phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-13 04:22:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Remove experimental from rerank models doc

Browse source
This commit is contained in:
Jiayi 2025-10-17 14:51:17 -07:00
parent 51c923f096
commit ad52849072
9 changed files with 13 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -1237,7 +1237,7 @@ class Inference(InferenceProvider):
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 (Experimental): these models reorder the documents based on their relevance to a query.
- Rerank models: these models reorder the documents based on their relevance to a query.
"""
@webmethod(route="/openai/v1/chat/completions", method="GET", level=LLAMA_STACK_API_V1, deprecated=True)