AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-08-18 15:35:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix document could be None (#15818)

Browse Source
This commit is contained in:
Jyong 2025-03-14 16:40:01 +08:00 committed by GitHub
parent 10bd03611c
commit 84a866028a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 26 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
api/core/rag/datasource/retrieval_service.py
View File

@ -276,6 +276,8 @@ class RetrievalService:
continue continue
dataset_document = dataset_documents[document_id] dataset_document = dataset_documents[document_id]
if not dataset_document:
continue
if dataset_document.doc_form == IndexType.PARENT_CHILD_INDEX: if dataset_document.doc_form == IndexType.PARENT_CHILD_INDEX:
# Handle parent-child documents # Handle parent-child documents

45
api/core/rag/retrieval/dataset_retrieval.py
View File

@ -433,30 +433,33 @@ class DatasetRetrieval:
dataset_document = DatasetDocument.query.filter( dataset_document = DatasetDocument.query.filter(
DatasetDocument.id == document.metadata["document_id"] DatasetDocument.id == document.metadata["document_id"]
).first() ).first()
if dataset_document.doc_form == IndexType.PARENT_CHILD_INDEX: if dataset_document:
child_chunk = ChildChunk.query.filter( if dataset_document.doc_form == IndexType.PARENT_CHILD_INDEX:
ChildChunk.index_node_id == document.metadata["doc_id"], child_chunk = ChildChunk.query.filter(
ChildChunk.dataset_id == dataset_document.dataset_id, ChildChunk.index_node_id == document.metadata["doc_id"],
ChildChunk.document_id == dataset_document.id, ChildChunk.dataset_id == dataset_document.dataset_id,
).first() ChildChunk.document_id == dataset_document.id,
if child_chunk: ).first()
segment = DocumentSegment.query.filter(DocumentSegment.id == child_chunk.segment_id).update( if child_chunk:
segment = DocumentSegment.query.filter(DocumentSegment.id == child_chunk.segment_id).update(
{DocumentSegment.hit_count: DocumentSegment.hit_count + 1}, synchronize_session=False
)
db.session.commit()
else:
query = db.session.query(DocumentSegment).filter(
DocumentSegment.index_node_id == document.metadata["doc_id"]
)
# if 'dataset_id' in document.metadata:
if "dataset_id" in document.metadata:
query = query.filter(DocumentSegment.dataset_id == document.metadata["dataset_id"])
# add hit count to document segment
query.update(
{DocumentSegment.hit_count: DocumentSegment.hit_count + 1}, synchronize_session=False {DocumentSegment.hit_count: DocumentSegment.hit_count + 1}, synchronize_session=False
) )
db.session.commit()
else:
query = db.session.query(DocumentSegment).filter(
DocumentSegment.index_node_id == document.metadata["doc_id"]
)
# if 'dataset_id' in document.metadata: db.session.commit()
if "dataset_id" in document.metadata:
query = query.filter(DocumentSegment.dataset_id == document.metadata["dataset_id"])
# add hit count to document segment
query.update({DocumentSegment.hit_count: DocumentSegment.hit_count + 1}, synchronize_session=False)
db.session.commit()
# get tracing instance # get tracing instance
trace_manager: TraceQueueManager | None = ( trace_manager: TraceQueueManager | None = (