zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-07-06 19:38:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

Feat: enable sync deleted files for more connectors (#14353)

Browse Source 
### What problem does this PR solve?

Feat: enable sync delted files for connectors

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
This commit is contained in:
Magicbook1108
2026-04-28 15:07:14 +08:00
committed by GitHub
parent 0df65d358a
commit 18fbfafca6
21 changed files with 789 additions and 304 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
api/db/services/document_service.py
View File

@@ -423,6 +423,9 @@ class DocumentService(CommonService):
if not cls.delete_document_and_update_kb_counts(doc.id):
return True
chunk_index_name = search.index_name(tenant_id)
chunk_index_exists = settings.docStoreConn.index_exist(chunk_index_name, doc.kb_id)
# Cancel all running tasks first Using preset function in task_service.py --- set cancel flag in Redis
try:
cancel_all_task_of(doc.id)
@@ -438,7 +441,8 @@ class DocumentService(CommonService):
# Delete chunk images (non-critical, log and continue)
try:
cls.delete_chunk_images(doc, tenant_id)
if chunk_index_exists:
cls.delete_chunk_images(doc, tenant_id)
except Exception as e:
logging.warning(f"Failed to delete chunk images for document {doc.id}: {e}")
@@ -452,7 +456,7 @@ class DocumentService(CommonService):
# Delete chunks from doc store - this is critical, log errors
try:
settings.docStoreConn.delete({"doc_id": doc.id}, search.index_name(tenant_id), doc.kb_id)
settings.docStoreConn.delete({"doc_id": doc.id}, chunk_index_name, doc.kb_id)
except Exception as e:
logging.error(f"Failed to delete chunks from doc store for document {doc.id}: {e}")
@@ -464,23 +468,24 @@ class DocumentService(CommonService):
# Cleanup knowledge graph references (non-critical, log and continue)
try:
graph_source = settings.docStoreConn.get_fields(
settings.docStoreConn.search(["source_id"], [], {"kb_id": doc.kb_id, "knowledge_graph_kwd": ["graph"]}, [], OrderByExpr(), 0, 1, search.index_name(tenant_id), [doc.kb_id]),
["source_id"],
)
if len(graph_source) > 0 and doc.id in list(graph_source.values())[0]["source_id"]:
settings.docStoreConn.update(
{"kb_id": doc.kb_id, "knowledge_graph_kwd": ["entity", "relation", "graph", "subgraph", "community_report"], "source_id": doc.id},
{"remove": {"source_id": doc.id}},
search.index_name(tenant_id),
doc.kb_id,
)
settings.docStoreConn.update({"kb_id": doc.kb_id, "knowledge_graph_kwd": ["graph"]}, {"removed_kwd": "Y"}, search.index_name(tenant_id), doc.kb_id)
settings.docStoreConn.delete(
{"kb_id": doc.kb_id, "knowledge_graph_kwd": ["entity", "relation", "graph", "subgraph", "community_report"], "must_not": {"exists": "source_id"}},
search.index_name(tenant_id),
doc.kb_id,
if chunk_index_exists:
graph_source = settings.docStoreConn.get_fields(
settings.docStoreConn.search(["source_id"], [], {"kb_id": doc.kb_id, "knowledge_graph_kwd": ["graph"]}, [], OrderByExpr(), 0, 1, chunk_index_name, [doc.kb_id]),
["source_id"],
)
if len(graph_source) > 0 and doc.id in list(graph_source.values())[0]["source_id"]:
settings.docStoreConn.update(
{"kb_id": doc.kb_id, "knowledge_graph_kwd": ["entity", "relation", "graph", "subgraph", "community_report"], "source_id": doc.id},
{"remove": {"source_id": doc.id}},
chunk_index_name,
doc.kb_id,
)
settings.docStoreConn.update({"kb_id": doc.kb_id, "knowledge_graph_kwd": ["graph"]}, {"removed_kwd": "Y"}, chunk_index_name, doc.kb_id)
settings.docStoreConn.delete(
{"kb_id": doc.kb_id, "knowledge_graph_kwd": ["entity", "relation", "graph", "subgraph", "community_report"], "must_not": {"exists": "source_id"}},
chunk_index_name,
doc.kb_id,
)
except Exception as e:
logging.warning(f"Failed to cleanup knowledge graph for document {doc.id}: {e}")