phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-29 15:04:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat (RAG): Implement configurable search mode in RAGQueryConfig

Browse source 
Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com>
This commit is contained in:
Varsha Prasad Narsing 2025-04-14 16:53:17 -07:00
parent 85b5f3172b
commit e2a7022d3c
14 changed files with 210 additions and 43 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/remote/vector_io/milvus/milvus.py
View file

@ -73,7 +73,9 @@ class MilvusIndex(EmbeddingIndex):
logger.error(f"Error inserting chunks into Milvus collection {self.collection_name}: {e}")
raise e
async def query(self, embedding: NDArray, k: int, score_threshold: float) -> QueryChunksResponse:
async def query(
self, embedding: NDArray, query_str: Optional[str], k: int, score_threshold: float, mode: str
) -> QueryChunksResponse:
search_res = await asyncio.to_thread(
self.client.search,
collection_name=self.collection_name,