource
description: A dataset stored in rows.
URIDataSource:
type: object
properties:
type:
type: string
const: uri
default: uri
uri:
type: string
description: >-
The dataset can be obtained from a URI. E.g. - "https://mywebsite.com/mydata.jsonl"
- "lsfs://mydata.jsonl" - "data:csv;base64,{base64_content}"
additionalProperties: false
required:
- type
- uri
title: URIDataSource
description: >-
A dataset that can be obtained from a URI.
Model:
type: object
properties:
identifier:
type: string
provider_resource_id:
type: string
provider_id:
type: string
type:
type: string
enum:
- model
- shield
- vector_db
- dataset
- scoring_function
- benchmark
- tool
- tool_group
title: ResourceType
const: model
default: model
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
model_type:
$ref: '#/components/schemas/ModelType'
default: llm
additionalProperties: false
required:
- identifier
- provider_id
- type
- metadata
- model_type
title: Model
ModelType:
type: string
enum:
- llm
- embedding
title: ModelType
AgentTurnInputType:
type: object
properties:
type:
type: string
const: agent_turn_input
default: agent_turn_input
additionalProperties: false
required:
- type
title: AgentTurnInputType
ArrayType:
type: object
properties:
type:
type: string
const: array
default: array
additionalProperties: false
required:
- type
title: ArrayType
BooleanType:
type: object
properties:
type:
type: string
const: boolean
default: boolean
additionalProperties: false
required:
- type
title: BooleanType
ChatCompletionInputType:
type: object
properties:
type:
type: string
const: chat_completion_input
default: chat_completion_input
additionalProperties: false
required:
- type
title: ChatCompletionInputType
CompletionInputType:
type: object
properties:
type:
type: string
const: completion_input
default: completion_input
additionalProperties: false
required:
- type
title: CompletionInputType
JsonType:
type: object
properties:
type:
type: string
const: json
default: json
additionalProperties: false
required:
- type
title: JsonType
NumberType:
type: object
properties:
type:
type: string
const: number
default: number
additionalProperties: false
required:
- type
title: NumberType
ObjectType:
type: object
properties:
type:
type: string
const: object
default: object
additionalProperties: false
required:
- type
title: ObjectType
ParamType:
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'
discriminator:
propertyName: type
mapping:
string: '#/components/schemas/StringType'
number: '#/components/schemas/NumberType'
boolean: '#/components/schemas/BooleanType'
array: '#/components/schemas/ArrayType'
object: '#/components/schemas/ObjectType'
json: '#/components/schemas/JsonType'
union: '#/components/schemas/UnionType'
chat_completion_input: '#/components/schemas/ChatCompletionInputType'
completion_input: '#/components/schemas/CompletionInputType'
agent_turn_input: '#/components/schemas/AgentTurnInputType'
ScoringFn:
type: object
properties:
identifier:
type: string
provider_resource_id:
type: string
provider_id:
type: string
type:
type: string
enum:
- model
- shield
- vector_db
- dataset
- scoring_function
- benchmark
- tool
- tool_group
title: ResourceType
const: scoring_function
default: scoring_function
description:
type: string
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
return_type:
$ref: '#/components/schemas/ParamType'
params:
$ref: '#/components/schemas/ScoringFnParams'
additionalProperties: false
required:
- identifier
- provider_id
- type
- metadata
- return_type
title: ScoringFn
StringType:
type: object
properties:
type:
type: string
const: string
default: string
additionalProperties: false
required:
- type
title: StringType
UnionType:
type: object
properties:
type:
type: string
const: union
default: union
additionalProperties: false
required:
- type
title: UnionType
Shield:
type: object
properties:
identifier:
type: string
provider_resource_id:
type: string
provider_id:
type: string
type:
type: string
enum:
- model
- shield
- vector_db
- dataset
- scoring_function
- benchmark
- tool
- tool_group
title: ResourceType
const: shield
default: shield
params:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- identifier
- provider_id
- type
title: Shield
description: >-
A safety shield resource that can be used to check content
Span:
type: object
properties:
span_id:
type: string
trace_id:
type: string
parent_span_id:
type: string
name:
type: string
start_time:
type: string
format: date-time
end_time:
type: string
format: date-time
attributes:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- span_id
- trace_id
- name
- start_time
title: Span
GetSpanTreeRequest:
type: object
properties:
attributes_to_return:
type: array
items:
type: string
description: The attributes to return in the tree.
max_depth:
type: integer
description: The maximum depth of the tree.
additionalProperties: false
title: GetSpanTreeRequest
SpanStatus:
type: string
enum:
- ok
- error
title: SpanStatus
SpanWithStatus:
type: object
properties:
span_id:
type: string
trace_id:
type: string
parent_span_id:
type: string
name:
type: string
start_time:
type: string
format: date-time
end_time:
type: string
format: date-time
attributes:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
status:
$ref: '#/components/schemas/SpanStatus'
additionalProperties: false
required:
- span_id
- trace_id
- name
- start_time
title: SpanWithStatus
QuerySpanTreeResponse:
type: object
properties:
data:
type: object
additionalProperties:
$ref: '#/components/schemas/SpanWithStatus'
additionalProperties: false
required:
- data
title: QuerySpanTreeResponse
Tool:
type: object
properties:
identifier:
type: string
provider_resource_id:
type: string
provider_id:
type: string
type:
type: string
enum:
- model
- shield
- vector_db
- dataset
- scoring_function
- benchmark
- tool
- tool_group
title: ResourceType
const: tool
default: tool
toolgroup_id:
type: string
description:
type: string
parameters:
type: array
items:
$ref: '#/components/schemas/ToolParameter'
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- identifier
- provider_id
- type
- toolgroup_id
- description
- parameters
title: Tool
ToolGroup:
type: object
properties:
identifier:
type: string
provider_resource_id:
type: string
provider_id:
type: string
type:
type: string
enum:
- model
- shield
- vector_db
- dataset
- scoring_function
- benchmark
- tool
- tool_group
title: ResourceType
const: tool_group
default: tool_group
mcp_endpoint:
$ref: '#/components/schemas/URL'
args:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- identifier
- provider_id
- type
title: ToolGroup
Trace:
type: object
properties:
trace_id:
type: string
root_span_id:
type: string
start_time:
type: string
format: date-time
end_time:
type: string
format: date-time
additionalProperties: false
required:
- trace_id
- root_span_id
- start_time
title: Trace
Checkpoint:
description: Checkpoint created during training runs
title: Checkpoint
PostTrainingJobArtifactsResponse:
type: object
properties:
job_uuid:
type: string
checkpoints:
type: array
items:
$ref: '#/components/schemas/Checkpoint'
additionalProperties: false
required:
- job_uuid
- checkpoints
title: PostTrainingJobArtifactsResponse
description: Artifacts of a finetuning job.
PostTrainingJobStatusResponse:
type: object
properties:
job_uuid:
type: string
status:
type: string
enum:
- completed
- in_progress
- failed
- scheduled
- cancelled
title: JobStatus
scheduled_at:
type: string
format: date-time
started_at:
type: string
format: date-time
completed_at:
type: string
format: date-time
resources_allocated:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
checkpoints:
type: array
items:
$ref: '#/components/schemas/Checkpoint'
additionalProperties: false
required:
- job_uuid
- status
- checkpoints
title: PostTrainingJobStatusResponse
description: Status of a finetuning job.
ListPostTrainingJobsResponse:
type: object
properties:
data:
type: array
items:
type: object
properties:
job_uuid:
type: string
additionalProperties: false
required:
- job_uuid
title: PostTrainingJob
additionalProperties: false
required:
- data
title: ListPostTrainingJobsResponse
VectorDB:
type: object
properties:
identifier:
type: string
provider_resource_id:
type: string
provider_id:
type: string
type:
type: string
enum:
- model
- shield
- vector_db
- dataset
- scoring_function
- benchmark
- tool
- tool_group
title: ResourceType
const: vector_db
default: vector_db
embedding_model:
type: string
embedding_dimension:
type: integer
additionalProperties: false
required:
- identifier
- provider_id
- type
- embedding_model
- embedding_dimension
title: VectorDB
HealthInfo:
type: object
properties:
status:
type: string
enum:
- OK
- Error
- Not Implemented
title: HealthStatus
additionalProperties: false
required:
- status
title: HealthInfo
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'
vector_db_id:
type: string
chunk_size_in_tokens:
type: integer
additionalProperties: false
required:
- documents
- vector_db_id
- chunk_size_in_tokens
title: InsertRequest
Chunk:
type: object
properties:
content:
$ref: '#/components/schemas/InterleavedContent'
description: >-
The content of the chunk, which can be interleaved text, images, or other
types.
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
Metadata associated with the chunk that will be used in the model context
during inference.
embedding:
type: array
items:
type: number
description: >-
Optional embedding for the chunk. If not provided, it will be computed
later.
stored_chunk_id:
type: string
description: >-
The chunk ID that is stored in the vector database. Used for backend functionality.
chunk_metadata:
$ref: '#/components/schemas/ChunkMetadata'
description: >-
Metadata for the chunk that will NOT be used in the context during inference.
The `chunk_metadata` is required backend functionality.
additionalProperties: false
required:
- content
- metadata
title: Chunk
description: >-
A chunk of content that can be inserted into a vector database.
ChunkMetadata:
type: object
properties:
chunk_id:
type: string
description: >-
The ID of the chunk. If not set, it will be generated based on the document
ID and content.
document_id:
type: string
description: >-
The ID of the document this chunk belongs to.
source:
type: string
description: >-
The source of the content, such as a URL, file path, or other identifier.
created_timestamp:
type: integer
description: >-
An optional timestamp indicating when the chunk was created.
updated_timestamp:
type: integer
description: >-
An optional timestamp indicating when the chunk was last updated.
chunk_window:
type: string
description: >-
The window of the chunk, which can be used to group related chunks together.
chunk_tokenizer:
type: string
description: >-
The tokenizer used to create the chunk. Default is Tiktoken.
chunk_embedding_model:
type: string
description: >-
The embedding model used to create the chunk's embedding.
chunk_embedding_dimension:
type: integer
description: >-
The dimension of the embedding vector for the chunk.
content_token_count:
type: integer
description: >-
The number of tokens in the content of the chunk.
metadata_token_count:
type: integer
description: >-
The number of tokens in the metadata of the chunk.
additionalProperties: false
title: ChunkMetadata
description: >-
`ChunkMetadata` is backend metadata for a `Chunk` that is used to store additional
information about the chunk that will not be used in the context during
inference, but is required for backend functionality. The `ChunkMetadata` is
set during chunk creation in `MemoryToolRuntimeImpl().insert()`and is not
expected to change after. Use `Chunk.metadata` for metadata that will
be used in the context during inference.
InsertChunksRequest:
type: object
properties:
vector_db_id:
type: string
description: >-
The identifier of the vector database to insert the chunks into.
chunks:
type: array
items:
$ref: '#/components/schemas/Chunk'
description: >-
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.
ttl_seconds:
type: integer
description: The time to live of the chunks.
additionalProperties: false
required:
- vector_db_id
- chunks
title: InsertChunksRequest
ProviderInfo:
type: object
properties:
api:
type: string
provider_id:
type: string
provider_type:
type: string
config:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
health:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- api
- provider_id
- provider_type
- config
- health
title: ProviderInfo
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
ToolInvocationResult:
type: object
properties:
content:
$ref: '#/components/schemas/InterleavedContent'
error_message:
type: string
error_code:
type: integer
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
title: ToolInvocationResult
PaginatedResponse:
type: object
properties:
data:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: The list of items for the current page
has_more:
type: boolean
description: >-
Whether there are more items available after this set
url:
type: string
description: The URL for accessing this list
additionalProperties: false
required:
- data
- has_more
title: PaginatedResponse
description: >-
A generic paginated response that follows a simple format.
Job:
type: object
properties:
job_id:
type: string
status:
type: string
enum:
- completed
- in_progress
- failed
- scheduled
- cancelled
title: JobStatus
additionalProperties: false
required:
- job_id
- status
title: Job
ListBenchmarksResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/Benchmark'
additionalProperties: false
required:
- data
title: ListBenchmarksResponse
Order:
type: string
enum:
- asc
- desc
title: Order
ListOpenAIChatCompletionResponse:
type: object
properties:
data:
type: array
items:
type: object
properties:
id:
type: string
description: The ID of the chat completion
choices:
type: array
items:
$ref: '#/components/schemas/OpenAIChoice'
description: List of choices
object:
type: string
const: chat.completion
default: chat.completion
description: >-
The object type, which will be "chat.completion"
created:
type: integer
description: >-
The Unix timestamp in seconds when the chat completion was created
model:
type: string
description: >-
The model that was used to generate the chat completion
input_messages:
type: array
items:
$ref: '#/components/schemas/OpenAIMessageParam'
additionalProperties: false
required:
- id
- choices
- object
- created
- model
- input_messages
title: OpenAICompletionWithInputMessages
has_more:
type: boolean
first_id:
type: string
last_id:
type: string
object:
type: string
const: list
default: list
additionalProperties: false
required:
- data
- has_more
- first_id
- last_id
- object
title: ListOpenAIChatCompletionResponse
ListDatasetsResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/Dataset'
additionalProperties: false
required:
- data
title: ListDatasetsResponse
ListModelsResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/Model'
additionalProperties: false
required:
- data
title: ListModelsResponse
ListOpenAIResponseInputItem:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/OpenAIResponseInput'
object:
type: string
const: list
default: list
additionalProperties: false
required:
- data
- object
title: ListOpenAIResponseInputItem
ListOpenAIResponseObject:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/OpenAIResponseObjectWithInput'
has_more:
type: boolean
first_id:
type: string
last_id:
type: string
object:
type: string
const: list
default: list
additionalProperties: false
required:
- data
- has_more
- first_id
- last_id
- object
title: ListOpenAIResponseObject
OpenAIResponseObjectWithInput:
type: object
properties:
created_at:
type: integer
error:
$ref: '#/components/schemas/OpenAIResponseError'
id:
type: string
model:
type: string
object:
type: string
const: response
default: response
output:
type: array
items:
$ref: '#/components/schemas/OpenAIResponseOutput'
parallel_tool_calls:
type: boolean
default: false
previous_response_id:
type: string
status:
type: string
temperature:
type: number
text:
$ref: '#/components/schemas/OpenAIResponseText'
top_p:
type: number
truncation:
type: string
user:
type: string
input:
type: array
items:
$ref: '#/components/schemas/OpenAIResponseInput'
additionalProperties: false
required:
- created_at
- id
- model
- object
- output
- parallel_tool_calls
- status
- text
- input
title: OpenAIResponseObjectWithInput
ListProvidersResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/ProviderInfo'
additionalProperties: false
required:
- data
title: ListProvidersResponse
RouteInfo:
type: object
properties:
route:
type: string
method:
type: string
provider_types:
type: array
items:
type: string
additionalProperties: false
required:
- route
- method
- provider_types
title: RouteInfo
ListRoutesResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/RouteInfo'
additionalProperties: false
required:
- data
title: ListRoutesResponse
ListToolDefsResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/ToolDef'
additionalProperties: false
required:
- data
title: ListToolDefsResponse
ListScoringFunctionsResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/ScoringFn'
additionalProperties: false
required:
- data
title: ListScoringFunctionsResponse
ListShieldsResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/Shield'
additionalProperties: false
required:
- data
title: ListShieldsResponse
ListToolGroupsResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/ToolGroup'
additionalProperties: false
required:
- data
title: ListToolGroupsResponse
ListToolsResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/Tool'
additionalProperties: false
required:
- data
title: ListToolsResponse
ListVectorDBsResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/VectorDB'
additionalProperties: false
required:
- data
title: ListVectorDBsResponse
Event:
oneOf:
- $ref: '#/components/schemas/UnstructuredLogEvent'
- $ref: '#/components/schemas/MetricEvent'
- $ref: '#/components/schemas/StructuredLogEvent'
discriminator:
propertyName: type
mapping:
unstructured_log: '#/components/schemas/UnstructuredLogEvent'
metric: '#/components/schemas/MetricEvent'
structured_log: '#/components/schemas/StructuredLogEvent'
EventType:
type: string
enum:
- unstructured_log
- structured_log
- metric
title: EventType
LogSeverity:
type: string
enum:
- verbose
- debug
- info
- warn
- error
- critical
title: LogSeverity
MetricEvent:
type: object
properties:
trace_id:
type: string
span_id:
type: string
timestamp:
type: string
format: date-time
attributes:
type: object
additionalProperties:
oneOf:
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
type:
$ref: '#/components/schemas/EventType'
const: metric
default: metric
metric:
type: string
value:
oneOf:
- type: integer
- type: number
unit:
type: string
additionalProperties: false
required:
- trace_id
- span_id
- timestamp
- type
- metric
- value
- unit
title: MetricEvent
SpanEndPayload:
type: object
properties:
type:
$ref: '#/components/schemas/StructuredLogType'
const: span_end
default: span_end
status:
$ref: '#/components/schemas/SpanStatus'
additionalProperties: false
required:
- type
- status
title: SpanEndPayload
SpanStartPayload:
type: object
properties:
type:
$ref: '#/components/schemas/StructuredLogType'
const: span_start
default: span_start
name:
type: string
parent_span_id:
type: string
additionalProperties: false
required:
- type
- name
title: SpanStartPayload
StructuredLogEvent:
type: object
properties:
trace_id:
type: string
span_id:
type: string
timestamp:
type: string
format: date-time
attributes:
type: object
additionalProperties:
oneOf:
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
type:
$ref: '#/components/schemas/EventType'
const: structured_log
default: structured_log
payload:
$ref: '#/components/schemas/StructuredLogPayload'
additionalProperties: false
required:
- trace_id
- span_id
- timestamp
- type
- payload
title: StructuredLogEvent
StructuredLogPayload:
oneOf:
- $ref: '#/components/schemas/SpanStartPayload'
- $ref: '#/components/schemas/SpanEndPayload'
discriminator:
propertyName: type
mapping:
span_start: '#/components/schemas/SpanStartPayload'
span_end: '#/components/schemas/SpanEndPayload'
StructuredLogType:
type: string
enum:
- span_start
- span_end
title: StructuredLogType
UnstructuredLogEvent:
type: object
properties:
trace_id:
type: string
span_id:
type: string
timestamp:
type: string
format: date-time
attributes:
type: object
additionalProperties:
oneOf:
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
type:
$ref: '#/components/schemas/EventType'
const: unstructured_log
default: unstructured_log
message:
type: string
severity:
$ref: '#/components/schemas/LogSeverity'
additionalProperties: false
required:
- trace_id
- span_id
- timestamp
- type
- message
- severity
title: UnstructuredLogEvent
LogEventRequest:
type: object
properties:
event:
$ref: '#/components/schemas/Event'
description: The event to log.
ttl_seconds:
type: integer
description: The time to live of the event.
additionalProperties: false
required:
- event
- ttl_seconds
title: LogEventRequest
VectorStoreChunkingStrategy:
oneOf:
- $ref: '#/components/schemas/VectorStoreChunkingStrategyAuto'
- $ref: '#/components/schemas/VectorStoreChunkingStrategyStatic'
discriminator:
propertyName: type
mapping:
auto: '#/components/schemas/VectorStoreChunkingStrategyAuto'
static: '#/components/schemas/VectorStoreChunkingStrategyStatic'
VectorStoreChunkingStrategyAuto:
type: object
properties:
type:
type: string
const: auto
default: auto
additionalProperties: false
required:
- type
title: VectorStoreChunkingStrategyAuto
VectorStoreChunkingStrategyStatic:
type: object
properties:
type:
type: string
const: static
default: static
static:
$ref: '#/components/schemas/VectorStoreChunkingStrategyStaticConfig'
additionalProperties: false
required:
- type
- static
title: VectorStoreChunkingStrategyStatic
VectorStoreChunkingStrategyStaticConfig:
type: object
properties:
chunk_overlap_tokens:
type: integer
default: 400
max_chunk_size_tokens:
type: integer
default: 800
additionalProperties: false
required:
- chunk_overlap_tokens
- max_chunk_size_tokens
title: VectorStoreChunkingStrategyStaticConfig
OpenaiAttachFileToVectorStoreRequest:
type: object
properties:
file_id:
type: string
description: >-
The ID of the file to attach to the vector store.
attributes:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
The key-value attributes stored with the file, which can be used for filtering.
chunking_strategy:
$ref: '#/components/schemas/VectorStoreChunkingStrategy'
description: >-
The chunking strategy to use for the file.
additionalProperties: false
required:
- file_id
title: OpenaiAttachFileToVectorStoreRequest
VectorStoreFileLastError:
type: object
properties:
code:
oneOf:
- type: string
const: server_error
- type: string
const: rate_limit_exceeded
message:
type: string
additionalProperties: false
required:
- code
- message
title: VectorStoreFileLastError
VectorStoreFileObject:
type: object
properties:
id:
type: string
object:
type: string
default: vector_store.file
attributes:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
chunking_strategy:
$ref: '#/components/schemas/VectorStoreChunkingStrategy'
created_at:
type: integer
last_error:
$ref: '#/components/schemas/VectorStoreFileLastError'
status:
$ref: '#/components/schemas/VectorStoreFileStatus'
usage_bytes:
type: integer
default: 0
vector_store_id:
type: string
additionalProperties: false
required:
- id
- object
- attributes
- chunking_strategy
- created_at
- status
- usage_bytes
- vector_store_id
title: VectorStoreFileObject
description: OpenAI Vector Store File object.
VectorStoreFileStatus:
oneOf:
- type: string
const: completed
- type: string
const: in_progress
- type: string
const: cancelled
- type: string
const: failed
OpenAIJSONSchema:
type: object
properties:
name:
type: string
description:
type: string
strict:
type: boolean
schema:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- name
title: OpenAIJSONSchema
OpenAIResponseFormatJSONObject:
type: object
properties:
type:
type: string
const: json_object
default: json_object
additionalProperties: false
required:
- type
title: OpenAIResponseFormatJSONObject
OpenAIResponseFormatJSONSchema:
type: object
properties:
type:
type: string
const: json_schema
default: json_schema
json_schema:
$ref: '#/components/schemas/OpenAIJSONSchema'
additionalProperties: false
required:
- type
- json_schema
title: OpenAIResponseFormatJSONSchema
OpenAIResponseFormatParam:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseFormatText'
- $ref: '#/components/schemas/OpenAIResponseFormatJSONSchema'
- $ref: '#/components/schemas/OpenAIResponseFormatJSONObject'
discriminator:
propertyName: type
mapping:
text: '#/components/schemas/OpenAIResponseFormatText'
json_schema: '#/components/schemas/OpenAIResponseFormatJSONSchema'
json_object: '#/components/schemas/OpenAIResponseFormatJSONObject'
OpenAIResponseFormatText:
type: object
properties:
type:
type: string
const: text
default: text
additionalProperties: false
required:
- type
title: OpenAIResponseFormatText
OpenaiChatCompletionRequest:
type: object
properties:
model:
type: string
description: >-
The identifier of the model to use. The model must be registered with
Llama Stack and available via the /models endpoint.
messages:
type: array
items:
$ref: '#/components/schemas/OpenAIMessageParam'
description: List of messages in the conversation.
frequency_penalty:
type: number
description: >-
(Optional) The penalty for repeated tokens.
function_call:
oneOf:
- type: string
- type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: (Optional) The function call to use.
functions:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: (Optional) List of functions to use.
logit_bias:
type: object
additionalProperties:
type: number
description: (Optional) The logit bias to use.
logprobs:
type: boolean
description: (Optional) The log probabilities to use.
max_completion_tokens:
type: integer
description: >-
(Optional) The maximum number of tokens to generate.
max_tokens:
type: integer
description: >-
(Optional) The maximum number of tokens to generate.
n:
type: integer
description: >-
(Optional) The number of completions to generate.
parallel_tool_calls:
type: boolean
description: >-
(Optional) Whether to parallelize tool calls.
presence_penalty:
type: number
description: >-
(Optional) The penalty for repeated tokens.
response_format:
$ref: '#/components/schemas/OpenAIResponseFormatParam'
description: (Optional) The response format to use.
seed:
type: integer
description: (Optional) The seed to use.
stop:
oneOf:
- type: string
- type: array
items:
type: string
description: (Optional) The stop tokens to use.
stream:
type: boolean
description: >-
(Optional) Whether to stream the response.
stream_options:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: (Optional) The stream options to use.
temperature:
type: number
description: (Optional) The temperature to use.
tool_choice:
oneOf:
- type: string
- type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: (Optional) The tool choice to use.
tools:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: (Optional) The tools to use.
top_logprobs:
type: integer
description: >-
(Optional) The top log probabilities to use.
top_p:
type: number
description: (Optional) The top p to use.
user:
type: string
description: (Optional) The user to use.
additionalProperties: false
required:
- model
- messages
title: OpenaiChatCompletionRequest
OpenAIChatCompletion:
type: object
properties:
id:
type: string
description: The ID of the chat completion
choices:
type: array
items:
$ref: '#/components/schemas/OpenAIChoice'
description: List of choices
object:
type: string
const: chat.completion
default: chat.completion
description: >-
The object type, which will be "chat.completion"
created:
type: integer
description: >-
The Unix timestamp in seconds when the chat completion was created
model:
type: string
description: >-
The model that was used to generate the chat completion
additionalProperties: false
required:
- id
- choices
- object
- created
- model
title: OpenAIChatCompletion
description: >-
Response from an OpenAI-compatible chat completion request.
OpenAIChatCompletionChunk:
type: object
properties:
id:
type: string
description: The ID of the chat completion
choices:
type: array
items:
$ref: '#/components/schemas/OpenAIChunkChoice'
description: List of choices
object:
type: string
const: chat.completion.chunk
default: chat.completion.chunk
description: >-
The object type, which will be "chat.completion.chunk"
created:
type: integer
description: >-
The Unix timestamp in seconds when the chat completion was created
model:
type: string
description: >-
The model that was used to generate the chat completion
additionalProperties: false
required:
- id
- choices
- object
- created
- model
title: OpenAIChatCompletionChunk
description: >-
Chunk from a streaming response to an OpenAI-compatible chat completion request.
OpenAIChoiceDelta:
type: object
properties:
content:
type: string
description: (Optional) The content of the delta
refusal:
type: string
description: (Optional) The refusal of the delta
role:
type: string
description: (Optional) The role of the delta
tool_calls:
type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionToolCall'
description: (Optional) The tool calls of the delta
additionalProperties: false
title: OpenAIChoiceDelta
description: >-
A delta from an OpenAI-compatible chat completion streaming response.
OpenAIChunkChoice:
type: object
properties:
delta:
$ref: '#/components/schemas/OpenAIChoiceDelta'
description: The delta from the chunk
finish_reason:
type: string
description: The reason the model stopped generating
index:
type: integer
description: The index of the choice
logprobs:
$ref: '#/components/schemas/OpenAIChoiceLogprobs'
description: >-
(Optional) The log probabilities for the tokens in the message
additionalProperties: false
required:
- delta
- finish_reason
- index
title: OpenAIChunkChoice
description: >-
A chunk choice from an OpenAI-compatible chat completion streaming response.
OpenaiCompletionRequest:
type: object
properties:
model:
type: string
description: >-
The identifier of the model to use. The model must be registered with
Llama Stack and available via the /models endpoint.
prompt:
oneOf:
- type: string
- type: array
items:
type: string
- type: array
items:
type: integer
- type: array
items:
type: array
items:
type: integer
description: The prompt to generate a completion for.
best_of:
type: integer
description: >-
(Optional) The number of completions to generate.
echo:
type: boolean
description: (Optional) Whether to echo the prompt.
frequency_penalty:
type: number
description: >-
(Optional) The penalty for repeated tokens.
logit_bias:
type: object
additionalProperties:
type: number
description: (Optional) The logit bias to use.
logprobs:
type: boolean
description: (Optional) The log probabilities to use.
max_tokens:
type: integer
description: >-
(Optional) The maximum number of tokens to generate.
n:
type: integer
description: >-
(Optional) The number of completions to generate.
presence_penalty:
type: number
description: >-
(Optional) The penalty for repeated tokens.
seed:
type: integer
description: (Optional) The seed to use.
stop:
oneOf:
- type: string
- type: array
items:
type: string
description: (Optional) The stop tokens to use.
stream:
type: boolean
description: >-
(Optional) Whether to stream the response.
stream_options:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: (Optional) The stream options to use.
temperature:
type: number
description: (Optional) The temperature to use.
top_p:
type: number
description: (Optional) The top p to use.
user:
type: string
description: (Optional) The user to use.
guided_choice:
type: array
items:
type: string
prompt_logprobs:
type: integer
suffix:
type: string
description: >-
(Optional) The suffix that should be appended to the completion.
additionalProperties: false
required:
- model
- prompt
title: OpenaiCompletionRequest
OpenAICompletion:
type: object
properties:
id:
type: string
choices:
type: array
items:
$ref: '#/components/schemas/OpenAICompletionChoice'
created:
type: integer
model:
type: string
object:
type: string
const: text_completion
default: text_completion
additionalProperties: false
required:
- id
- choices
- created
- model
- object
title: OpenAICompletion
description: >-
Response from an OpenAI-compatible completion request.
OpenAICompletionChoice:
type: object
properties:
finish_reason:
type: string
text:
type: string
index:
type: integer
logprobs:
$ref: '#/components/schemas/OpenAIChoiceLogprobs'
additionalProperties: false
required:
- finish_reason
- text
- index
title: OpenAICompletionChoice
description: >-
A choice from an OpenAI-compatible completion response.
OpenaiCreateVectorStoreRequest:
type: object
properties:
name:
type: string
description: A name for the vector store.
file_ids:
type: array
items:
type: string
description: >-
A list of File IDs that the vector store should use. Useful for tools
like `file_search` that can access files.
expires_after:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
The expiration policy for a vector store.
chunking_strategy:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
The chunking strategy used to chunk the file(s). If not set, will use
the `auto` strategy.
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
Set of 16 key-value pairs that can be attached to an object.
embedding_model:
type: string
description: >-
The embedding model to use for this vector store.
embedding_dimension:
type: integer
description: >-
The dimension of the embedding vectors (default: 384).
provider_id:
type: string
description: >-
The ID of the provider to use for this vector store.
provider_vector_db_id:
type: string
description: >-
The provider-specific vector database ID.
additionalProperties: false
required:
- name
title: OpenaiCreateVectorStoreRequest
VectorStoreFileCounts:
type: object
properties:
completed:
type: integer
cancelled:
type: integer
failed:
type: integer
in_progress:
type: integer
total:
type: integer
additionalProperties: false
required:
- completed
- cancelled
- failed
- in_progress
- total
title: VectorStoreFileCounts
VectorStoreObject:
type: object
properties:
id:
type: string
object:
type: string
default: vector_store
created_at:
type: integer
name:
type: string
usage_bytes:
type: integer
default: 0
file_counts:
$ref: '#/components/schemas/VectorStoreFileCounts'
status:
type: string
default: completed
expires_after:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
expires_at:
type: integer
last_active_at:
type: integer
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- id
- object
- created_at
- usage_bytes
- file_counts
- status
- metadata
title: VectorStoreObject
description: OpenAI Vector Store object.
OpenAIFileDeleteResponse:
type: object
properties:
id:
type: string
description: The file identifier that was deleted
object:
type: string
const: file
default: file
description: The object type, which is always "file"
deleted:
type: boolean
description: >-
Whether the file was successfully deleted
additionalProperties: false
required:
- id
- object
- deleted
title: OpenAIFileDeleteResponse
description: >-
Response for deleting a file in OpenAI Files API.
VectorStoreDeleteResponse:
type: object
properties:
id:
type: string
object:
type: string
default: vector_store.deleted
deleted:
type: boolean
default: true
additionalProperties: false
required:
- id
- object
- deleted
title: VectorStoreDeleteResponse
description: Response from deleting a vector store.
VectorStoreFileDeleteResponse:
type: object
properties:
id:
type: string
object:
type: string
default: vector_store.file.deleted
deleted:
type: boolean
default: true
additionalProperties: false
required:
- id
- object
- deleted
title: VectorStoreFileDeleteResponse
description: >-
Response from deleting a vector store file.
OpenaiEmbeddingsRequest:
type: object
properties:
model:
type: string
description: >-
The identifier of the model to use. The model must be an embedding model
registered with Llama Stack and available via the /models endpoint.
input:
oneOf:
- type: string
- type: array
items:
type: string
description: >-
Input text to embed, encoded as a string or array of strings. To embed
multiple inputs in a single request, pass an array of strings.
encoding_format:
type: string
description: >-
(Optional) The format to return the embeddings in. Can be either "float"
or "base64". Defaults to "float".
dimensions:
type: integer
description: >-
(Optional) The number of dimensions the resulting output embeddings should
have. Only supported in text-embedding-3 and later models.
user:
type: string
description: >-
(Optional) A unique identifier representing your end-user, which can help
OpenAI to monitor and detect abuse.
additionalProperties: false
required:
- model
- input
title: OpenaiEmbeddingsRequest
OpenAIEmbeddingData:
type: object
properties:
object:
type: string
const: embedding
default: embedding
description: >-
The object type, which will be "embedding"
embedding:
oneOf:
- type: array
items:
type: number
- type: string
description: >-
The embedding vector as a list of floats (when encoding_format="float")
or as a base64-encoded string (when encoding_format="base64")
index:
type: integer
description: >-
The index of the embedding in the input list
additionalProperties: false
required:
- object
- embedding
- index
title: OpenAIEmbeddingData
description: >-
A single embedding data object from an OpenAI-compatible embeddings response.
OpenAIEmbeddingUsage:
type: object
properties:
prompt_tokens:
type: integer
description: The number of tokens in the input
total_tokens:
type: integer
description: The total number of tokens used
additionalProperties: false
required:
- prompt_tokens
- total_tokens
title: OpenAIEmbeddingUsage
description: >-
Usage information for an OpenAI-compatible embeddings response.
OpenAIEmbeddingsResponse:
type: object
properties:
object:
type: string
const: list
default: list
description: The object type, which will be "list"
data:
type: array
items:
$ref: '#/components/schemas/OpenAIEmbeddingData'
description: List of embedding data objects
model:
type: string
description: >-
The model that was used to generate the embeddings
usage:
$ref: '#/components/schemas/OpenAIEmbeddingUsage'
description: Usage information
additionalProperties: false
required:
- object
- data
- model
- usage
title: OpenAIEmbeddingsResponse
description: >-
Response from an OpenAI-compatible embeddings request.
OpenAIFilePurpose:
type: string
enum:
- assistants
title: OpenAIFilePurpose
description: >-
Valid purpose values for OpenAI Files API.
ListOpenAIFileResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/OpenAIFileObject'
description: List of file objects
has_more:
type: boolean
first_id:
type: string
last_id:
type: string
object:
type: string
const: list
default: list
description: The object type, which is always "list"
additionalProperties: false
required:
- data
- has_more
- first_id
- last_id
- object
title: ListOpenAIFileResponse
description: >-
Response for listing files in OpenAI Files API.
OpenAIFileObject:
type: object
properties:
object:
type: string
const: file
default: file
description: The object type, which is always "file"
id:
type: string
description: >-
The file identifier, which can be referenced in the API endpoints
bytes:
type: integer
description: The size of the file, in bytes
created_at:
type: integer
description: >-
The Unix timestamp (in seconds) for when the file was created
expires_at:
type: integer
description: >-
The Unix timestamp (in seconds) for when the file expires
filename:
type: string
description: The name of the file
purpose:
type: string
enum:
- assistants
description: The intended purpose of the file
additionalProperties: false
required:
- object
- id
- bytes
- created_at
- expires_at
- filename
- purpose
title: OpenAIFileObject
description: >-
OpenAI File object as defined in the OpenAI Files API.
VectorStoreListFilesResponse:
type: object
properties:
object:
type: string
default: list
data:
type: array
items:
$ref: '#/components/schemas/VectorStoreFileObject'
first_id:
type: string
last_id:
type: string
has_more:
type: boolean
default: false
additionalProperties: false
required:
- object
- data
- has_more
title: VectorStoreListFilesResponse
description: Response from listing vector stores.
OpenAIModel:
type: object
properties:
id:
type: string
object:
type: string
const: model
default: model
created:
type: integer
owned_by:
type: string
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
VectorStoreListResponse:
type: object
properties:
object:
type: string
default: list
data:
type: array
items:
$ref: '#/components/schemas/VectorStoreObject'
first_id:
type: string
last_id:
type: string
has_more:
type: boolean
default: false
additionalProperties: false
required:
- object
- data
- has_more
title: VectorStoreListResponse
description: Response from listing vector stores.
Response:
type: object
title: Response
VectorStoreContent:
type: object
properties:
type:
type: string
const: text
text:
type: string
additionalProperties: false
required:
- type
- text
title: VectorStoreContent
VectorStoreFileContentsResponse:
type: object
properties:
file_id:
type: string
filename:
type: string
attributes:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
content:
type: array
items:
$ref: '#/components/schemas/VectorStoreContent'
additionalProperties: false
required:
- file_id
- filename
- attributes
- content
title: VectorStoreFileContentsResponse
description: >-
Response from retrieving the contents of a vector store file.
OpenaiSearchVectorStoreRequest:
type: object
properties:
query:
oneOf:
- type: string
- type: array
items:
type: string
description: >-
The query string or array for performing the search.
filters:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
Filters based on file attributes to narrow the search results.
max_num_results:
type: integer
description: >-
Maximum number of results to return (1 to 50 inclusive, default 10).
ranking_options:
type: object
properties:
ranker:
type: string
score_threshold:
type: number
default: 0.0
additionalProperties: false
description: >-
Ranking options for fine-tuning the search results.
rewrite_query:
type: boolean
description: >-
Whether to rewrite the natural language query for vector search (default
false)
search_mode:
type: string
description: >-
The search mode to use - "keyword", "vector", or "hybrid" (default "vector")
additionalProperties: false
required:
- query
title: OpenaiSearchVectorStoreRequest
VectorStoreSearchResponse:
type: object
properties:
file_id:
type: string
filename:
type: string
score:
type: number
attributes:
type: object
additionalProperties:
oneOf:
- type: string
- type: number
- type: boolean
content:
type: array
items:
$ref: '#/components/schemas/VectorStoreContent'
additionalProperties: false
required:
- file_id
- filename
- score
- content
title: VectorStoreSearchResponse
description: Response from searching a vector store.
VectorStoreSearchResponsePage:
type: object
properties:
object:
type: string
default: vector_store.search_results.page
search_query:
type: string
data:
type: array
items:
$ref: '#/components/schemas/VectorStoreSearchResponse'
has_more:
type: boolean
default: false
next_page:
type: string
additionalProperties: false
required:
- object
- search_query
- data
- has_more
title: VectorStoreSearchResponsePage
description: Response from searching a vector store.
OpenaiUpdateVectorStoreRequest:
type: object
properties:
name:
type: string
description: The name of the vector store.
expires_after:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
The expiration policy for a vector store.
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
Set of 16 key-value pairs that can be attached to an object.
additionalProperties: false
title: OpenaiUpdateVectorStoreRequest
OpenaiUpdateVectorStoreFileRequest:
type: object
properties:
attributes:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
The updated key-value attributes to store with the file.
additionalProperties: false
required:
- attributes
title: OpenaiUpdateVectorStoreFileRequest
DPOAlignmentConfig:
type: object
properties:
reward_scale:
type: number
reward_clip:
type: number
epsilon:
type: number
gamma:
type: number
additionalProperties: false
required:
- reward_scale
- reward_clip
- epsilon
- gamma
title: DPOAlignmentConfig
DataConfig:
type: object
properties:
dataset_id:
type: string
batch_size:
type: integer
shuffle:
type: boolean
data_format:
$ref: '#/components/schemas/DatasetFormat'
validation_dataset_id:
type: string
packed:
type: boolean
default: false
train_on_input:
type: boolean
default: false
additionalProperties: false
required:
- dataset_id
- batch_size
- shuffle
- data_format
title: DataConfig
DatasetFormat:
type: string
enum:
- instruct
- dialog
title: DatasetFormat
EfficiencyConfig:
type: object
properties:
enable_activation_checkpointing:
type: boolean
default: false
enable_activation_offloading:
type: boolean
default: false
memory_efficient_fsdp_wrap:
type: boolean
default: false
fsdp_cpu_offload:
type: boolean
default: false
additionalProperties: false
title: EfficiencyConfig
OptimizerConfig:
type: object
properties:
optimizer_type:
$ref: '#/components/schemas/OptimizerType'
lr:
type: number
weight_decay:
type: number
num_warmup_steps:
type: integer
additionalProperties: false
required:
- optimizer_type
- lr
- weight_decay
- num_warmup_steps
title: OptimizerConfig
OptimizerType:
type: string
enum:
- adam
- adamw
- sgd
title: OptimizerType
TrainingConfig:
type: object
properties:
n_epochs:
type: integer
max_steps_per_epoch:
type: integer
default: 1
gradient_accumulation_steps:
type: integer
default: 1
max_validation_steps:
type: integer
default: 1
data_config:
$ref: '#/components/schemas/DataConfig'
optimizer_config:
$ref: '#/components/schemas/OptimizerConfig'
efficiency_config:
$ref: '#/components/schemas/EfficiencyConfig'
dtype:
type: string
default: bf16
additionalProperties: false
required:
- n_epochs
- max_steps_per_epoch
- gradient_accumulation_steps
title: TrainingConfig
PreferenceOptimizeRequest:
type: object
properties:
job_uuid:
type: string
description: The UUID of the job to create.
finetuned_model:
type: string
description: The model to fine-tune.
algorithm_config:
$ref: '#/components/schemas/DPOAlignmentConfig'
description: The algorithm configuration.
training_config:
$ref: '#/components/schemas/TrainingConfig'
description: The training configuration.
hyperparam_search_config:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: The hyperparam search configuration.
logger_config:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: The logger configuration.
additionalProperties: false
required:
- job_uuid
- finetuned_model
- algorithm_config
- training_config
- hyperparam_search_config
- logger_config
title: PreferenceOptimizeRequest
PostTrainingJob:
type: object
properties:
job_uuid:
type: string
additionalProperties: false
required:
- job_uuid
title: PostTrainingJob
DefaultRAGQueryGeneratorConfig:
type: object
properties:
type:
type: string
const: default
default: default
separator:
type: string
default: ' '
additionalProperties: false
required:
- type
- separator
title: DefaultRAGQueryGeneratorConfig
LLMRAGQueryGeneratorConfig:
type: object
properties:
type:
type: string
const: llm
default: llm
model:
type: string
template:
type: string
additionalProperties: false
required:
- type
- model
- template
title: LLMRAGQueryGeneratorConfig
RAGQueryConfig:
type: object
properties:
query_generator_config:
$ref: '#/components/schemas/RAGQueryGeneratorConfig'
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}
Content: {chunk.content}
Metadata: {metadata}
description: >-
Template for formatting each retrieved chunk in the context. Available
placeholders: {index} (1-based chunk ordinal), {chunk.content} (chunk
content string), {metadata} (chunk metadata dict). Default: "Result {index}\nContent:
{chunk.content}\nMetadata: {metadata}\n"
mode:
type: string
description: >-
Search mode for retrieval—either "vector", "keyword", or "hybrid". Default
"vector".
ranker:
$ref: '#/components/schemas/Ranker'
description: >-
Configuration for the ranker to use in hybrid search. Defaults to RRF
ranker.
additionalProperties: false
required:
- query_generator_config
- max_tokens_in_context
- max_chunks
- chunk_template
title: RAGQueryConfig
description: >-
Configuration for the RAG query generation.
RAGQueryGeneratorConfig:
oneOf:
- $ref: '#/components/schemas/DefaultRAGQueryGeneratorConfig'
- $ref: '#/components/schemas/LLMRAGQueryGeneratorConfig'
discriminator:
propertyName: type
mapping:
default: '#/components/schemas/DefaultRAGQueryGeneratorConfig'
llm: '#/components/schemas/LLMRAGQueryGeneratorConfig'
RRFRanker:
type: object
properties:
type:
type: string
const: rrf
default: rrf
description: The type of ranker, always "rrf"
impact_factor:
type: number
default: 60.0
description: >-
The impact factor for RRF scoring. Higher values give more weight to higher-ranked
results. Must be greater than 0. Default of 60 is from the original RRF
paper (Cormack et al., 2009).
additionalProperties: false
required:
- type
- impact_factor
title: RRFRanker
description: >-
Reciprocal Rank Fusion (RRF) ranker configuration.
Ranker:
oneOf:
- $ref: '#/components/schemas/RRFRanker'
- $ref: '#/components/schemas/WeightedRanker'
discriminator:
propertyName: type
mapping:
rrf: '#/components/schemas/RRFRanker'
weighted: '#/components/schemas/WeightedRanker'
WeightedRanker:
type: object
properties:
type:
type: string
const: weighted
default: weighted
description: The type of ranker, always "weighted"
alpha:
type: number
default: 0.5
description: >-
Weight factor between 0 and 1. 0 means only use keyword scores, 1 means
only use vector scores, values in between blend both scores.
additionalProperties: false
required:
- type
- alpha
title: WeightedRanker
description: >-
Weighted ranker configuration that combines vector and keyword scores.
QueryRequest:
type: object
properties:
content:
$ref: '#/components/schemas/InterleavedContent'
vector_db_ids:
type: array
items:
type: string
query_config:
$ref: '#/components/schemas/RAGQueryConfig'
additionalProperties: false
required:
- content
- vector_db_ids
title: QueryRequest
RAGQueryResult:
type: object
properties:
content:
$ref: '#/components/schemas/InterleavedContent'
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- metadata
title: RAGQueryResult
QueryChunksRequest:
type: object
properties:
vector_db_id:
type: string
description: >-
The identifier of the vector database to query.
query:
$ref: '#/components/schemas/InterleavedContent'
description: The query to search for.
params:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: The parameters of the query.
additionalProperties: false
required:
- vector_db_id
- query
title: QueryChunksRequest
QueryChunksResponse:
type: object
properties:
chunks:
type: array
items:
$ref: '#/components/schemas/Chunk'
scores:
type: array
items:
type: number
additionalProperties: false
required:
- chunks
- scores
title: QueryChunksResponse
QueryMetricsRequest:
type: object
properties:
start_time:
type: integer
description: The start time of the metric to query.
end_time:
type: integer
description: The end time of the metric to query.
granularity:
type: string
description: The granularity of the metric to query.
query_type:
type: string
enum:
- range
- instant
description: The type of query to perform.
label_matchers:
type: array
items:
type: object
properties:
name:
type: string
value:
type: string
operator:
type: string
enum:
- '='
- '!='
- =~
- '!~'
title: MetricLabelOperator
default: '='
additionalProperties: false
required:
- name
- value
- operator
title: MetricLabelMatcher
description: >-
The label matchers to apply to the metric.
additionalProperties: false
required:
- start_time
- query_type
title: QueryMetricsRequest
MetricDataPoint:
type: object
properties:
timestamp:
type: integer
value:
type: number
additionalProperties: false
required:
- timestamp
- value
title: MetricDataPoint
MetricLabel:
type: object
properties:
name:
type: string
value:
type: string
additionalProperties: false
required:
- name
- value
title: MetricLabel
MetricSeries:
type: object
properties:
metric:
type: string
labels:
type: array
items:
$ref: '#/components/schemas/MetricLabel'
values:
type: array
items:
$ref: '#/components/schemas/MetricDataPoint'
additionalProperties: false
required:
- metric
- labels
- values
title: MetricSeries
QueryMetricsResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/MetricSeries'
additionalProperties: false
required:
- data
title: QueryMetricsResponse
QueryCondition:
type: object
properties:
key:
type: string
op:
$ref: '#/components/schemas/QueryConditionOp'
value:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- key
- op
- value
title: QueryCondition
QueryConditionOp:
type: string
enum:
- eq
- ne
- gt
- lt
title: QueryConditionOp
QuerySpansRequest:
type: object
properties:
attribute_filters:
type: array
items:
$ref: '#/components/schemas/QueryCondition'
description: >-
The attribute filters to apply to the spans.
attributes_to_return:
type: array
items:
type: string
description: The attributes to return in the spans.
max_depth:
type: integer
description: The maximum depth of the tree.
additionalProperties: false
required:
- attribute_filters
- attributes_to_return
title: QuerySpansRequest
QuerySpansResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/Span'
additionalProperties: false
required:
- data
title: QuerySpansResponse
QueryTracesRequest:
type: object
properties:
attribute_filters:
type: array
items:
$ref: '#/components/schemas/QueryCondition'
description: >-
The attribute filters to apply to the traces.
limit:
type: integer
description: The limit of traces to return.
offset:
type: integer
description: The offset of the traces to return.
order_by:
type: array
items:
type: string
description: The order by of the traces to return.
additionalProperties: false
title: QueryTracesRequest
QueryTracesResponse:
type: object
properties:
data:
type: array
items:
$ref: '#/components/schemas/Trace'
additionalProperties: false
required:
- data
title: QueryTracesResponse
RegisterBenchmarkRequest:
type: object
properties:
benchmark_id:
type: string
description: The ID of the benchmark to register.
dataset_id:
type: string
description: >-
The ID of the dataset to use for the benchmark.
scoring_functions:
type: array
items:
type: string
description: >-
The scoring functions to use for the benchmark.
provider_benchmark_id:
type: string
description: >-
The ID of the provider benchmark to use for the benchmark.
provider_id:
type: string
description: >-
The ID of the provider to use for the benchmark.
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: The metadata to use for the benchmark.
additionalProperties: false
required:
- benchmark_id
- dataset_id
- scoring_functions
title: RegisterBenchmarkRequest
RegisterDatasetRequest:
type: object
properties:
purpose:
type: string
enum:
- post-training/messages
- eval/question-answer
- eval/messages-answer
description: >-
The purpose of the dataset. One of: - "post-training/messages": The dataset
contains a messages column with list of messages for post-training. {
"messages": [ {"role": "user", "content": "Hello, world!"}, {"role": "assistant",
"content": "Hello, world!"}, ] } - "eval/question-answer": The dataset
contains a question column and an answer column for evaluation. { "question":
"What is the capital of France?", "answer": "Paris" } - "eval/messages-answer":
The dataset contains a messages column with list of messages and an answer
column for evaluation. { "messages": [ {"role": "user", "content": "Hello,
my name is John Doe."}, {"role": "assistant", "content": "Hello, John
Doe. How can I help you today?"}, {"role": "user", "content": "What's
my name?"}, ], "answer": "John Doe" }
source:
$ref: '#/components/schemas/DataSource'
description: >-
The data source of the dataset. Ensure that the data source schema is
compatible with the purpose of the dataset. Examples: - { "type": "uri",
"uri": "https://mywebsite.com/mydata.jsonl" } - { "type": "uri", "uri":
"lsfs://mydata.jsonl" } - { "type": "uri", "uri": "data:csv;base64,{base64_content}"
} - { "type": "uri", "uri": "huggingface://llamastack/simpleqa?split=train"
} - { "type": "rows", "rows": [ { "messages": [ {"role": "user", "content":
"Hello, world!"}, {"role": "assistant", "content": "Hello, world!"}, ]
} ] }
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: >-
The metadata for the dataset. - E.g. {"description": "My dataset"}.
dataset_id:
type: string
description: >-
The ID of the dataset. If not provided, an ID will be generated.
additionalProperties: false
required:
- purpose
- source
title: RegisterDatasetRequest
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
RegisterScoringFunctionRequest:
type: object
properties:
scoring_fn_id:
type: string
description: >-
The ID of the scoring function to register.
description:
type: string
description: The description of the scoring function.
return_type:
$ref: '#/components/schemas/ParamType'
description: The return type of the scoring function.
provider_scoring_fn_id:
type: string
description: >-
The ID of the provider scoring function to use for the scoring function.
provider_id:
type: string
description: >-
The ID of the provider to use for the scoring function.
params:
$ref: '#/components/schemas/ScoringFnParams'
description: >-
The parameters for the scoring function for benchmark eval, these can
be overridden for app eval.
additionalProperties: false
required:
- scoring_fn_id
- description
- return_type
title: RegisterScoringFunctionRequest
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
RegisterToolGroupRequest:
type: object
properties:
toolgroup_id:
type: string
description: The ID of the tool group to register.
provider_id:
type: string
description: >-
The ID of the provider to use for the tool group.
mcp_endpoint:
$ref: '#/components/schemas/URL'
description: >-
The MCP endpoint to use for the tool group.
args:
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 group.
additionalProperties: false
required:
- toolgroup_id
- provider_id
title: RegisterToolGroupRequest
RegisterVectorDbRequest:
type: object
properties:
vector_db_id:
type: string
description: >-
The identifier of the vector database to register.
embedding_model:
type: string
description: The embedding model to use.
embedding_dimension:
type: integer
description: The dimension of the embedding model.
provider_id:
type: string
description: The identifier of the provider.
provider_vector_db_id:
type: string
description: >-
The identifier of the vector database in the provider.
additionalProperties: false
required:
- vector_db_id
- embedding_model
title: RegisterVectorDbRequest
ResumeAgentTurnRequest:
type: object
properties:
tool_responses:
type: array
items:
$ref: '#/components/schemas/ToolResponse'
description: >-
The tool call responses to resume the turn with.
stream:
type: boolean
description: Whether to stream the response.
additionalProperties: false
required:
- tool_responses
title: ResumeAgentTurnRequest
RunEvalRequest:
type: object
properties:
benchmark_config:
$ref: '#/components/schemas/BenchmarkConfig'
description: The configuration for the benchmark.
additionalProperties: false
required:
- benchmark_config
title: RunEvalRequest
RunShieldRequest:
type: object
properties:
shield_id:
type: string
description: The identifier of the shield to run.
messages:
type: array
items:
$ref: '#/components/schemas/Message'
description: The messages to run the shield on.
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
- messages
- params
title: RunShieldRequest
RunShieldResponse:
type: object
properties:
violation:
$ref: '#/components/schemas/SafetyViolation'
additionalProperties: false
title: RunShieldResponse
SaveSpansToDatasetRequest:
type: object
properties:
attribute_filters:
type: array
items:
$ref: '#/components/schemas/QueryCondition'
description: >-
The attribute filters to apply to the spans.
attributes_to_save:
type: array
items:
type: string
description: The attributes to save to the dataset.
dataset_id:
type: string
description: >-
The ID of the dataset to save the spans to.
max_depth:
type: integer
description: The maximum depth of the tree.
additionalProperties: false
required:
- attribute_filters
- attributes_to_save
- dataset_id
title: SaveSpansToDatasetRequest
ScoreRequest:
type: object
properties:
input_rows:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: The rows to score.
scoring_functions:
type: object
additionalProperties:
oneOf:
- $ref: '#/components/schemas/ScoringFnParams'
- type: 'null'
description: >-
The scoring functions to use for the scoring.
additionalProperties: false
required:
- input_rows
- scoring_functions
title: ScoreRequest
ScoreResponse:
type: object
properties:
results:
type: object
additionalProperties:
$ref: '#/components/schemas/ScoringResult'
description: >-
A map of scoring function name to ScoringResult.
additionalProperties: false
required:
- results
title: ScoreResponse
description: The response from scoring.
ScoreBatchRequest:
type: object
properties:
dataset_id:
type: string
description: The ID of the dataset to score.
scoring_functions:
type: object
additionalProperties:
oneOf:
- $ref: '#/components/schemas/ScoringFnParams'
- type: 'null'
description: >-
The scoring functions to use for the scoring.
save_results_dataset:
type: boolean
description: >-
Whether to save the results to a dataset.
additionalProperties: false
required:
- dataset_id
- scoring_functions
- save_results_dataset
title: ScoreBatchRequest
ScoreBatchResponse:
type: object
properties:
dataset_id:
type: string
results:
type: object
additionalProperties:
$ref: '#/components/schemas/ScoringResult'
additionalProperties: false
required:
- results
title: ScoreBatchResponse
AlgorithmConfig:
oneOf:
- $ref: '#/components/schemas/LoraFinetuningConfig'
- $ref: '#/components/schemas/QATFinetuningConfig'
discriminator:
propertyName: type
mapping:
LoRA: '#/components/schemas/LoraFinetuningConfig'
QAT: '#/components/schemas/QATFinetuningConfig'
LoraFinetuningConfig:
type: object
properties:
type:
type: string
const: LoRA
default: LoRA
lora_attn_modules:
type: array
items:
type: string
apply_lora_to_mlp:
type: boolean
apply_lora_to_output:
type: boolean
rank:
type: integer
alpha:
type: integer
use_dora:
type: boolean
default: false
quantize_base:
type: boolean
default: false
additionalProperties: false
required:
- type
- lora_attn_modules
- apply_lora_to_mlp
- apply_lora_to_output
- rank
- alpha
title: LoraFinetuningConfig
QATFinetuningConfig:
type: object
properties:
type:
type: string
const: QAT
default: QAT
quantizer_name:
type: string
group_size:
type: integer
additionalProperties: false
required:
- type
- quantizer_name
- group_size
title: QATFinetuningConfig
SupervisedFineTuneRequest:
type: object
properties:
job_uuid:
type: string
description: The UUID of the job to create.
training_config:
$ref: '#/components/schemas/TrainingConfig'
description: The training configuration.
hyperparam_search_config:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: The hyperparam search configuration.
logger_config:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: The logger configuration.
model:
type: string
description: The model to fine-tune.
checkpoint_dir:
type: string
description: The directory to save checkpoint(s) to.
algorithm_config:
$ref: '#/components/schemas/AlgorithmConfig'
description: The algorithm configuration.
additionalProperties: false
required:
- job_uuid
- training_config
- hyperparam_search_config
- logger_config
title: SupervisedFineTuneRequest
SyntheticDataGenerateRequest:
type: object
properties:
dialogs:
type: array
items:
$ref: '#/components/schemas/Message'
filtering_function:
type: string
enum:
- none
- random
- top_k
- top_p
- top_k_top_p
- sigmoid
title: FilteringFunction
description: The type of filtering function.
model:
type: string
additionalProperties: false
required:
- dialogs
- filtering_function
title: SyntheticDataGenerateRequest
SyntheticDataGenerationResponse:
type: object
properties:
synthetic_data:
type: array
items:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
statistics:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- synthetic_data
title: SyntheticDataGenerationResponse
description: >-
Response from the synthetic data generation. Batch of (prompt, response, score)
tuples that pass the threshold.
VersionInfo:
type: object
properties:
version:
type: string
additionalProperties: false
required:
- version
title: VersionInfo
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: >-
Main functionalities provided by this API:
- Create agents with specific instructions and ability to use tools.
- Interactions with agents are grouped into sessions ("threads"), and each interaction
is called a "turn".
- Agents can be provided with various tools (see the ToolGroups and ToolRuntime
APIs for more details).
- Agents can be provided with various shields (see the Safety API for more details).
- Agents can also use Memory to retrieve information from knowledge bases. See
the RAG Tool and Vector IO APIs for more details.
x-displayName: >-
Agents API for creating and interacting with agentic systems.
- name: BatchInference (Coming Soon)
description: >-
This is an asynchronous API. If the request is successful, the response will
be a job which can be polled for completion.
NOTE: This API is not yet implemented and is subject to change in concert with
other asynchronous APIs
including (post-training, evals, etc).
x-displayName: >-
Batch inference API for generating completions and chat completions.
- name: Benchmarks
- name: DatasetIO
- name: Datasets
- name: Eval
x-displayName: >-
Llama Stack Evaluation API for running evaluations on model and agent candidates.
- name: Files
- name: Inference
description: >-
This API provides the raw interface to the underlying models. Two 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.
x-displayName: >-
Llama Stack Inference API for generating completions, chat completions, and
embeddings.
- name: Inspect
- name: Models
- name: PostTraining (Coming Soon)
- name: Providers
x-displayName: >-
Providers API for inspecting, listing, and modifying providers and their configurations.
- name: Safety
- name: Scoring
- name: ScoringFunctions
- name: Shields
- name: SyntheticDataGeneration (Coming Soon)
- name: Telemetry
- name: ToolGroups
- name: ToolRuntime
- name: VectorDBs
- name: VectorIO
x-tagGroups:
- name: Operations
tags:
- Agents
- BatchInference (Coming Soon)
- Benchmarks
- DatasetIO
- Datasets
- Eval
- Files
- Inference
- Inspect
- Models
- PostTraining (Coming Soon)
- Providers
- Safety
- Scoring
- ScoringFunctions
- Shields
- SyntheticDataGeneration (Coming Soon)
- Telemetry
- ToolGroups
- ToolRuntime
- VectorDBs
- VectorIO
Reference in a new issue View git blame Copy permalink