phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into chroma

Browse source
This commit is contained in:
kimbwook 2025-10-15 00:14:05 +09:00
commit 3f66f55771
No known key found for this signature in database
GPG key ID: 13B032C99CBD373A
137 changed files with 35682 additions and 1800 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/docs/building_applications/rag.mdx
View file

@ -47,8 +47,8 @@ client = LlamaStackClient(base_url=f"http://localhost:{os.environ['LLAMA_STACK_P
vector_db_id = "my_documents"
response = client.vector_dbs.register(
vector_db_id=vector_db_id,
embedding_model="all-MiniLM-L6-v2",
embedding_dimension=384,
embedding_model="nomic-embed-text-v1.5",
embedding_dimension=768,
provider_id="faiss",
)
```

4
docs/docs/distributions/k8s/stack_run_config.yaml
View file

@ -110,8 +110,8 @@ inference_store:
password: ${env.POSTGRES_PASSWORD:=llamastack}
models:
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
embedding_dimension: 768
model_id: nomic-embed-text-v1.5
provider_id: sentence-transformers
model_type: embedding
- metadata: {}

2
docs/docs/getting_started/detailed_tutorial.mdx
View file

@ -164,7 +164,7 @@ Available Models
┏━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━┓
┃ model_type ┃ identifier ┃ provider_resource_id ┃ metadata ┃ provider_id ┃
┡━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━┩
│ embedding │ ollama/all-minilm:l6-v2 │ all-minilm:l6-v2 │ {'embedding_dimension': 384.0} │ ollama │
│ embedding │ ollama/nomic-embed-text:v1.5 │ nomic-embed-text:v1.5 │ {'embedding_dimension': 768.0} │ ollama │
├─────────────────┼─────────────────────────────────────┼─────────────────────────────────────┼───────────────────────────────────────────┼───────────────────────┤
│ ... │ ... │ ... │ │ ... │
├─────────────────┼─────────────────────────────────────┼─────────────────────────────────────┼───────────────────────────────────────────┼───────────────────────┤

8
docs/docs/references/llama_stack_client_cli_reference.md
View file

@ -224,8 +224,8 @@ llama-stack-client vector_dbs list
┏━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ identifier ┃ provider_id ┃ provider_resource_id ┃ vector_db_type ┃ params ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩
│ my_demo_vector_db │ faiss │ my_demo_vector_db │ │ embedding_dimension: 384 │
│ │ │ │ │ embedding_model: all-MiniLM-L6-v2 │
│ my_demo_vector_db │ faiss │ my_demo_vector_db │ │ embedding_dimension: 768 │
│ │ │ │ │ embedding_model: nomic-embed-text-v1.5 │
│ │ │ │ │ type: vector_db │
│ │ │ │ │ │
└──────────────────────────┴─────────────┴──────────────────────────┴────────────────┴───────────────────────────────────┘
@ -244,8 +244,8 @@ Required arguments:
Optional arguments:
- `--provider-id`: Provider ID for the vector db
- `--provider-vector-db-id`: Provider's vector db ID
- `--embedding-model`: Embedding model to use. Default: `all-MiniLM-L6-v2`
- `--embedding-dimension`: Dimension of embeddings. Default: 384
- `--embedding-model`: Embedding model to use. Default: `nomic-embed-text-v1.5`
- `--embedding-dimension`: Dimension of embeddings. Default: 768
### `llama-stack-client vector_dbs unregister`
Delete a vector db

4
docs/getting_started.ipynb
View file

@ -1352,8 +1352,8 @@
"vector_db_id = f\"test-vector-db-{uuid.uuid4().hex}\"\n",
"client.vector_dbs.register(\n",
" vector_db_id=vector_db_id,\n",
" embedding_model=\"all-MiniLM-L6-v2\",\n",
" embedding_dimension=384,\n",
" embedding_model=\"nomic-embed-text-v1.5\",\n",
" embedding_dimension=768,\n",
")\n",
"client.tool_runtime.rag_tool.insert(\n",
" documents=documents,\n",

6
docs/notebooks/Llama_Stack_RAG_Lifecycle.ipynb
View file

@ -831,7 +831,7 @@
},
{
"cell_type": "code",
"execution_count": 23,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -860,8 +860,8 @@
"vector_db_id = f\"test_vector_db_{uuid.uuid4()}\"\n",
"client.vector_dbs.register(\n",
" vector_db_id=vector_db_id,\n",
" embedding_model=\"all-MiniLM-L6-v2\",\n",
" embedding_dimension=384,\n",
" embedding_model=\"nomic-embed-text-v1.5\",\n",
" embedding_dimension=768,\n",
" provider_id=selected_vector_provider.provider_id,\n",
")\n",
"\n",

54
docs/static/deprecated-llama-stack-spec.html vendored
View file

@ -1662,7 +1662,7 @@
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/OpenaiEmbeddingsRequest"
"$ref": "#/components/schemas/OpenAIEmbeddingsRequestWithExtraBody"
}
}
},
@ -2436,13 +2436,13 @@
"VectorIO"
],
"summary": "Creates a vector store.",
"description": "Creates a vector store.",
"description": "Creates a vector store.\nGenerate an OpenAI-compatible vector store with the given parameters.",
"parameters": [],
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/OpenaiCreateVectorStoreRequest"
"$ref": "#/components/schemas/OpenAICreateVectorStoreRequestWithExtraBody"
}
}
},
@ -2622,7 +2622,7 @@
"VectorIO"
],
"summary": "Create a vector store file batch.",
"description": "Create a vector store file batch.",
"description": "Create a vector store file batch.\nGenerate an OpenAI-compatible vector store file batch for the given vector store.",
"parameters": [
{
"name": "vector_store_id",
@ -2638,7 +2638,7 @@
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/OpenaiCreateVectorStoreFileBatchRequest"
"$ref": "#/components/schemas/OpenAICreateVectorStoreFileBatchRequestWithExtraBody"
}
}
},
@ -8174,7 +8174,7 @@
"title": "OpenAICompletionChoice",
"description": "A choice from an OpenAI-compatible completion response."
},
"OpenaiEmbeddingsRequest": {
"OpenAIEmbeddingsRequestWithExtraBody": {
"type": "object",
"properties": {
"model": {
@ -8197,6 +8197,7 @@
},
"encoding_format": {
"type": "string",
"default": "float",
"description": "(Optional) The format to return the embeddings in. Can be either \"float\" or \"base64\". Defaults to \"float\"."
},
"dimensions": {
@ -8213,7 +8214,8 @@
"model",
"input"
],
"title": "OpenaiEmbeddingsRequest"
"title": "OpenAIEmbeddingsRequestWithExtraBody",
"description": "Request parameters for OpenAI-compatible embeddings endpoint."
},
"OpenAIEmbeddingData": {
"type": "object",
@ -12061,19 +12063,19 @@
"title": "VectorStoreObject",
"description": "OpenAI Vector Store object."
},
"OpenaiCreateVectorStoreRequest": {
"OpenAICreateVectorStoreRequestWithExtraBody": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "A name for the vector store."
"description": "(Optional) 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."
"description": "List of file IDs to include in the vector store"
},
"expires_after": {
"type": "object",
@ -12099,7 +12101,7 @@
}
]
},
"description": "The expiration policy for a vector store."
"description": "(Optional) Expiration policy for the vector store"
},
"chunking_strategy": {
"type": "object",
@ -12125,7 +12127,7 @@
}
]
},
"description": "The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy."
"description": "(Optional) Strategy for splitting files into chunks"
},
"metadata": {
"type": "object",
@ -12151,23 +12153,12 @@
}
]
},
"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."
"description": "Set of key-value pairs that can be attached to the vector store"
}
},
"additionalProperties": false,
"title": "OpenaiCreateVectorStoreRequest"
"title": "OpenAICreateVectorStoreRequestWithExtraBody",
"description": "Request to create a vector store with extra_body support."
},
"OpenaiUpdateVectorStoreRequest": {
"type": "object",
@ -12337,7 +12328,7 @@
"title": "VectorStoreChunkingStrategyStaticConfig",
"description": "Configuration for static chunking strategy."
},
"OpenaiCreateVectorStoreFileBatchRequest": {
"OpenAICreateVectorStoreFileBatchRequestWithExtraBody": {
"type": "object",
"properties": {
"file_ids": {
@ -12345,7 +12336,7 @@
"items": {
"type": "string"
},
"description": "A list of File IDs that the vector store should use."
"description": "A list of File IDs that the vector store should use"
},
"attributes": {
"type": "object",
@ -12371,18 +12362,19 @@
}
]
},
"description": "(Optional) Key-value attributes to store with the files."
"description": "(Optional) Key-value attributes to store with the files"
},
"chunking_strategy": {
"$ref": "#/components/schemas/VectorStoreChunkingStrategy",
"description": "(Optional) The chunking strategy used to chunk the file(s). Defaults to auto."
"description": "(Optional) The chunking strategy used to chunk the file(s). Defaults to auto"
}
},
"additionalProperties": false,
"required": [
"file_ids"
],
"title": "OpenaiCreateVectorStoreFileBatchRequest"
"title": "OpenAICreateVectorStoreFileBatchRequestWithExtraBody",
"description": "Request to create a vector store file batch with extra_body support."
},
"VectorStoreFileBatchObject": {
"type": "object",

68
docs/static/deprecated-llama-stack-spec.yaml vendored
View file

@ -1203,7 +1203,7 @@ paths:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiEmbeddingsRequest'
$ref: '#/components/schemas/OpenAIEmbeddingsRequestWithExtraBody'
required: true
deprecated: true
/v1/openai/v1/files:
@ -1792,13 +1792,16 @@ paths:
tags:
- VectorIO
summary: Creates a vector store.
description: Creates a vector store.
description: >-
Creates a vector store.
Generate an OpenAI-compatible vector store with the given parameters.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiCreateVectorStoreRequest'
$ref: '#/components/schemas/OpenAICreateVectorStoreRequestWithExtraBody'
required: true
deprecated: true
/v1/openai/v1/vector_stores/{vector_store_id}:
@ -1924,7 +1927,11 @@ paths:
tags:
- VectorIO
summary: Create a vector store file batch.
description: Create a vector store file batch.
description: >-
Create a vector store file batch.
Generate an OpenAI-compatible vector store file batch for the given vector
store.
parameters:
- name: vector_store_id
in: path
@ -1937,7 +1944,7 @@ paths:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiCreateVectorStoreFileBatchRequest'
$ref: '#/components/schemas/OpenAICreateVectorStoreFileBatchRequestWithExtraBody'
required: true
deprecated: true
/v1/openai/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}:
@ -6035,7 +6042,7 @@ components:
title: OpenAICompletionChoice
description: >-
A choice from an OpenAI-compatible completion response.
OpenaiEmbeddingsRequest:
OpenAIEmbeddingsRequestWithExtraBody:
type: object
properties:
model:
@ -6054,6 +6061,7 @@ components:
multiple inputs in a single request, pass an array of strings.
encoding_format:
type: string
default: float
description: >-
(Optional) The format to return the embeddings in. Can be either "float"
or "base64". Defaults to "float".
@ -6071,7 +6079,9 @@ components:
required:
- model
- input
title: OpenaiEmbeddingsRequest
title: OpenAIEmbeddingsRequestWithExtraBody
description: >-
Request parameters for OpenAI-compatible embeddings endpoint.
OpenAIEmbeddingData:
type: object
properties:
@ -9147,19 +9157,18 @@ components:
- metadata
title: VectorStoreObject
description: OpenAI Vector Store object.
OpenaiCreateVectorStoreRequest:
"OpenAICreateVectorStoreRequestWithExtraBody":
type: object
properties:
name:
type: string
description: A name for the vector store.
description: (Optional) 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.
List of file IDs to include in the vector store
expires_after:
type: object
additionalProperties:
@ -9171,7 +9180,7 @@ components:
- type: array
- type: object
description: >-
The expiration policy for a vector store.
(Optional) Expiration policy for the vector store
chunking_strategy:
type: object
additionalProperties:
@ -9183,8 +9192,7 @@ components:
- type: array
- type: object
description: >-
The chunking strategy used to chunk the file(s). If not set, will use
the `auto` strategy.
(Optional) Strategy for splitting files into chunks
metadata:
type: object
additionalProperties:
@ -9196,21 +9204,12 @@ components:
- 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.
Set of key-value pairs that can be attached to the vector store
additionalProperties: false
title: OpenaiCreateVectorStoreRequest
title: >-
OpenAICreateVectorStoreRequestWithExtraBody
description: >-
Request to create a vector store with extra_body support.
OpenaiUpdateVectorStoreRequest:
type: object
properties:
@ -9331,7 +9330,7 @@ components:
title: VectorStoreChunkingStrategyStaticConfig
description: >-
Configuration for static chunking strategy.
OpenaiCreateVectorStoreFileBatchRequest:
"OpenAICreateVectorStoreFileBatchRequestWithExtraBody":
type: object
properties:
file_ids:
@ -9339,7 +9338,7 @@ components:
items:
type: string
description: >-
A list of File IDs that the vector store should use.
A list of File IDs that the vector store should use
attributes:
type: object
additionalProperties:
@ -9351,16 +9350,19 @@ components:
- type: array
- type: object
description: >-
(Optional) Key-value attributes to store with the files.
(Optional) Key-value attributes to store with the files
chunking_strategy:
$ref: '#/components/schemas/VectorStoreChunkingStrategy'
description: >-
(Optional) The chunking strategy used to chunk the file(s). Defaults to
auto.
auto
additionalProperties: false
required:
- file_ids
title: OpenaiCreateVectorStoreFileBatchRequest
title: >-
OpenAICreateVectorStoreFileBatchRequestWithExtraBody
description: >-
Request to create a vector store file batch with extra_body support.
VectorStoreFileBatchObject:
type: object
properties:

612
docs/static/llama-stack-spec.html vendored
View file

@ -765,7 +765,7 @@
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/OpenaiEmbeddingsRequest"
"$ref": "#/components/schemas/OpenAIEmbeddingsRequestWithExtraBody"
}
}
},
@ -3170,13 +3170,13 @@
"VectorIO"
],
"summary": "Creates a vector store.",
"description": "Creates a vector store.",
"description": "Creates a vector store.\nGenerate an OpenAI-compatible vector store with the given parameters.",
"parameters": [],
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/OpenaiCreateVectorStoreRequest"
"$ref": "#/components/schemas/OpenAICreateVectorStoreRequestWithExtraBody"
}
}
},
@ -3356,7 +3356,7 @@
"VectorIO"
],
"summary": "Create a vector store file batch.",
"description": "Create a vector store file batch.",
"description": "Create a vector store file batch.\nGenerate an OpenAI-compatible vector store file batch for the given vector store.",
"parameters": [
{
"name": "vector_store_id",
@ -3372,7 +3372,7 @@
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/OpenaiCreateVectorStoreFileBatchRequest"
"$ref": "#/components/schemas/OpenAICreateVectorStoreFileBatchRequestWithExtraBody"
}
}
},
@ -6324,7 +6324,7 @@
"title": "ConversationItemDeletedResource",
"description": "Response for deleted conversation item."
},
"OpenaiEmbeddingsRequest": {
"OpenAIEmbeddingsRequestWithExtraBody": {
"type": "object",
"properties": {
"model": {
@ -6347,6 +6347,7 @@
},
"encoding_format": {
"type": "string",
"default": "float",
"description": "(Optional) The format to return the embeddings in. Can be either \"float\" or \"base64\". Defaults to \"float\"."
},
"dimensions": {
@ -6363,7 +6364,8 @@
"model",
"input"
],
"title": "OpenaiEmbeddingsRequest"
"title": "OpenAIEmbeddingsRequestWithExtraBody",
"description": "Request parameters for OpenAI-compatible embeddings endpoint."
},
"OpenAIEmbeddingData": {
"type": "object",
@ -9816,284 +9818,6 @@
"title": "ListOpenAIResponseInputItem",
"description": "List container for OpenAI response input items."
},
"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."
},
"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"
},
{
"$ref": "#/components/schemas/TextContentItem"
}
],
"discriminator": {
"propertyName": "type",
"mapping": {
"image": "#/components/schemas/ImageContentItem",
"text": "#/components/schemas/TextContentItem"
}
}
},
"Message": {
"oneOf": [
{
"$ref": "#/components/schemas/UserMessage"
},
{
"$ref": "#/components/schemas/SystemMessage"
},
{
"$ref": "#/components/schemas/ToolResponseMessage"
},
{
"$ref": "#/components/schemas/CompletionMessage"
}
],
"discriminator": {
"propertyName": "role",
"mapping": {
"user": "#/components/schemas/UserMessage",
"system": "#/components/schemas/SystemMessage",
"tool": "#/components/schemas/ToolResponseMessage",
"assistant": "#/components/schemas/CompletionMessage"
}
}
},
"SystemMessage": {
"type": "object",
"properties": {
"role": {
"type": "string",
"const": "system",
"default": "system",
"description": "Must be \"system\" to identify this as a system message"
},
"content": {
"$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": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"call_id",
"tool_name",
"arguments"
],
"title": "ToolCall"
},
"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": {
"$ref": "#/components/schemas/InterleavedContent",
"description": "The response content from the tool"
}
},
"additionalProperties": false,
"required": [
"role",
"call_id",
"content"
],
"title": "ToolResponseMessage",
"description": "A message representing the result of a tool invocation."
},
"URL": {
"type": "object",
"properties": {
"uri": {
"type": "string",
"description": "The URL string pointing to the resource"
}
},
"additionalProperties": false,
"required": [
"uri"
],
"title": "URL",
"description": "A URL reference to external content."
},
"UserMessage": {
"type": "object",
"properties": {
"role": {
"type": "string",
"const": "user",
"default": "user",
"description": "Must be \"user\" to identify this as a user message"
},
"content": {
"$ref": "#/components/schemas/InterleavedContent",
"description": "The content of the message, which can include text and other media"
},
"context": {
"$ref": "#/components/schemas/InterleavedContent",
"description": "(Optional) This field is used internally by Llama Stack to pass RAG context. This field may be removed in the API in the future."
}
},
"additionalProperties": false,
"required": [
"role",
"content"
],
"title": "UserMessage",
"description": "A message from the user in a chat conversation."
},
"RunShieldRequest": {
"type": "object",
"properties": {
@ -10104,7 +9828,7 @@
"messages": {
"type": "array",
"items": {
"$ref": "#/components/schemas/Message"
"$ref": "#/components/schemas/OpenAIMessageParam"
},
"description": "The messages to run the shield on."
},
@ -11070,6 +10794,284 @@
],
"title": "RegisterShieldRequest"
},
"CompletionMessage": {
"type": "object",
"properties": {
"role": {
"type": "string",
"const": "assistant",
"default": "assistant",
"description": "Must be \"assistant\" to identify this as the model's response"
},
"content": {
"$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": {
"$ref": "#/components/schemas/ToolCall"
},
"description": "List of tool calls. Each tool call is a ToolCall object."
}
},
"additionalProperties": false,
"required": [
"role",
"content",
"stop_reason"
],
"title": "CompletionMessage",
"description": "A message containing the model's (assistant) response in a chat conversation."
},
"ImageContentItem": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "image",
"default": "image",
"description": "Discriminator type of the content item. Always \"image\""
},
"image": {
"type": "object",
"properties": {
"url": {
"$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"
}
}
},
"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"
}
}
},
"SystemMessage": {
"type": "object",
"properties": {
"role": {
"type": "string",
"const": "system",
"default": "system",
"description": "Must be \"system\" to identify this as a system message"
},
"content": {
"$ref": "#/components/schemas/InterleavedContent",
"description": "The content of the \"system prompt\". If multiple system messages are provided, they are concatenated. The underlying Llama Stack code may also add other system messages (for example, for formatting tool definitions)."
}
},
"additionalProperties": false,
"required": [
"role",
"content"
],
"title": "SystemMessage",
"description": "A system message providing instructions or context to the model."
},
"TextContentItem": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "text",
"default": "text",
"description": "Discriminator type of the content item. Always \"text\""
},
"text": {
"type": "string",
"description": "Text content"
}
},
"additionalProperties": false,
"required": [
"type",
"text"
],
"title": "TextContentItem",
"description": "A text content item"
},
"ToolCall": {
"type": "object",
"properties": {
"call_id": {
"type": "string"
},
"tool_name": {
"oneOf": [
{
"type": "string",
"enum": [
"brave_search",
"wolfram_alpha",
"photogen",
"code_interpreter"
],
"title": "BuiltinTool"
},
{
"type": "string"
}
]
},
"arguments": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"call_id",
"tool_name",
"arguments"
],
"title": "ToolCall"
},
"ToolResponseMessage": {
"type": "object",
"properties": {
"role": {
"type": "string",
"const": "tool",
"default": "tool",
"description": "Must be \"tool\" to identify this as a tool response"
},
"call_id": {
"type": "string",
"description": "Unique identifier for the tool call this response is for"
},
"content": {
"$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."
},
"URL": {
"type": "object",
"properties": {
"uri": {
"type": "string",
"description": "The URL string pointing to the resource"
}
},
"additionalProperties": false,
"required": [
"uri"
],
"title": "URL",
"description": "A URL reference to external content."
},
"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."
},
"SyntheticDataGenerateRequest": {
"type": "object",
"properties": {
@ -12587,19 +12589,19 @@
"title": "VectorStoreObject",
"description": "OpenAI Vector Store object."
},
"OpenaiCreateVectorStoreRequest": {
"OpenAICreateVectorStoreRequestWithExtraBody": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "A name for the vector store."
"description": "(Optional) 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."
"description": "List of file IDs to include in the vector store"
},
"expires_after": {
"type": "object",
@ -12625,7 +12627,7 @@
}
]
},
"description": "The expiration policy for a vector store."
"description": "(Optional) Expiration policy for the vector store"
},
"chunking_strategy": {
"type": "object",
@ -12651,7 +12653,7 @@
}
]
},
"description": "The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy."
"description": "(Optional) Strategy for splitting files into chunks"
},
"metadata": {
"type": "object",
@ -12677,23 +12679,12 @@
}
]
},
"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."
"description": "Set of key-value pairs that can be attached to the vector store"
}
},
"additionalProperties": false,
"title": "OpenaiCreateVectorStoreRequest"
"title": "OpenAICreateVectorStoreRequestWithExtraBody",
"description": "Request to create a vector store with extra_body support."
},
"OpenaiUpdateVectorStoreRequest": {
"type": "object",
@ -12863,7 +12854,7 @@
"title": "VectorStoreChunkingStrategyStaticConfig",
"description": "Configuration for static chunking strategy."
},
"OpenaiCreateVectorStoreFileBatchRequest": {
"OpenAICreateVectorStoreFileBatchRequestWithExtraBody": {
"type": "object",
"properties": {
"file_ids": {
@ -12871,7 +12862,7 @@
"items": {
"type": "string"
},
"description": "A list of File IDs that the vector store should use."
"description": "A list of File IDs that the vector store should use"
},
"attributes": {
"type": "object",
@ -12897,18 +12888,19 @@
}
]
},
"description": "(Optional) Key-value attributes to store with the files."
"description": "(Optional) Key-value attributes to store with the files"
},
"chunking_strategy": {
"$ref": "#/components/schemas/VectorStoreChunkingStrategy",
"description": "(Optional) The chunking strategy used to chunk the file(s). Defaults to auto."
"description": "(Optional) The chunking strategy used to chunk the file(s). Defaults to auto"
}
},
"additionalProperties": false,
"required": [
"file_ids"
],
"title": "OpenaiCreateVectorStoreFileBatchRequest"
"title": "OpenAICreateVectorStoreFileBatchRequestWithExtraBody",
"description": "Request to create a vector store file batch with extra_body support."
},
"VectorStoreFileBatchObject": {
"type": "object",

512
docs/static/llama-stack-spec.yaml vendored
View file

@ -617,7 +617,7 @@ paths:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiEmbeddingsRequest'
$ref: '#/components/schemas/OpenAIEmbeddingsRequestWithExtraBody'
required: true
deprecated: false
/v1/files:
@ -2413,13 +2413,16 @@ paths:
tags:
- VectorIO
summary: Creates a vector store.
description: Creates a vector store.
description: >-
Creates a vector store.
Generate an OpenAI-compatible vector store with the given parameters.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiCreateVectorStoreRequest'
$ref: '#/components/schemas/OpenAICreateVectorStoreRequestWithExtraBody'
required: true
deprecated: false
/v1/vector_stores/{vector_store_id}:
@ -2545,7 +2548,11 @@ paths:
tags:
- VectorIO
summary: Create a vector store file batch.
description: Create a vector store file batch.
description: >-
Create a vector store file batch.
Generate an OpenAI-compatible vector store file batch for the given vector
store.
parameters:
- name: vector_store_id
in: path
@ -2558,7 +2565,7 @@ paths:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiCreateVectorStoreFileBatchRequest'
$ref: '#/components/schemas/OpenAICreateVectorStoreFileBatchRequestWithExtraBody'
required: true
deprecated: false
/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}:
@ -4797,7 +4804,7 @@ components:
- deleted
title: ConversationItemDeletedResource
description: Response for deleted conversation item.
OpenaiEmbeddingsRequest:
OpenAIEmbeddingsRequestWithExtraBody:
type: object
properties:
model:
@ -4816,6 +4823,7 @@ components:
multiple inputs in a single request, pass an array of strings.
encoding_format:
type: string
default: float
description: >-
(Optional) The format to return the embeddings in. Can be either "float"
or "base64". Defaults to "float".
@ -4833,7 +4841,9 @@ components:
required:
- model
- input
title: OpenaiEmbeddingsRequest
title: OpenAIEmbeddingsRequestWithExtraBody
description: >-
Request parameters for OpenAI-compatible embeddings endpoint.
OpenAIEmbeddingData:
type: object
properties:
@ -7591,227 +7601,6 @@ components:
title: ListOpenAIResponseInputItem
description: >-
List container for OpenAI response input items.
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.
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'
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'
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:
type: string
additionalProperties: false
required:
- call_id
- tool_name
- arguments
title: ToolCall
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.
URL:
type: object
properties:
uri:
type: string
description: The URL string pointing to the resource
additionalProperties: false
required:
- uri
title: URL
description: A URL reference to external content.
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.
RunShieldRequest:
type: object
properties:
@ -7821,7 +7610,7 @@ components:
messages:
type: array
items:
$ref: '#/components/schemas/Message'
$ref: '#/components/schemas/OpenAIMessageParam'
description: The messages to run the shield on.
params:
type: object
@ -8488,6 +8277,227 @@ components:
required:
- shield_id
title: RegisterShieldRequest
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.
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'
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'
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:
type: string
additionalProperties: false
required:
- call_id
- tool_name
- arguments
title: ToolCall
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.
URL:
type: object
properties:
uri:
type: string
description: The URL string pointing to the resource
additionalProperties: false
required:
- uri
title: URL
description: A URL reference to external content.
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.
SyntheticDataGenerateRequest:
type: object
properties:
@ -9612,19 +9622,18 @@ components:
- metadata
title: VectorStoreObject
description: OpenAI Vector Store object.
OpenaiCreateVectorStoreRequest:
"OpenAICreateVectorStoreRequestWithExtraBody":
type: object
properties:
name:
type: string
description: A name for the vector store.
description: (Optional) 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.
List of file IDs to include in the vector store
expires_after:
type: object
additionalProperties:
@ -9636,7 +9645,7 @@ components:
- type: array
- type: object
description: >-
The expiration policy for a vector store.
(Optional) Expiration policy for the vector store
chunking_strategy:
type: object
additionalProperties:
@ -9648,8 +9657,7 @@ components:
- type: array
- type: object
description: >-
The chunking strategy used to chunk the file(s). If not set, will use
the `auto` strategy.
(Optional) Strategy for splitting files into chunks
metadata:
type: object
additionalProperties:
@ -9661,21 +9669,12 @@ components:
- 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.
Set of key-value pairs that can be attached to the vector store
additionalProperties: false
title: OpenaiCreateVectorStoreRequest
title: >-
OpenAICreateVectorStoreRequestWithExtraBody
description: >-
Request to create a vector store with extra_body support.
OpenaiUpdateVectorStoreRequest:
type: object
properties:
@ -9796,7 +9795,7 @@ components:
title: VectorStoreChunkingStrategyStaticConfig
description: >-
Configuration for static chunking strategy.
OpenaiCreateVectorStoreFileBatchRequest:
"OpenAICreateVectorStoreFileBatchRequestWithExtraBody":
type: object
properties:
file_ids:
@ -9804,7 +9803,7 @@ components:
items:
type: string
description: >-
A list of File IDs that the vector store should use.
A list of File IDs that the vector store should use
attributes:
type: object
additionalProperties:
@ -9816,16 +9815,19 @@ components:
- type: array
- type: object
description: >-
(Optional) Key-value attributes to store with the files.
(Optional) Key-value attributes to store with the files
chunking_strategy:
$ref: '#/components/schemas/VectorStoreChunkingStrategy'
description: >-
(Optional) The chunking strategy used to chunk the file(s). Defaults to
auto.
auto
additionalProperties: false
required:
- file_ids
title: OpenaiCreateVectorStoreFileBatchRequest
title: >-
OpenAICreateVectorStoreFileBatchRequestWithExtraBody
description: >-
Request to create a vector store file batch with extra_body support.
VectorStoreFileBatchObject:
type: object
properties:

612
docs/static/stainless-llama-stack-spec.html vendored
View file

@ -765,7 +765,7 @@
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/OpenaiEmbeddingsRequest"
"$ref": "#/components/schemas/OpenAIEmbeddingsRequestWithExtraBody"
}
}
},
@ -3170,13 +3170,13 @@
"VectorIO"
],
"summary": "Creates a vector store.",
"description": "Creates a vector store.",
"description": "Creates a vector store.\nGenerate an OpenAI-compatible vector store with the given parameters.",
"parameters": [],
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/OpenaiCreateVectorStoreRequest"
"$ref": "#/components/schemas/OpenAICreateVectorStoreRequestWithExtraBody"
}
}
},
@ -3356,7 +3356,7 @@
"VectorIO"
],
"summary": "Create a vector store file batch.",
"description": "Create a vector store file batch.",
"description": "Create a vector store file batch.\nGenerate an OpenAI-compatible vector store file batch for the given vector store.",
"parameters": [
{
"name": "vector_store_id",
@ -3372,7 +3372,7 @@
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/OpenaiCreateVectorStoreFileBatchRequest"
"$ref": "#/components/schemas/OpenAICreateVectorStoreFileBatchRequestWithExtraBody"
}
}
},
@ -8333,7 +8333,7 @@
"title": "ConversationItemDeletedResource",
"description": "Response for deleted conversation item."
},
"OpenaiEmbeddingsRequest": {
"OpenAIEmbeddingsRequestWithExtraBody": {
"type": "object",
"properties": {
"model": {
@ -8356,6 +8356,7 @@
},
"encoding_format": {
"type": "string",
"default": "float",
"description": "(Optional) The format to return the embeddings in. Can be either \"float\" or \"base64\". Defaults to \"float\"."
},
"dimensions": {
@ -8372,7 +8373,8 @@
"model",
"input"
],
"title": "OpenaiEmbeddingsRequest"
"title": "OpenAIEmbeddingsRequestWithExtraBody",
"description": "Request parameters for OpenAI-compatible embeddings endpoint."
},
"OpenAIEmbeddingData": {
"type": "object",
@ -11825,284 +11827,6 @@
"title": "ListOpenAIResponseInputItem",
"description": "List container for OpenAI response input items."
},
"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."
},
"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"
},
{
"$ref": "#/components/schemas/TextContentItem"
}
],
"discriminator": {
"propertyName": "type",
"mapping": {
"image": "#/components/schemas/ImageContentItem",
"text": "#/components/schemas/TextContentItem"
}
}
},
"Message": {
"oneOf": [
{
"$ref": "#/components/schemas/UserMessage"
},
{
"$ref": "#/components/schemas/SystemMessage"
},
{
"$ref": "#/components/schemas/ToolResponseMessage"
},
{
"$ref": "#/components/schemas/CompletionMessage"
}
],
"discriminator": {
"propertyName": "role",
"mapping": {
"user": "#/components/schemas/UserMessage",
"system": "#/components/schemas/SystemMessage",
"tool": "#/components/schemas/ToolResponseMessage",
"assistant": "#/components/schemas/CompletionMessage"
}
}
},
"SystemMessage": {
"type": "object",
"properties": {
"role": {
"type": "string",
"const": "system",
"default": "system",
"description": "Must be \"system\" to identify this as a system message"
},
"content": {
"$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": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"call_id",
"tool_name",
"arguments"
],
"title": "ToolCall"
},
"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": {
"$ref": "#/components/schemas/InterleavedContent",
"description": "The response content from the tool"
}
},
"additionalProperties": false,
"required": [
"role",
"call_id",
"content"
],
"title": "ToolResponseMessage",
"description": "A message representing the result of a tool invocation."
},
"URL": {
"type": "object",
"properties": {
"uri": {
"type": "string",
"description": "The URL string pointing to the resource"
}
},
"additionalProperties": false,
"required": [
"uri"
],
"title": "URL",
"description": "A URL reference to external content."
},
"UserMessage": {
"type": "object",
"properties": {
"role": {
"type": "string",
"const": "user",
"default": "user",
"description": "Must be \"user\" to identify this as a user message"
},
"content": {
"$ref": "#/components/schemas/InterleavedContent",
"description": "The content of the message, which can include text and other media"
},
"context": {
"$ref": "#/components/schemas/InterleavedContent",
"description": "(Optional) This field is used internally by Llama Stack to pass RAG context. This field may be removed in the API in the future."
}
},
"additionalProperties": false,
"required": [
"role",
"content"
],
"title": "UserMessage",
"description": "A message from the user in a chat conversation."
},
"RunShieldRequest": {
"type": "object",
"properties": {
@ -12113,7 +11837,7 @@
"messages": {
"type": "array",
"items": {
"$ref": "#/components/schemas/Message"
"$ref": "#/components/schemas/OpenAIMessageParam"
},
"description": "The messages to run the shield on."
},
@ -13079,6 +12803,284 @@
],
"title": "RegisterShieldRequest"
},
"CompletionMessage": {
"type": "object",
"properties": {
"role": {
"type": "string",
"const": "assistant",
"default": "assistant",
"description": "Must be \"assistant\" to identify this as the model's response"
},
"content": {
"$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": {
"$ref": "#/components/schemas/ToolCall"
},
"description": "List of tool calls. Each tool call is a ToolCall object."
}
},
"additionalProperties": false,
"required": [
"role",
"content",
"stop_reason"
],
"title": "CompletionMessage",
"description": "A message containing the model's (assistant) response in a chat conversation."
},
"ImageContentItem": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "image",
"default": "image",
"description": "Discriminator type of the content item. Always \"image\""
},
"image": {
"type": "object",
"properties": {
"url": {
"$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"
}
}
},
"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"
}
}
},
"SystemMessage": {
"type": "object",
"properties": {
"role": {
"type": "string",
"const": "system",
"default": "system",
"description": "Must be \"system\" to identify this as a system message"
},
"content": {
"$ref": "#/components/schemas/InterleavedContent",
"description": "The content of the \"system prompt\". If multiple system messages are provided, they are concatenated. The underlying Llama Stack code may also add other system messages (for example, for formatting tool definitions)."
}
},
"additionalProperties": false,
"required": [
"role",
"content"
],
"title": "SystemMessage",
"description": "A system message providing instructions or context to the model."
},
"TextContentItem": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "text",
"default": "text",
"description": "Discriminator type of the content item. Always \"text\""
},
"text": {
"type": "string",
"description": "Text content"
}
},
"additionalProperties": false,
"required": [
"type",
"text"
],
"title": "TextContentItem",
"description": "A text content item"
},
"ToolCall": {
"type": "object",
"properties": {
"call_id": {
"type": "string"
},
"tool_name": {
"oneOf": [
{
"type": "string",
"enum": [
"brave_search",
"wolfram_alpha",
"photogen",
"code_interpreter"
],
"title": "BuiltinTool"
},
{
"type": "string"
}
]
},
"arguments": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"call_id",
"tool_name",
"arguments"
],
"title": "ToolCall"
},
"ToolResponseMessage": {
"type": "object",
"properties": {
"role": {
"type": "string",
"const": "tool",
"default": "tool",
"description": "Must be \"tool\" to identify this as a tool response"
},
"call_id": {
"type": "string",
"description": "Unique identifier for the tool call this response is for"
},
"content": {
"$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."
},
"URL": {
"type": "object",
"properties": {
"uri": {
"type": "string",
"description": "The URL string pointing to the resource"
}
},
"additionalProperties": false,
"required": [
"uri"
],
"title": "URL",
"description": "A URL reference to external content."
},
"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."
},
"SyntheticDataGenerateRequest": {
"type": "object",
"properties": {
@ -14596,19 +14598,19 @@
"title": "VectorStoreObject",
"description": "OpenAI Vector Store object."
},
"OpenaiCreateVectorStoreRequest": {
"OpenAICreateVectorStoreRequestWithExtraBody": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "A name for the vector store."
"description": "(Optional) 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."
"description": "List of file IDs to include in the vector store"
},
"expires_after": {
"type": "object",
@ -14634,7 +14636,7 @@
}
]
},
"description": "The expiration policy for a vector store."
"description": "(Optional) Expiration policy for the vector store"
},
"chunking_strategy": {
"type": "object",
@ -14660,7 +14662,7 @@
}
]
},
"description": "The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy."
"description": "(Optional) Strategy for splitting files into chunks"
},
"metadata": {
"type": "object",
@ -14686,23 +14688,12 @@
}
]
},
"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."
"description": "Set of key-value pairs that can be attached to the vector store"
}
},
"additionalProperties": false,
"title": "OpenaiCreateVectorStoreRequest"
"title": "OpenAICreateVectorStoreRequestWithExtraBody",
"description": "Request to create a vector store with extra_body support."
},
"OpenaiUpdateVectorStoreRequest": {
"type": "object",
@ -14872,7 +14863,7 @@
"title": "VectorStoreChunkingStrategyStaticConfig",
"description": "Configuration for static chunking strategy."
},
"OpenaiCreateVectorStoreFileBatchRequest": {
"OpenAICreateVectorStoreFileBatchRequestWithExtraBody": {
"type": "object",
"properties": {
"file_ids": {
@ -14880,7 +14871,7 @@
"items": {
"type": "string"
},
"description": "A list of File IDs that the vector store should use."
"description": "A list of File IDs that the vector store should use"
},
"attributes": {
"type": "object",
@ -14906,18 +14897,19 @@
}
]
},
"description": "(Optional) Key-value attributes to store with the files."
"description": "(Optional) Key-value attributes to store with the files"
},
"chunking_strategy": {
"$ref": "#/components/schemas/VectorStoreChunkingStrategy",
"description": "(Optional) The chunking strategy used to chunk the file(s). Defaults to auto."
"description": "(Optional) The chunking strategy used to chunk the file(s). Defaults to auto"
}
},
"additionalProperties": false,
"required": [
"file_ids"
],
"title": "OpenaiCreateVectorStoreFileBatchRequest"
"title": "OpenAICreateVectorStoreFileBatchRequestWithExtraBody",
"description": "Request to create a vector store file batch with extra_body support."
},
"VectorStoreFileBatchObject": {
"type": "object",

512
docs/static/stainless-llama-stack-spec.yaml vendored
View file

@ -620,7 +620,7 @@ paths:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiEmbeddingsRequest'
$ref: '#/components/schemas/OpenAIEmbeddingsRequestWithExtraBody'
required: true
deprecated: false
/v1/files:
@ -2416,13 +2416,16 @@ paths:
tags:
- VectorIO
summary: Creates a vector store.
description: Creates a vector store.
description: >-
Creates a vector store.
Generate an OpenAI-compatible vector store with the given parameters.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiCreateVectorStoreRequest'
$ref: '#/components/schemas/OpenAICreateVectorStoreRequestWithExtraBody'
required: true
deprecated: false
/v1/vector_stores/{vector_store_id}:
@ -2548,7 +2551,11 @@ paths:
tags:
- VectorIO
summary: Create a vector store file batch.
description: Create a vector store file batch.
description: >-
Create a vector store file batch.
Generate an OpenAI-compatible vector store file batch for the given vector
store.
parameters:
- name: vector_store_id
in: path
@ -2561,7 +2568,7 @@ paths:
content:
application/json:
schema:
$ref: '#/components/schemas/OpenaiCreateVectorStoreFileBatchRequest'
$ref: '#/components/schemas/OpenAICreateVectorStoreFileBatchRequestWithExtraBody'
required: true
deprecated: false
/v1/vector_stores/{vector_store_id}/file_batches/{batch_id}:
@ -6242,7 +6249,7 @@ components:
- deleted
title: ConversationItemDeletedResource
description: Response for deleted conversation item.
OpenaiEmbeddingsRequest:
OpenAIEmbeddingsRequestWithExtraBody:
type: object
properties:
model:
@ -6261,6 +6268,7 @@ components:
multiple inputs in a single request, pass an array of strings.
encoding_format:
type: string
default: float
description: >-
(Optional) The format to return the embeddings in. Can be either "float"
or "base64". Defaults to "float".
@ -6278,7 +6286,9 @@ components:
required:
- model
- input
title: OpenaiEmbeddingsRequest
title: OpenAIEmbeddingsRequestWithExtraBody
description: >-
Request parameters for OpenAI-compatible embeddings endpoint.
OpenAIEmbeddingData:
type: object
properties:
@ -9036,227 +9046,6 @@ components:
title: ListOpenAIResponseInputItem
description: >-
List container for OpenAI response input items.
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.
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'
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'
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:
type: string
additionalProperties: false
required:
- call_id
- tool_name
- arguments
title: ToolCall
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.
URL:
type: object
properties:
uri:
type: string
description: The URL string pointing to the resource
additionalProperties: false
required:
- uri
title: URL
description: A URL reference to external content.
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.
RunShieldRequest:
type: object
properties:
@ -9266,7 +9055,7 @@ components:
messages:
type: array
items:
$ref: '#/components/schemas/Message'
$ref: '#/components/schemas/OpenAIMessageParam'
description: The messages to run the shield on.
params:
type: object
@ -9933,6 +9722,227 @@ components:
required:
- shield_id
title: RegisterShieldRequest
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.
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'
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'
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:
type: string
additionalProperties: false
required:
- call_id
- tool_name
- arguments
title: ToolCall
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.
URL:
type: object
properties:
uri:
type: string
description: The URL string pointing to the resource
additionalProperties: false
required:
- uri
title: URL
description: A URL reference to external content.
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.
SyntheticDataGenerateRequest:
type: object
properties:
@ -11057,19 +11067,18 @@ components:
- metadata
title: VectorStoreObject
description: OpenAI Vector Store object.
OpenaiCreateVectorStoreRequest:
"OpenAICreateVectorStoreRequestWithExtraBody":
type: object
properties:
name:
type: string
description: A name for the vector store.
description: (Optional) 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.
List of file IDs to include in the vector store
expires_after:
type: object
additionalProperties:
@ -11081,7 +11090,7 @@ components:
- type: array
- type: object
description: >-
The expiration policy for a vector store.
(Optional) Expiration policy for the vector store
chunking_strategy:
type: object
additionalProperties:
@ -11093,8 +11102,7 @@ components:
- type: array
- type: object
description: >-
The chunking strategy used to chunk the file(s). If not set, will use
the `auto` strategy.
(Optional) Strategy for splitting files into chunks
metadata:
type: object
additionalProperties:
@ -11106,21 +11114,12 @@ components:
- 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.
Set of key-value pairs that can be attached to the vector store
additionalProperties: false
title: OpenaiCreateVectorStoreRequest
title: >-
OpenAICreateVectorStoreRequestWithExtraBody
description: >-
Request to create a vector store with extra_body support.
OpenaiUpdateVectorStoreRequest:
type: object
properties:
@ -11241,7 +11240,7 @@ components:
title: VectorStoreChunkingStrategyStaticConfig
description: >-
Configuration for static chunking strategy.
OpenaiCreateVectorStoreFileBatchRequest:
"OpenAICreateVectorStoreFileBatchRequestWithExtraBody":
type: object
properties:
file_ids:
@ -11249,7 +11248,7 @@ components:
items:
type: string
description: >-
A list of File IDs that the vector store should use.
A list of File IDs that the vector store should use
attributes:
type: object
additionalProperties:
@ -11261,16 +11260,19 @@ components:
- type: array
- type: object
description: >-
(Optional) Key-value attributes to store with the files.
(Optional) Key-value attributes to store with the files
chunking_strategy:
$ref: '#/components/schemas/VectorStoreChunkingStrategy'
description: >-
(Optional) The chunking strategy used to chunk the file(s). Defaults to
auto.
auto
additionalProperties: false
required:
- file_ids
title: OpenaiCreateVectorStoreFileBatchRequest
title: >-
OpenAICreateVectorStoreFileBatchRequestWithExtraBody
description: >-
Request to create a vector store file batch with extra_body support.
VectorStoreFileBatchObject:
type: object
properties:

5
docs/zero_to_hero_guide/05_Memory101.ipynb
View file

@ -161,6 +161,7 @@
{
"cell_type": "code",
"execution_count": null,
"id": "4ad70258",
"metadata": {},
"outputs": [],
"source": [
@ -180,8 +181,8 @@
"# Create a vector database with optimized settings for general use\n",
"client.vector_dbs.register(\n",
" vector_db_id=VECTOR_DB_ID,\n",
" embedding_model=\"all-MiniLM-L6-v2\",\n",
" embedding_dimension=384, # This is the dimension for all-MiniLM-L6-v2\n",
" embedding_model=\"nomic-embed-text-v1.5\",\n",
" embedding_dimension=768, # This is the dimension for nomic-embed-text-v1.5\n",
" provider_id=provider_id,\n",
")"
]