mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
chore(api): remove deprecated embeddings impls
This commit is contained in:
Matthew Farrellee
parent
478b4ff1e6
commit
30998fd1ff
20 changed files with 3 additions and 927 deletions
117
docs/_static/llama-stack-spec.html
vendored
117
docs/_static/llama-stack-spec.html
vendored
|
|
@ -901,49 +901,6 @@
|
|||
]
|
||||
}
|
||||
},
|
||||
"/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": {
|
||||
|
|
@ -9698,80 +9655,6 @@
|
|||
"title": "OpenAIDeleteResponseObject",
|
||||
"description": "Response object confirming deletion of an OpenAI response."
|
||||
},
|
||||
"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": {
|
||||
|
|
|
|||
99
docs/_static/llama-stack-spec.yaml
vendored
99
docs/_static/llama-stack-spec.yaml
vendored
|
|
@ -616,39 +616,6 @@ paths:
|
|||
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:
|
||||
|
|
@ -7173,72 +7140,6 @@ components:
|
|||
title: OpenAIDeleteResponseObject
|
||||
description: >-
|
||||
Response object confirming deletion of an OpenAI response.
|
||||
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:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue