phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-19 03:19:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: support filters in file search

Browse source 
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-06-18 20:40:34 -07:00
parent 90d03552d4
commit 1c56b9133a
13 changed files with 449 additions and 63 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/apis/vector_io/vector_io.py
View file

@ -157,6 +157,11 @@ VectorStoreChunkingStrategy = Annotated[
register_schema(VectorStoreChunkingStrategy, name="VectorStoreChunkingStrategy")
class SearchRankingOptions(BaseModel):
ranker: str | None = None
score_threshold: float | None = Field(default=0.0, ge=0.0, le=1.0)
@json_schema_type
class VectorStoreFileLastError(BaseModel):
code: Literal["server_error"] | Literal["rate_limit_exceeded"]
@ -319,7 +324,7 @@ class VectorIO(Protocol):
query: str | list[str],
filters: dict[str, Any] | None = None,
max_num_results: int | None = 10,
ranking_options: dict[str, Any] | None = None,
ranking_options: SearchRankingOptions | None = None,
rewrite_query: bool | None = False,
) -> VectorStoreSearchResponsePage:
"""Search for chunks in a vector store.