phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add rerank API for NVIDIA Inference Provider

Browse source
This commit is contained in:
Jiayi 2025-09-03 17:34:05 -07:00
parent ce77c27ff8
commit bab9d7aaea
9 changed files with 9213 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

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 by relevance
"""
llm = "llm"
embedding = "embedding"
rerank = "rerank"
@json_schema_type