Merge branch 'main' into add-mcp-authentication-param

This commit is contained in:
Omar Abdelwahab 2025-11-12 14:55:23 -08:00 committed by GitHub
commit 607e3cc05c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
44 changed files with 1899 additions and 464 deletions

View file

@ -221,7 +221,15 @@ models:
```
A Model is an instance of a "Resource" (see [Concepts](../concepts/)) and is associated with a specific inference provider (in this case, the provider with identifier `ollama`). This is an instance of a "pre-registered" model. While we always encourage the clients to register models before using them, some Stack servers may come up a list of "already known and available" models.
What's with the `provider_model_id` field? This is an identifier for the model inside the provider's model catalog. Contrast it with `model_id` which is the identifier for the same model for Llama Stack's purposes. For example, you may want to name "llama3.2:vision-11b" as "image_captioning_model" when you use it in your Stack interactions. When omitted, the server will set `provider_model_id` to be the same as `model_id`.
What's with the `provider_model_id` field? This is an identifier for the model inside the provider's model catalog. The `model_id` field is provided for configuration purposes but is not used as part of the model identifier.
**Important:** Models are identified as `provider_id/provider_model_id` in the system and when making API calls. When `provider_model_id` is omitted, the server will set it to be the same as `model_id`.
Examples:
- Config: `model_id: llama3.2`, `provider_id: ollama`, `provider_model_id: null`
→ Access as: `ollama/llama3.2`
- Config: `model_id: my-llama`, `provider_id: vllm-inference`, `provider_model_id: llama-3-2-3b`
→ Access as: `vllm-inference/llama-3-2-3b` (the `model_id` is not used in the identifier)
If you need to conditionally register a model in the configuration, such as only when specific environment variable(s) are set, this can be accomplished by utilizing a special `__disabled__` string as the default value of an environment variable substitution, as shown below:

View file

@ -2688,7 +2688,8 @@ paths:
responses:
'200':
description: >-
A VectorStoreFileContentResponse representing the file contents.
File contents, optionally with embeddings and metadata based on query
parameters.
content:
application/json:
schema:
@ -2723,6 +2724,20 @@ paths:
required: true
schema:
type: string
- name: include_embeddings
in: query
description: >-
Whether to include embedding vectors in the response.
required: false
schema:
$ref: '#/components/schemas/bool'
- name: include_metadata
in: query
description: >-
Whether to include chunk metadata in the response.
required: false
schema:
$ref: '#/components/schemas/bool'
deprecated: false
/v1/vector_stores/{vector_store_id}/search:
post:
@ -9379,6 +9394,8 @@ components:
title: VectorStoreFileDeleteResponse
description: >-
Response from deleting a vector store file.
bool:
type: boolean
VectorStoreContent:
type: object
properties:
@ -9390,6 +9407,26 @@ components:
text:
type: string
description: The actual text content
embedding:
type: array
items:
type: number
description: >-
Optional embedding vector for this content chunk
chunk_metadata:
$ref: '#/components/schemas/ChunkMetadata'
description: Optional chunk metadata
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: Optional user-defined metadata
additionalProperties: false
required:
- type
@ -9413,6 +9450,7 @@ components:
description: Parsed content of the file
has_more:
type: boolean
default: false
description: >-
Indicates if there are more content pages to fetch
next_page:

View file

@ -2691,7 +2691,8 @@ paths:
responses:
'200':
description: >-
A VectorStoreFileContentResponse representing the file contents.
File contents, optionally with embeddings and metadata based on query
parameters.
content:
application/json:
schema:
@ -2726,6 +2727,20 @@ paths:
required: true
schema:
type: string
- name: include_embeddings
in: query
description: >-
Whether to include embedding vectors in the response.
required: false
schema:
$ref: '#/components/schemas/bool'
- name: include_metadata
in: query
description: >-
Whether to include chunk metadata in the response.
required: false
schema:
$ref: '#/components/schemas/bool'
deprecated: false
/v1/vector_stores/{vector_store_id}/search:
post:
@ -10095,6 +10110,8 @@ components:
title: VectorStoreFileDeleteResponse
description: >-
Response from deleting a vector store file.
bool:
type: boolean
VectorStoreContent:
type: object
properties:
@ -10106,6 +10123,26 @@ components:
text:
type: string
description: The actual text content
embedding:
type: array
items:
type: number
description: >-
Optional embedding vector for this content chunk
chunk_metadata:
$ref: '#/components/schemas/ChunkMetadata'
description: Optional chunk metadata
metadata:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
description: Optional user-defined metadata
additionalProperties: false
required:
- type
@ -10129,6 +10166,7 @@ components:
description: Parsed content of the file
has_more:
type: boolean
default: false
description: >-
Indicates if there are more content pages to fetch
next_page: