phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-08 13:00:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix rerank integration test based on client side changes

Browse source
This commit is contained in:
Jiayi 2025-10-01 10:37:58 -07:00
parent bb2eb33fc3
commit 6b4940806f
8 changed files with 27 additions and 276 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/static/deprecated-llama-stack-spec.html vendored
View file

@ -13335,7 +13335,7 @@
},
{
"name": "Inference",
"description": "This 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": "This 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": "Llama Stack Inference API for generating completions, chat completions, and embeddings."
},
{

7
docs/static/deprecated-llama-stack-spec.yaml vendored
View file

@ -9990,13 +9990,16 @@ tags:
description: ''
- name: Inference
description: >-
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: >-
Llama Stack Inference API for generating completions, chat completions, and
embeddings.

7
docs/static/stainless-llama-stack-spec.html vendored
View file

@ -8838,7 +8838,8 @@
"type": "string",
"enum": [
"llm",
"embedding"
"embedding",
"rerank"
],
"title": "ModelType",
"description": "Enumeration of supported model types in Llama Stack."
@ -17033,7 +17034,7 @@
"properties": {
"model": {
"type": "string",
"description": "The identifier of the reranking model to use."
"description": "The identifier of the reranking model to use. The model must be a reranking model registered with Llama Stack and available via the /models endpoint."
},
"query": {
"oneOf": [
@ -18456,7 +18457,7 @@
},
{
"name": "Inference",
"description": "This 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": "This 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": "Llama Stack Inference API for generating completions, chat completions, and embeddings."
},
{

11
docs/static/stainless-llama-stack-spec.yaml vendored
View file

@ -6603,6 +6603,7 @@ components:
enum:
- llm
- embedding
- rerank
title: ModelType
description: >-
Enumeration of supported model types in Llama Stack.
@ -12693,7 +12694,8 @@ components:
model:
type: string
description: >-
The identifier of the reranking model to use.
The identifier of the reranking model to use. The model must be a reranking
model registered with Llama Stack and available via the /models endpoint.
query:
oneOf:
- type: string
@ -13774,13 +13776,16 @@ tags:
description: ''
- name: Inference
description: >-
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: >-
Llama Stack Inference API for generating completions, chat completions, and
embeddings.