github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-01 10:54:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[patch]: add support for similarity_score_threshold search in… (#20852)

Browse Source 
See
https://github.com/langchain-ai/langchain/issues/20600#issuecomment-2075569338
for details.

@chrislrobert
This commit is contained in:
Massimiliano Pronesti 2024-04-24 21:14:33 +02:00 committed by GitHub
parent 87d31a3ec0
commit 8d1167b32f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
libs/community/langchain_community/vectorstores/azuresearch.py
View File

@ -479,7 +479,7 @@ class AzureSearch(VectorStore):
def hybrid_search_with_score(
self, query: str, k: int = 4, filters: Optional[str] = None
) -> List[Tuple[Document, float]]:
"""Return docs most similar to query with an hybrid query.
"""Return docs most similar to query with a hybrid query.
Args:
query: Text to look up documents similar to.
@ -558,7 +558,7 @@ class AzureSearch(VectorStore):
def semantic_hybrid_search_with_score_and_rerank(
self, query: str, k: int = 4, filters: Optional[str] = None
) -> List[Tuple[Document, float, float]]:
"""Return docs most similar to query with an hybrid query.
"""Return docs most similar to query with a hybrid query.
Args:
query: Text to look up documents similar to.
@ -702,7 +702,12 @@ class AzureSearchVectorStoreRetriever(BaseRetriever):
if "search_type" in values:
search_type = values["search_type"]
if search_type not in (
allowed_search_types := ("similarity", "hybrid", "semantic_hybrid")
allowed_search_types := (
"similarity",
"similarity_score_threshold",
"hybrid",
"semantic_hybrid",
)
):
raise ValueError(
f"search_type of {search_type} not allowed. Valid values are: "
@ -718,6 +723,13 @@ class AzureSearchVectorStoreRetriever(BaseRetriever):
) -> List[Document]:
if self.search_type == "similarity":
docs = self.vectorstore.vector_search(query, k=self.k, **kwargs)
elif self.search_type == "similarity_score_threshold":
docs = [
doc
for doc, _ in self.vectorstore.similarity_search_with_relevance_scores(
query, k=self.k, **kwargs
)
]
elif self.search_type == "hybrid":
docs = self.vectorstore.hybrid_search(query, k=self.k, **kwargs)
elif self.search_type == "semantic_hybrid":