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

Update docs to include rerank models

Browse source
This commit is contained in:
Jiayi 2025-09-10 11:50:55 -07:00
parent 78375889ec
commit d1b4e090ef
2 changed files with 5 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -17875,7 +17875,7 @@
}, },
{ {
"name": "Inference", "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 by relevance.",
"x-displayName": "Llama Stack Inference API for generating completions, chat completions, and embeddings." "x-displayName": "Llama Stack Inference API for generating completions, chat completions, and embeddings."
}, },
{ {

6
docs/static/llama-stack-spec.yaml vendored
View file

@ -13452,13 +13452,15 @@ tags:
description: '' description: ''
- name: Inference - name: Inference
description: >- description: >-
This API provides the raw interface to the underlying models. Two kinds of models This API provides the raw interface to the underlying models. Three kinds of
are supported: models are supported:
- LLM models: these models generate "raw" and "chat" (conversational) completions. - LLM models: these models generate "raw" and "chat" (conversational) completions.
- Embedding models: these models generate embeddings to be used for semantic - Embedding models: these models generate embeddings to be used for semantic
search. search.
- Rerank models: these models reorder the documents by relevance.
x-displayName: >- x-displayName: >-
Llama Stack Inference API for generating completions, chat completions, and Llama Stack Inference API for generating completions, chat completions, and
embeddings. embeddings.