phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-12 20:12:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add rerank models and rerank API change

Browse source
This commit is contained in:
Jiayi 2025-10-16 17:27:38 -07:00
parent f675fdda0f
commit 51c923f096
12 changed files with 215 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/apis/inference/inference.py
View file

@ -1234,9 +1234,10 @@ class Inference(InferenceProvider):
Llama Stack Inference API for generating completions, chat completions, and 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 (Experimental): 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)

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

@ -27,10 +27,12 @@ class ModelType(StrEnum):
"""Enumeration of supported model types in Llama Stack.
:cvar llm: Large language model for text generation and completion
:cvar embedding: Embedding model for converting text to vector representations
:cvar rerank: Reranking model for reordering documents based on their relevance to a query
"""
llm = "llm"
embedding = "embedding"
rerank = "rerank"
@json_schema_type