phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-16 04:32:39 +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

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: >-