opensource
/
dify
mirror of https://github.com/langgenius/dify.git
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix: document is not bound to a session (#26480)

This commit is contained in:
quicksand 2025-09-30 14:24:40 +08:00 committed by crazywoola
parent 4a67f661d3
commit 79ded7d6e3
1 changed files with 15 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
api/core/workflow/nodes/knowledge_index/knowledge_index_node.py
View File

@ -136,6 +136,11 @@ class KnowledgeIndexNode(Node):
document = db.session.query(Document).filter_by(id=document_id.value).first()
if not document:
raise KnowledgeIndexNodeError(f"Document {document_id.value} not found.")
doc_id_value = document.id
ds_id_value = dataset.id
dataset_name_value = dataset.name
document_name_value = document.name
created_at_value = document.created_at
# chunk nodes by chunk size
indexing_start_at = time.perf_counter()
index_processor = IndexProcessorFactory(dataset.chunk_structure).init_index_processor()
@ -161,16 +166,16 @@ class KnowledgeIndexNode(Node):
document.word_count = (
db.session.query(func.sum(DocumentSegment.word_count))
.where(
DocumentSegment.document_id == document.id,
DocumentSegment.dataset_id == dataset.id,
DocumentSegment.document_id == doc_id_value,
DocumentSegment.dataset_id == ds_id_value,
)
.scalar()
)
db.session.add(document)
# update document segment status
db.session.query(DocumentSegment).where(
DocumentSegment.document_id == document.id,
DocumentSegment.dataset_id == dataset.id,
DocumentSegment.document_id == doc_id_value,
DocumentSegment.dataset_id == ds_id_value,
).update(
{
DocumentSegment.status: "completed",
@ -182,13 +187,13 @@ class KnowledgeIndexNode(Node):
db.session.commit()
return {
"dataset_id": dataset.id,
"dataset_name": dataset.name,
"dataset_id": ds_id_value,
"dataset_name": dataset_name_value,
"batch": batch.value,
"document_id": document.id,
"document_name": document.name,
"created_at": document.created_at.timestamp(),
"display_status": document.indexing_status,
"document_id": doc_id_value,
"document_name": document_name_value,
"created_at": created_at_value.timestamp(),
"display_status": "completed",
}
def _get_preview_output(self, chunk_structure: str, chunks: Any) -> Mapping[str, Any]: