phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update docs

Browse source
This commit is contained in:
Jiayi 2025-09-12 19:55:04 -07:00
parent a0e6e82c1e
commit 3538477070
7 changed files with 6 additions and 137 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -1162,7 +1162,7 @@ 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: these models reorder the documents by relevance.
- 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)