phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-15 08:02:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge remote-tracking branch 'origin/main' into dependabot/uv/openai-2.5.0

Browse source
This commit is contained in:
Ashwin Bharambe 2025-10-22 12:17:03 -07:00
commit 13450c1a68
317 changed files with 86802 additions and 18957 deletions
Download patch file Download diff file Expand all files Collapse all files

14
docs/static/deprecated-llama-stack-spec.html vendored
View file

@ -5547,7 +5547,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -5798,7 +5798,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -9024,6 +9024,10 @@
"$ref": "#/components/schemas/OpenAIResponseUsage",
"description": "(Optional) Token usage information for the response"
},
"instructions": {
"type": "string",
"description": "(Optional) System message inserted into the model's context"
},
"input": {
"type": "array",
"items": {
@ -9901,6 +9905,10 @@
"usage": {
"$ref": "#/components/schemas/OpenAIResponseUsage",
"description": "(Optional) Token usage information for the response"
},
"instructions": {
"type": "string",
"description": "(Optional) System message inserted into the model's context"
}
},
"additionalProperties": false,
@ -13459,7 +13467,7 @@
},
{
"name": "Inference",
"description": "Llama Stack Inference API for generating completions, chat completions, and embeddings.\n\nThis API provides the raw interface to the underlying models. Two kinds of models are supported:\n- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.\n- Embedding models: these models generate embeddings to be used for semantic search.",
"description": "Llama Stack Inference API for generating completions, chat completions, and embeddings.\n\nThis API provides the raw interface to the underlying models. Three kinds of models are supported:\n- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.\n- Embedding models: these models generate embeddings to be used for semantic search.\n- Rerank models: these models reorder the documents based on their relevance to a query.",
"x-displayName": "Inference"
},
{

19
docs/static/deprecated-llama-stack-spec.yaml vendored
View file

@ -4114,7 +4114,7 @@ components:
enum:
- model
- shield
- vector_db
- vector_store
- dataset
- scoring_function
- benchmark
@ -4303,7 +4303,7 @@ components:
enum:
- model
- shield
- vector_db
- vector_store
- dataset
- scoring_function
- benchmark
@ -6734,6 +6734,10 @@ components:
$ref: '#/components/schemas/OpenAIResponseUsage'
description: >-
(Optional) Token usage information for the response
instructions:
type: string
description: >-
(Optional) System message inserted into the model's context
input:
type: array
items:
@ -7403,6 +7407,10 @@ components:
$ref: '#/components/schemas/OpenAIResponseUsage'
description: >-
(Optional) Token usage information for the response
instructions:
type: string
description: >-
(Optional) System message inserted into the model's context
additionalProperties: false
required:
- created_at
@ -10210,13 +10218,16 @@ tags:
embeddings.
This API provides the raw interface to the underlying models. Two kinds of models
are supported:
This API provides the raw interface to the underlying models. Three 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.
- Rerank models: these models reorder the documents based on their relevance
to a query.
x-displayName: Inference
- name: Models
description: ''

4
docs/static/experimental-llama-stack-spec.html vendored
View file

@ -1850,7 +1850,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -3983,7 +3983,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",

4
docs/static/experimental-llama-stack-spec.yaml vendored
View file

@ -1320,7 +1320,7 @@ components:
enum:
- model
- shield
- vector_db
- vector_store
- dataset
- scoring_function
- benchmark
@ -2927,7 +2927,7 @@ components:
enum:
- model
- shield
- vector_db
- vector_store
- dataset
- scoring_function
- benchmark

21
docs/static/llama-stack-spec.html vendored
View file

@ -6767,7 +6767,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -6826,7 +6826,8 @@
"type": "string",
"enum": [
"llm",
"embedding"
"embedding",
"rerank"
],
"title": "ModelType",
"description": "Enumeration of supported model types in Llama Stack."
@ -7567,6 +7568,10 @@
"$ref": "#/components/schemas/OpenAIResponseUsage",
"description": "(Optional) Token usage information for the response"
},
"instructions": {
"type": "string",
"description": "(Optional) System message inserted into the model's context"
},
"input": {
"type": "array",
"items": {
@ -8115,6 +8120,10 @@
"usage": {
"$ref": "#/components/schemas/OpenAIResponseUsage",
"description": "(Optional) Token usage information for the response"
},
"instructions": {
"type": "string",
"description": "(Optional) System message inserted into the model's context"
}
},
"additionalProperties": false,
@ -10164,7 +10173,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -10646,7 +10655,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -11699,7 +11708,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -13228,7 +13237,7 @@
},
{
"name": "Inference",
"description": "Llama Stack Inference API for generating completions, chat completions, and embeddings.\n\nThis API provides the raw interface to the underlying models. Two kinds of models are supported:\n- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.\n- Embedding models: these models generate embeddings to be used for semantic search.",
"description": "Llama Stack Inference API for generating completions, chat completions, and embeddings.\n\nThis API provides the raw interface to the underlying models. Three kinds of models are supported:\n- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.\n- Embedding models: these models generate embeddings to be used for semantic search.\n- Rerank models: these models reorder the documents based on their relevance to a query.",
"x-displayName": "Inference"
},
{

24
docs/static/llama-stack-spec.yaml vendored
View file

@ -5127,7 +5127,7 @@ components:
enum:
- model
- shield
- vector_db
- vector_store
- dataset
- scoring_function
- benchmark
@ -5169,6 +5169,7 @@ components:
enum:
- llm
- embedding
- rerank
title: ModelType
description: >-
Enumeration of supported model types in Llama Stack.
@ -5715,6 +5716,10 @@ components:
$ref: '#/components/schemas/OpenAIResponseUsage'
description: >-
(Optional) Token usage information for the response
instructions:
type: string
description: >-
(Optional) System message inserted into the model's context
input:
type: array
items:
@ -6118,6 +6123,10 @@ components:
$ref: '#/components/schemas/OpenAIResponseUsage'
description: >-
(Optional) Token usage information for the response
instructions:
type: string
description: >-
(Optional) System message inserted into the model's context
additionalProperties: false
required:
- created_at
@ -7811,7 +7820,7 @@ components:
enum:
- model
- shield
- vector_db
- vector_store
- dataset
- scoring_function
- benchmark
@ -8119,7 +8128,7 @@ components:
enum:
- model
- shield
- vector_db
- vector_store
- dataset
- scoring_function
- benchmark
@ -8882,7 +8891,7 @@ components:
enum:
- model
- shield
- vector_db
- vector_store
- dataset
- scoring_function
- benchmark
@ -10082,13 +10091,16 @@ tags:
embeddings.
This API provides the raw interface to the underlying models. Two kinds of models
are supported:
This API provides the raw interface to the underlying models. Three 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.
- Rerank models: these models reorder the documents based on their relevance
to a query.
x-displayName: Inference
- name: Inspect
description: >-

25
docs/static/stainless-llama-stack-spec.html vendored
View file

@ -8439,7 +8439,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -8498,7 +8498,8 @@
"type": "string",
"enum": [
"llm",
"embedding"
"embedding",
"rerank"
],
"title": "ModelType",
"description": "Enumeration of supported model types in Llama Stack."
@ -9239,6 +9240,10 @@
"$ref": "#/components/schemas/OpenAIResponseUsage",
"description": "(Optional) Token usage information for the response"
},
"instructions": {
"type": "string",
"description": "(Optional) System message inserted into the model's context"
},
"input": {
"type": "array",
"items": {
@ -9787,6 +9792,10 @@
"usage": {
"$ref": "#/components/schemas/OpenAIResponseUsage",
"description": "(Optional) Token usage information for the response"
},
"instructions": {
"type": "string",
"description": "(Optional) System message inserted into the model's context"
}
},
"additionalProperties": false,
@ -11836,7 +11845,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -12318,7 +12327,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -13371,7 +13380,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -14918,7 +14927,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -16663,7 +16672,7 @@
"enum": [
"model",
"shield",
"vector_db",
"vector_store",
"dataset",
"scoring_function",
"benchmark",
@ -17918,7 +17927,7 @@
},
{
"name": "Inference",
"description": "Llama Stack Inference API for generating completions, chat completions, and embeddings.\n\nThis API provides the raw interface to the underlying models. Two kinds of models are supported:\n- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.\n- Embedding models: these models generate embeddings to be used for semantic search.",
"description": "Llama Stack Inference API for generating completions, chat completions, and embeddings.\n\nThis API provides the raw interface to the underlying models. Three kinds of models are supported:\n- LLM models: these models generate \"raw\" and \"chat\" (conversational) completions.\n- Embedding models: these models generate embeddings to be used for semantic search.\n- Rerank models: these models reorder the documents based on their relevance to a query.",
"x-displayName": "Inference"
},
{

28
docs/static/stainless-llama-stack-spec.yaml vendored
View file

@ -6340,7 +6340,7 @@ components:
enum:
- model
- shield
- vector_db
- vector_store
- dataset
- scoring_function
- benchmark
@ -6382,6 +6382,7 @@ components:
enum:
- llm
- embedding
- rerank
title: ModelType
description: >-
Enumeration of supported model types in Llama Stack.
@ -6928,6 +6929,10 @@ components:
$ref: '#/components/schemas/OpenAIResponseUsage'
description: >-
(Optional) Token usage information for the response
instructions:
type: string
description: >-
(Optional) System message inserted into the model's context
input:
type: array
items:
@ -7331,6 +7336,10 @@ components:
$ref: '#/components/schemas/OpenAIResponseUsage'
description: >-
(Optional) Token usage information for the response
instructions:
type: string
description: >-
(Optional) System message inserted into the model's context
additionalProperties: false
required:
- created_at
@ -9024,7 +9033,7 @@ components:
enum:
- model
- shield
- vector_db
- vector_store
- dataset
- scoring_function
- benchmark
@ -9332,7 +9341,7 @@ components:
enum:
- model
- shield
- vector_db
- vector_store
- dataset
- scoring_function
- benchmark
@ -10095,7 +10104,7 @@ components:
enum:
- model
- shield
- vector_db
- vector_store
- dataset
- scoring_function
- benchmark
@ -11217,7 +11226,7 @@ components:
enum:
- model
- shield
- vector_db
- vector_store
- dataset
- scoring_function
- benchmark
@ -12544,7 +12553,7 @@ components:
enum:
- model
- shield
- vector_db
- vector_store
- dataset
- scoring_function
- benchmark
@ -13477,13 +13486,16 @@ tags:
embeddings.
This API provides the raw interface to the underlying models. Two kinds of models
are supported:
This API provides the raw interface to the underlying models. Three 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.
- Rerank models: these models reorder the documents based on their relevance
to a query.
x-displayName: Inference
- name: Inspect
description: >-