phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-03 19:57:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(api): fix a mistake from #3636 which overwrote POST /responses

Browse source
This commit is contained in:
Ashwin Bharambe 2025-10-02 13:03:17 -07:00 • committed by Raghotham Murthy
parent 36543a1100
commit 0beb61b13b
10 changed files with 75 additions and 195 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/docs/providers/agents/index.mdx
View file

@ -1,7 +1,7 @@
---
description: "Agents
APIs for creating and interacting with agentic systems."
APIs for creating and interacting with agentic systems."
sidebar_label: Agents
title: Agents
---
@ -12,6 +12,6 @@ title: Agents
Agents
APIs for creating and interacting with agentic systems.
APIs for creating and interacting with agentic systems.
This section contains documentation for all available providers for the **agents** API.

24
docs/docs/providers/batches/index.mdx
View file

@ -1,14 +1,14 @@
---
description: "The Batches API enables efficient processing of multiple requests in a single operation,
particularly useful for processing large datasets, batch evaluation workflows, and
cost-effective inference at scale.
particularly useful for processing large datasets, batch evaluation workflows, and
cost-effective inference at scale.
The API is designed to allow use of openai client libraries for seamless integration.
The API is designed to allow use of openai client libraries for seamless integration.
This API provides the following extensions:
- idempotent batch creation
This API provides the following extensions:
- idempotent batch creation
Note: This API is currently under active development and may undergo changes."
Note: This API is currently under active development and may undergo changes."
sidebar_label: Batches
title: Batches
---
@ -18,14 +18,14 @@ title: Batches
## Overview
The Batches API enables efficient processing of multiple requests in a single operation,
particularly useful for processing large datasets, batch evaluation workflows, and
cost-effective inference at scale.
particularly useful for processing large datasets, batch evaluation workflows, and
cost-effective inference at scale.
The API is designed to allow use of openai client libraries for seamless integration.
The API is designed to allow use of openai client libraries for seamless integration.
This API provides the following extensions:
- idempotent batch creation
This API provides the following extensions:
- idempotent batch creation
Note: This API is currently under active development and may undergo changes.
Note: This API is currently under active development and may undergo changes.
This section contains documentation for all available providers for the **batches** API.

12
docs/docs/providers/inference/index.mdx
View file

@ -1,9 +1,9 @@
---
description: "Llama Stack Inference API for generating completions, chat completions, and embeddings.
This API provides the raw interface to the underlying models. Two kinds of models are supported:
- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic search."
This API provides the raw interface to the underlying models. Two kinds of models are supported:
- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic search."
sidebar_label: Inference
title: Inference
---
@ -14,8 +14,8 @@ title: Inference
Llama Stack Inference API for generating completions, chat completions, and embeddings.
This API provides the raw interface to the underlying models. Two kinds of models are supported:
- LLM models: these models generate "raw" and "chat" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic search.
This API provides the raw interface to the underlying models. Two kinds of models are supported:
- LLM models: these models generate "raw" and "chat" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic search.
This section contains documentation for all available providers for the **inference** API.

42
docs/static/deprecated-llama-stack-spec.html vendored
View file

@ -2089,11 +2089,16 @@
"post": {
"responses": {
"200": {
"description": "A ListOpenAIResponseObject.",
"description": "An OpenAIResponseObject.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ListOpenAIResponseObject"
"$ref": "#/components/schemas/OpenAIResponseObject"
}
},
"text/event-stream": {
"schema": {
"$ref": "#/components/schemas/OpenAIResponseObjectStream"
}
}
}
@ -2114,14 +2119,14 @@
"tags": [
"Agents"
],
"summary": "List all OpenAI responses.",
"description": "List all OpenAI responses.",
"summary": "Create a new OpenAI response.",
"description": "Create a new OpenAI response.",
"parameters": [],
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ListOpenaiResponsesRequest"
"$ref": "#/components/schemas/CreateOpenaiResponseRequest"
}
}
},
@ -10908,33 +10913,6 @@
],
"title": "OpenAIResponseObjectStreamResponseWebSearchCallSearching"
},
"ListOpenaiResponsesRequest": {
"type": "object",
"properties": {
"after": {
"type": "string",
"description": "The ID of the last response to return."
},
"limit": {
"type": "integer",
"description": "The number of responses to return."
},
"model": {
"type": "string",
"description": "The model to filter responses by."
},
"order": {
"type": "string",
"enum": [
"asc",
"desc"
],
"description": "The order to sort responses by when sorted by created_at ('asc' or 'desc')."
}
},
"additionalProperties": false,
"title": "ListOpenaiResponsesRequest"
},
"OpenAIDeleteResponseObject": {
"type": "object",
"properties": {

34
docs/static/deprecated-llama-stack-spec.yaml vendored
View file

@ -1529,11 +1529,14 @@ paths:
post:
responses:
'200':
description: A ListOpenAIResponseObject.
description: An OpenAIResponseObject.
content:
application/json:
schema:
$ref: '#/components/schemas/ListOpenAIResponseObject'
$ref: '#/components/schemas/OpenAIResponseObject'
text/event-stream:
schema:
$ref: '#/components/schemas/OpenAIResponseObjectStream'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
@ -1546,14 +1549,14 @@ paths:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
summary: List all OpenAI responses.
description: List all OpenAI responses.
summary: Create a new OpenAI response.
description: Create a new OpenAI response.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ListOpenaiResponsesRequest'
$ref: '#/components/schemas/CreateOpenaiResponseRequest'
required: true
deprecated: true
/v1/openai/v1/responses/{response_id}:
@ -8150,27 +8153,6 @@ components:
- type
title: >-
OpenAIResponseObjectStreamResponseWebSearchCallSearching
ListOpenaiResponsesRequest:
type: object
properties:
after:
type: string
description: The ID of the last response to return.
limit:
type: integer
description: The number of responses to return.
model:
type: string
description: The model to filter responses by.
order:
type: string
enum:
- asc
- desc
description: >-
The order to sort responses by when sorted by created_at ('asc' or 'desc').
additionalProperties: false
title: ListOpenaiResponsesRequest
OpenAIDeleteResponseObject:
type: object
properties:

42
docs/static/llama-stack-spec.html vendored
View file

@ -1310,11 +1310,16 @@
"post": {
"responses": {
"200": {
"description": "A ListOpenAIResponseObject.",
"description": "An OpenAIResponseObject.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ListOpenAIResponseObject"
"$ref": "#/components/schemas/OpenAIResponseObject"
}
},
"text/event-stream": {
"schema": {
"$ref": "#/components/schemas/OpenAIResponseObjectStream"
}
}
}
@ -1335,14 +1340,14 @@
"tags": [
"Agents"
],
"summary": "List all OpenAI responses.",
"description": "List all OpenAI responses.",
"summary": "Create a new OpenAI response.",
"description": "Create a new OpenAI response.",
"parameters": [],
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ListOpenaiResponsesRequest"
"$ref": "#/components/schemas/CreateOpenaiResponseRequest"
}
}
},
@ -8233,33 +8238,6 @@
],
"title": "OpenAIResponseObjectStreamResponseWebSearchCallSearching"
},
"ListOpenaiResponsesRequest": {
"type": "object",
"properties": {
"after": {
"type": "string",
"description": "The ID of the last response to return."
},
"limit": {
"type": "integer",
"description": "The number of responses to return."
},
"model": {
"type": "string",
"description": "The model to filter responses by."
},
"order": {
"type": "string",
"enum": [
"asc",
"desc"
],
"description": "The order to sort responses by when sorted by created_at ('asc' or 'desc')."
}
},
"additionalProperties": false,
"title": "ListOpenaiResponsesRequest"
},
"OpenAIDeleteResponseObject": {
"type": "object",
"properties": {

34
docs/static/llama-stack-spec.yaml vendored
View file

@ -967,11 +967,14 @@ paths:
post:
responses:
'200':
description: A ListOpenAIResponseObject.
description: An OpenAIResponseObject.
content:
application/json:
schema:
$ref: '#/components/schemas/ListOpenAIResponseObject'
$ref: '#/components/schemas/OpenAIResponseObject'
text/event-stream:
schema:
$ref: '#/components/schemas/OpenAIResponseObjectStream'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
@ -984,14 +987,14 @@ paths:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
summary: List all OpenAI responses.
description: List all OpenAI responses.
summary: Create a new OpenAI response.
description: Create a new OpenAI response.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ListOpenaiResponsesRequest'
$ref: '#/components/schemas/CreateOpenaiResponseRequest'
required: true
deprecated: false
/v1/responses/{response_id}:
@ -6196,27 +6199,6 @@ components:
- type
title: >-
OpenAIResponseObjectStreamResponseWebSearchCallSearching
ListOpenaiResponsesRequest:
type: object
properties:
after:
type: string
description: The ID of the last response to return.
limit:
type: integer
description: The number of responses to return.
model:
type: string
description: The model to filter responses by.
order:
type: string
enum:
- asc
- desc
description: >-
The order to sort responses by when sorted by created_at ('asc' or 'desc').
additionalProperties: false
title: ListOpenaiResponsesRequest
OpenAIDeleteResponseObject:
type: object
properties:

42
docs/static/stainless-llama-stack-spec.html vendored
View file

@ -1310,11 +1310,16 @@
"post": {
"responses": {
"200": {
"description": "A ListOpenAIResponseObject.",
"description": "An OpenAIResponseObject.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ListOpenAIResponseObject"
"$ref": "#/components/schemas/OpenAIResponseObject"
}
},
"text/event-stream": {
"schema": {
"$ref": "#/components/schemas/OpenAIResponseObjectStream"
}
}
}
@ -1335,14 +1340,14 @@
"tags": [
"Agents"
],
"summary": "List all OpenAI responses.",
"description": "List all OpenAI responses.",
"summary": "Create a new OpenAI response.",
"description": "Create a new OpenAI response.",
"parameters": [],
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/ListOpenaiResponsesRequest"
"$ref": "#/components/schemas/CreateOpenaiResponseRequest"
}
}
},
@ -10242,33 +10247,6 @@
],
"title": "OpenAIResponseObjectStreamResponseWebSearchCallSearching"
},
"ListOpenaiResponsesRequest": {
"type": "object",
"properties": {
"after": {
"type": "string",
"description": "The ID of the last response to return."
},
"limit": {
"type": "integer",
"description": "The number of responses to return."
},
"model": {
"type": "string",
"description": "The model to filter responses by."
},
"order": {
"type": "string",
"enum": [
"asc",
"desc"
],
"description": "The order to sort responses by when sorted by created_at ('asc' or 'desc')."
}
},
"additionalProperties": false,
"title": "ListOpenaiResponsesRequest"
},
"OpenAIDeleteResponseObject": {
"type": "object",
"properties": {

34
docs/static/stainless-llama-stack-spec.yaml vendored
View file

@ -970,11 +970,14 @@ paths:
post:
responses:
'200':
description: A ListOpenAIResponseObject.
description: An OpenAIResponseObject.
content:
application/json:
schema:
$ref: '#/components/schemas/ListOpenAIResponseObject'
$ref: '#/components/schemas/OpenAIResponseObject'
text/event-stream:
schema:
$ref: '#/components/schemas/OpenAIResponseObjectStream'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
@ -987,14 +990,14 @@ paths:
$ref: '#/components/responses/DefaultError'
tags:
- Agents
summary: List all OpenAI responses.
description: List all OpenAI responses.
summary: Create a new OpenAI response.
description: Create a new OpenAI response.
parameters: []
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/ListOpenaiResponsesRequest'
$ref: '#/components/schemas/CreateOpenaiResponseRequest'
required: true
deprecated: false
/v1/responses/{response_id}:
@ -7641,27 +7644,6 @@ components:
- type
title: >-
OpenAIResponseObjectStreamResponseWebSearchCallSearching
ListOpenaiResponsesRequest:
type: object
properties:
after:
type: string
description: The ID of the last response to return.
limit:
type: integer
description: The number of responses to return.
model:
type: string
description: The model to filter responses by.
order:
type: string
enum:
- asc
- desc
description: >-
The order to sort responses by when sorted by created_at ('asc' or 'desc').
additionalProperties: false
title: ListOpenaiResponsesRequest
OpenAIDeleteResponseObject:
type: object
properties:

2
llama_stack/apis/agents/agents.py
View file

@ -816,7 +816,7 @@ class Agents(Protocol):
"""
...
@webmethod(route="/openai/v1/responses", method="POST", level=LLAMA_STACK_API_V1, deprecated=True)
@webmethod(route="/openai/v1/responses", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)
@webmethod(route="/responses", method="GET", level=LLAMA_STACK_API_V1)
async def list_openai_responses(
self,