mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-09 13:14:39 +00:00
Merge branch 'main' into content-extension
This commit is contained in:
Francisco Arceo
GitHub
commit
3e11e1472c
334 changed files with 22841 additions and 8940 deletions
281
docs/_static/llama-stack-spec.html
vendored
281
docs/_static/llama-stack-spec.html
vendored
|
|
@ -4605,6 +4605,49 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"/v1/inference/rerank": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "RerankResponse with indices sorted by relevance score (descending).",
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/RerankResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"$ref": "#/components/responses/BadRequest400"
|
||||
},
|
||||
"429": {
|
||||
"$ref": "#/components/responses/TooManyRequests429"
|
||||
},
|
||||
"500": {
|
||||
"$ref": "#/components/responses/InternalServerError500"
|
||||
},
|
||||
"default": {
|
||||
"$ref": "#/components/responses/DefaultError"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Inference"
|
||||
],
|
||||
"description": "Rerank a list of documents based on their relevance to a query.",
|
||||
"parameters": [],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/RerankRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"/v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/resume": {
|
||||
"post": {
|
||||
"responses": {
|
||||
|
|
@ -8821,6 +8864,61 @@
|
|||
"title": "OpenAIResponseOutputMessageMCPListTools",
|
||||
"description": "MCP list tools output message containing available tools from an MCP server."
|
||||
},
|
||||
"OpenAIResponseContentPart": {
|
||||
"oneOf": [
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseContentPartOutputText"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseContentPartRefusal"
|
||||
}
|
||||
],
|
||||
"discriminator": {
|
||||
"propertyName": "type",
|
||||
"mapping": {
|
||||
"output_text": "#/components/schemas/OpenAIResponseContentPartOutputText",
|
||||
"refusal": "#/components/schemas/OpenAIResponseContentPartRefusal"
|
||||
}
|
||||
}
|
||||
},
|
||||
"OpenAIResponseContentPartOutputText": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"type": {
|
||||
"type": "string",
|
||||
"const": "output_text",
|
||||
"default": "output_text"
|
||||
},
|
||||
"text": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"type",
|
||||
"text"
|
||||
],
|
||||
"title": "OpenAIResponseContentPartOutputText"
|
||||
},
|
||||
"OpenAIResponseContentPartRefusal": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"type": {
|
||||
"type": "string",
|
||||
"const": "refusal",
|
||||
"default": "refusal"
|
||||
},
|
||||
"refusal": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"type",
|
||||
"refusal"
|
||||
],
|
||||
"title": "OpenAIResponseContentPartRefusal"
|
||||
},
|
||||
"OpenAIResponseObjectStream": {
|
||||
"oneOf": [
|
||||
{
|
||||
|
|
@ -8877,6 +8975,12 @@
|
|||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallCompleted"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseObjectStreamResponseContentPartAdded"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseObjectStreamResponseContentPartDone"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIResponseObjectStreamResponseCompleted"
|
||||
}
|
||||
|
|
@ -8902,6 +9006,8 @@
|
|||
"response.mcp_call.in_progress": "#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallInProgress",
|
||||
"response.mcp_call.failed": "#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallFailed",
|
||||
"response.mcp_call.completed": "#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallCompleted",
|
||||
"response.content_part.added": "#/components/schemas/OpenAIResponseObjectStreamResponseContentPartAdded",
|
||||
"response.content_part.done": "#/components/schemas/OpenAIResponseObjectStreamResponseContentPartDone",
|
||||
"response.completed": "#/components/schemas/OpenAIResponseObjectStreamResponseCompleted"
|
||||
}
|
||||
}
|
||||
|
|
@ -8928,6 +9034,80 @@
|
|||
"title": "OpenAIResponseObjectStreamResponseCompleted",
|
||||
"description": "Streaming event indicating a response has been completed."
|
||||
},
|
||||
"OpenAIResponseObjectStreamResponseContentPartAdded": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"response_id": {
|
||||
"type": "string",
|
||||
"description": "Unique identifier of the response containing this content"
|
||||
},
|
||||
"item_id": {
|
||||
"type": "string",
|
||||
"description": "Unique identifier of the output item containing this content part"
|
||||
},
|
||||
"part": {
|
||||
"$ref": "#/components/schemas/OpenAIResponseContentPart",
|
||||
"description": "The content part that was added"
|
||||
},
|
||||
"sequence_number": {
|
||||
"type": "integer",
|
||||
"description": "Sequential number for ordering streaming events"
|
||||
},
|
||||
"type": {
|
||||
"type": "string",
|
||||
"const": "response.content_part.added",
|
||||
"default": "response.content_part.added",
|
||||
"description": "Event type identifier, always \"response.content_part.added\""
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"response_id",
|
||||
"item_id",
|
||||
"part",
|
||||
"sequence_number",
|
||||
"type"
|
||||
],
|
||||
"title": "OpenAIResponseObjectStreamResponseContentPartAdded",
|
||||
"description": "Streaming event for when a new content part is added to a response item."
|
||||
},
|
||||
"OpenAIResponseObjectStreamResponseContentPartDone": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"response_id": {
|
||||
"type": "string",
|
||||
"description": "Unique identifier of the response containing this content"
|
||||
},
|
||||
"item_id": {
|
||||
"type": "string",
|
||||
"description": "Unique identifier of the output item containing this content part"
|
||||
},
|
||||
"part": {
|
||||
"$ref": "#/components/schemas/OpenAIResponseContentPart",
|
||||
"description": "The completed content part"
|
||||
},
|
||||
"sequence_number": {
|
||||
"type": "integer",
|
||||
"description": "Sequential number for ordering streaming events"
|
||||
},
|
||||
"type": {
|
||||
"type": "string",
|
||||
"const": "response.content_part.done",
|
||||
"default": "response.content_part.done",
|
||||
"description": "Event type identifier, always \"response.content_part.done\""
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"response_id",
|
||||
"item_id",
|
||||
"part",
|
||||
"sequence_number",
|
||||
"type"
|
||||
],
|
||||
"title": "OpenAIResponseObjectStreamResponseContentPartDone",
|
||||
"description": "Streaming event for when a content part is completed."
|
||||
},
|
||||
"OpenAIResponseObjectStreamResponseCreated": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
@ -14630,7 +14810,8 @@
|
|||
"OpenAIFilePurpose": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"assistants"
|
||||
"assistants",
|
||||
"batch"
|
||||
],
|
||||
"title": "OpenAIFilePurpose",
|
||||
"description": "Valid purpose values for OpenAI Files API."
|
||||
|
|
@ -14707,7 +14888,8 @@
|
|||
"purpose": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"assistants"
|
||||
"assistants",
|
||||
"batch"
|
||||
],
|
||||
"description": "The intended purpose of the file"
|
||||
}
|
||||
|
|
@ -15926,12 +16108,16 @@
|
|||
"value": {
|
||||
"type": "number",
|
||||
"description": "The numeric value of the metric at this timestamp"
|
||||
},
|
||||
"unit": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"timestamp",
|
||||
"value"
|
||||
"value",
|
||||
"unit"
|
||||
],
|
||||
"title": "MetricDataPoint",
|
||||
"description": "A single data point in a metric time series."
|
||||
|
|
@ -16489,6 +16675,95 @@
|
|||
],
|
||||
"title": "RegisterVectorDbRequest"
|
||||
},
|
||||
"RerankRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"model": {
|
||||
"type": "string",
|
||||
"description": "The identifier of the reranking model to use."
|
||||
},
|
||||
"query": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIChatCompletionContentPartTextParam"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIChatCompletionContentPartImageParam"
|
||||
}
|
||||
],
|
||||
"description": "The search query to rank items against. Can be a string, text content part, or image content part. The input must not exceed the model's max input token length."
|
||||
},
|
||||
"items": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIChatCompletionContentPartTextParam"
|
||||
},
|
||||
{
|
||||
"$ref": "#/components/schemas/OpenAIChatCompletionContentPartImageParam"
|
||||
}
|
||||
]
|
||||
},
|
||||
"description": "List of items to rerank. Each item can be a string, text content part, or image content part. Each input must not exceed the model's max input token length."
|
||||
},
|
||||
"max_num_results": {
|
||||
"type": "integer",
|
||||
"description": "(Optional) Maximum number of results to return. Default: returns all."
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"model",
|
||||
"query",
|
||||
"items"
|
||||
],
|
||||
"title": "RerankRequest"
|
||||
},
|
||||
"RerankData": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"index": {
|
||||
"type": "integer",
|
||||
"description": "The original index of the document in the input list"
|
||||
},
|
||||
"relevance_score": {
|
||||
"type": "number",
|
||||
"description": "The relevance score from the model output. Values are inverted when applicable so that higher scores indicate greater relevance."
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"index",
|
||||
"relevance_score"
|
||||
],
|
||||
"title": "RerankData",
|
||||
"description": "A single rerank result from a reranking response."
|
||||
},
|
||||
"RerankResponse": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"data": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"$ref": "#/components/schemas/RerankData"
|
||||
},
|
||||
"description": "List of rerank result objects, sorted by relevance score (descending)"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"data"
|
||||
],
|
||||
"title": "RerankResponse",
|
||||
"description": "Response from a reranking request."
|
||||
},
|
||||
"ResumeAgentTurnRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
|
|||
217
docs/_static/llama-stack-spec.yaml
vendored
217
docs/_static/llama-stack-spec.yaml
vendored
|
|
@ -3264,6 +3264,37 @@ paths:
|
|||
schema:
|
||||
$ref: '#/components/schemas/QueryTracesRequest'
|
||||
required: true
|
||||
/v1/inference/rerank:
|
||||
post:
|
||||
responses:
|
||||
'200':
|
||||
description: >-
|
||||
RerankResponse with indices sorted by relevance score (descending).
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/RerankResponse'
|
||||
'400':
|
||||
$ref: '#/components/responses/BadRequest400'
|
||||
'429':
|
||||
$ref: >-
|
||||
#/components/responses/TooManyRequests429
|
||||
'500':
|
||||
$ref: >-
|
||||
#/components/responses/InternalServerError500
|
||||
default:
|
||||
$ref: '#/components/responses/DefaultError'
|
||||
tags:
|
||||
- Inference
|
||||
description: >-
|
||||
Rerank a list of documents based on their relevance to a query.
|
||||
parameters: []
|
||||
requestBody:
|
||||
content:
|
||||
application/json:
|
||||
schema:
|
||||
$ref: '#/components/schemas/RerankRequest'
|
||||
required: true
|
||||
/v1/agents/{agent_id}/session/{session_id}/turn/{turn_id}/resume:
|
||||
post:
|
||||
responses:
|
||||
|
|
@ -6441,6 +6472,43 @@ components:
|
|||
title: OpenAIResponseOutputMessageMCPListTools
|
||||
description: >-
|
||||
MCP list tools output message containing available tools from an MCP server.
|
||||
OpenAIResponseContentPart:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/OpenAIResponseContentPartOutputText'
|
||||
- $ref: '#/components/schemas/OpenAIResponseContentPartRefusal'
|
||||
discriminator:
|
||||
propertyName: type
|
||||
mapping:
|
||||
output_text: '#/components/schemas/OpenAIResponseContentPartOutputText'
|
||||
refusal: '#/components/schemas/OpenAIResponseContentPartRefusal'
|
||||
OpenAIResponseContentPartOutputText:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: output_text
|
||||
default: output_text
|
||||
text:
|
||||
type: string
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
- text
|
||||
title: OpenAIResponseContentPartOutputText
|
||||
OpenAIResponseContentPartRefusal:
|
||||
type: object
|
||||
properties:
|
||||
type:
|
||||
type: string
|
||||
const: refusal
|
||||
default: refusal
|
||||
refusal:
|
||||
type: string
|
||||
additionalProperties: false
|
||||
required:
|
||||
- type
|
||||
- refusal
|
||||
title: OpenAIResponseContentPartRefusal
|
||||
OpenAIResponseObjectStream:
|
||||
oneOf:
|
||||
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseCreated'
|
||||
|
|
@ -6461,6 +6529,8 @@ components:
|
|||
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallInProgress'
|
||||
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallFailed'
|
||||
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallCompleted'
|
||||
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseContentPartAdded'
|
||||
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseContentPartDone'
|
||||
- $ref: '#/components/schemas/OpenAIResponseObjectStreamResponseCompleted'
|
||||
discriminator:
|
||||
propertyName: type
|
||||
|
|
@ -6483,6 +6553,8 @@ components:
|
|||
response.mcp_call.in_progress: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallInProgress'
|
||||
response.mcp_call.failed: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallFailed'
|
||||
response.mcp_call.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseMcpCallCompleted'
|
||||
response.content_part.added: '#/components/schemas/OpenAIResponseObjectStreamResponseContentPartAdded'
|
||||
response.content_part.done: '#/components/schemas/OpenAIResponseObjectStreamResponseContentPartDone'
|
||||
response.completed: '#/components/schemas/OpenAIResponseObjectStreamResponseCompleted'
|
||||
"OpenAIResponseObjectStreamResponseCompleted":
|
||||
type: object
|
||||
|
|
@ -6504,6 +6576,76 @@ components:
|
|||
OpenAIResponseObjectStreamResponseCompleted
|
||||
description: >-
|
||||
Streaming event indicating a response has been completed.
|
||||
"OpenAIResponseObjectStreamResponseContentPartAdded":
|
||||
type: object
|
||||
properties:
|
||||
response_id:
|
||||
type: string
|
||||
description: >-
|
||||
Unique identifier of the response containing this content
|
||||
item_id:
|
||||
type: string
|
||||
description: >-
|
||||
Unique identifier of the output item containing this content part
|
||||
part:
|
||||
$ref: '#/components/schemas/OpenAIResponseContentPart'
|
||||
description: The content part that was added
|
||||
sequence_number:
|
||||
type: integer
|
||||
description: >-
|
||||
Sequential number for ordering streaming events
|
||||
type:
|
||||
type: string
|
||||
const: response.content_part.added
|
||||
default: response.content_part.added
|
||||
description: >-
|
||||
Event type identifier, always "response.content_part.added"
|
||||
additionalProperties: false
|
||||
required:
|
||||
- response_id
|
||||
- item_id
|
||||
- part
|
||||
- sequence_number
|
||||
- type
|
||||
title: >-
|
||||
OpenAIResponseObjectStreamResponseContentPartAdded
|
||||
description: >-
|
||||
Streaming event for when a new content part is added to a response item.
|
||||
"OpenAIResponseObjectStreamResponseContentPartDone":
|
||||
type: object
|
||||
properties:
|
||||
response_id:
|
||||
type: string
|
||||
description: >-
|
||||
Unique identifier of the response containing this content
|
||||
item_id:
|
||||
type: string
|
||||
description: >-
|
||||
Unique identifier of the output item containing this content part
|
||||
part:
|
||||
$ref: '#/components/schemas/OpenAIResponseContentPart'
|
||||
description: The completed content part
|
||||
sequence_number:
|
||||
type: integer
|
||||
description: >-
|
||||
Sequential number for ordering streaming events
|
||||
type:
|
||||
type: string
|
||||
const: response.content_part.done
|
||||
default: response.content_part.done
|
||||
description: >-
|
||||
Event type identifier, always "response.content_part.done"
|
||||
additionalProperties: false
|
||||
required:
|
||||
- response_id
|
||||
- item_id
|
||||
- part
|
||||
- sequence_number
|
||||
- type
|
||||
title: >-
|
||||
OpenAIResponseObjectStreamResponseContentPartDone
|
||||
description: >-
|
||||
Streaming event for when a content part is completed.
|
||||
"OpenAIResponseObjectStreamResponseCreated":
|
||||
type: object
|
||||
properties:
|
||||
|
|
@ -10840,6 +10982,7 @@ components:
|
|||
type: string
|
||||
enum:
|
||||
- assistants
|
||||
- batch
|
||||
title: OpenAIFilePurpose
|
||||
description: >-
|
||||
Valid purpose values for OpenAI Files API.
|
||||
|
|
@ -10908,6 +11051,7 @@ components:
|
|||
type: string
|
||||
enum:
|
||||
- assistants
|
||||
- batch
|
||||
description: The intended purpose of the file
|
||||
additionalProperties: false
|
||||
required:
|
||||
|
|
@ -11838,10 +11982,13 @@ components:
|
|||
type: number
|
||||
description: >-
|
||||
The numeric value of the metric at this timestamp
|
||||
unit:
|
||||
type: string
|
||||
additionalProperties: false
|
||||
required:
|
||||
- timestamp
|
||||
- value
|
||||
- unit
|
||||
title: MetricDataPoint
|
||||
description: >-
|
||||
A single data point in a metric time series.
|
||||
|
|
@ -12252,6 +12399,76 @@ components:
|
|||
- vector_db_id
|
||||
- embedding_model
|
||||
title: RegisterVectorDbRequest
|
||||
RerankRequest:
|
||||
type: object
|
||||
properties:
|
||||
model:
|
||||
type: string
|
||||
description: >-
|
||||
The identifier of the reranking model to use.
|
||||
query:
|
||||
oneOf:
|
||||
- type: string
|
||||
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
|
||||
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
|
||||
description: >-
|
||||
The search query to rank items against. Can be a string, text content
|
||||
part, or image content part. The input must not exceed the model's max
|
||||
input token length.
|
||||
items:
|
||||
type: array
|
||||
items:
|
||||
oneOf:
|
||||
- type: string
|
||||
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
|
||||
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
|
||||
description: >-
|
||||
List of items to rerank. Each item can be a string, text content part,
|
||||
or image content part. Each input must not exceed the model's max input
|
||||
token length.
|
||||
max_num_results:
|
||||
type: integer
|
||||
description: >-
|
||||
(Optional) Maximum number of results to return. Default: returns all.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- model
|
||||
- query
|
||||
- items
|
||||
title: RerankRequest
|
||||
RerankData:
|
||||
type: object
|
||||
properties:
|
||||
index:
|
||||
type: integer
|
||||
description: >-
|
||||
The original index of the document in the input list
|
||||
relevance_score:
|
||||
type: number
|
||||
description: >-
|
||||
The relevance score from the model output. Values are inverted when applicable
|
||||
so that higher scores indicate greater relevance.
|
||||
additionalProperties: false
|
||||
required:
|
||||
- index
|
||||
- relevance_score
|
||||
title: RerankData
|
||||
description: >-
|
||||
A single rerank result from a reranking response.
|
||||
RerankResponse:
|
||||
type: object
|
||||
properties:
|
||||
data:
|
||||
type: array
|
||||
items:
|
||||
$ref: '#/components/schemas/RerankData'
|
||||
description: >-
|
||||
List of rerank result objects, sorted by relevance score (descending)
|
||||
additionalProperties: false
|
||||
required:
|
||||
- data
|
||||
title: RerankResponse
|
||||
description: Response from a reranking request.
|
||||
ResumeAgentTurnRequest:
|
||||
type: object
|
||||
properties:
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue