AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-06-04 11:14:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix metadata filter not affect in keyword-search and fulltext-search (#16644)

Browse Source
This commit is contained in:
Jyong 2025-03-24 18:35:16 +08:00 committed by GitHub
parent c167a1f4f4
commit 1be0d26c1f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
api/core/rag/datasource/retrieval_service.py
View File

@ -97,6 +97,7 @@ class RetrievalService:
all_documents=all_documents, all_documents=all_documents,
retrieval_method=retrieval_method, retrieval_method=retrieval_method,
exceptions=exceptions, exceptions=exceptions,
document_ids_filter=document_ids_filter,
) )
) )
concurrent.futures.wait(futures, timeout=30, return_when=concurrent.futures.ALL_COMPLETED) concurrent.futures.wait(futures, timeout=30, return_when=concurrent.futures.ALL_COMPLETED)
@ -222,6 +223,7 @@ class RetrievalService:
all_documents: list, all_documents: list,
retrieval_method: str, retrieval_method: str,
exceptions: list, exceptions: list,
document_ids_filter: Optional[list[str]] = None,
): ):
with flask_app.app_context(): with flask_app.app_context():
try: try:
@ -231,7 +233,9 @@ class RetrievalService:
vector_processor = Vector(dataset=dataset) vector_processor = Vector(dataset=dataset)
documents = vector_processor.search_by_full_text(cls.escape_query_for_search(query), top_k=top_k) documents = vector_processor.search_by_full_text(
cls.escape_query_for_search(query), top_k=top_k, document_ids_filter=document_ids_filter
)
if documents: if documents:
if ( if (
reranking_model reranking_model

6
api/core/rag/retrieval/dataset_retrieval.py
View File

@ -610,7 +610,11 @@ class DatasetRetrieval:
if dataset.indexing_technique == "economy": if dataset.indexing_technique == "economy":
# use keyword table query # use keyword table query
documents = RetrievalService.retrieve( documents = RetrievalService.retrieve(
retrieval_method="keyword_search", dataset_id=dataset.id, query=query, top_k=top_k retrieval_method="keyword_search",
dataset_id=dataset.id,
query=query,
top_k=top_k,
document_ids_filter=document_ids_filter,
) )
if documents: if documents:
all_documents.extend(documents) all_documents.extend(documents)