pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-30 00:32:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: Delete chunk images on document parser config change. (#12262)

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

Modifying a document’s parser config previously left behind obsolete
chunk images. If the dataset isn’t manually deleted, these images
accumulate and waste storage. This PR fixes the issue by automatically
removing associated images when the parser config changes.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
lys1313013
2025-12-29 12:54:11 +08:00
committed by GitHub
parent 27c55f6514
commit 8d3f9d61da
2 changed files with 19 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
api/db/services/document_service.py
View File

@ -342,21 +342,7 @@ class DocumentService(CommonService):
cls.clear_chunk_num(doc.id)
try:
TaskService.filter_delete([Task.doc_id == doc.id])
page = 0
page_size = 1000
all_chunk_ids = []
while True:
chunks = settings.docStoreConn.search(["img_id"], [], {"doc_id": doc.id}, [], OrderByExpr(),
page * page_size, page_size, search.index_name(tenant_id),
[doc.kb_id])
chunk_ids = settings.docStoreConn.get_doc_ids(chunks)
if not chunk_ids:
break
all_chunk_ids.extend(chunk_ids)
page += 1
for cid in all_chunk_ids:
if settings.STORAGE_IMPL.obj_exist(doc.kb_id, cid):
settings.STORAGE_IMPL.rm(doc.kb_id, cid)
cls.delete_chunk_images(doc, tenant_id)
if doc.thumbnail and not doc.thumbnail.startswith(IMG_BASE64_PREFIX):
if settings.STORAGE_IMPL.obj_exist(doc.kb_id, doc.thumbnail):
settings.STORAGE_IMPL.rm(doc.kb_id, doc.thumbnail)
@ -378,6 +364,23 @@ class DocumentService(CommonService):
pass
return cls.delete_by_id(doc.id)
@classmethod
@DB.connection_context()
def delete_chunk_images(cls, doc, tenant_id):
page = 0
page_size = 1000
while True:
chunks = settings.docStoreConn.search(["img_id"], [], {"doc_id": doc.id}, [], OrderByExpr(),
page * page_size, page_size, search.index_name(tenant_id),
[doc.kb_id])
chunk_ids = settings.docStoreConn.get_doc_ids(chunks)
if not chunk_ids:
break
for cid in chunk_ids:
if settings.STORAGE_IMPL.obj_exist(doc.kb_id, cid):
settings.STORAGE_IMPL.rm(doc.kb_id, cid)
page += 1
@classmethod
@DB.connection_context()
def get_newly_uploaded(cls):