youngkingdom/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-01-19 11:45:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: duplicate content in chunk (#12655)

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

Fix: duplicate content in chunk #12336

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Magicbook1108
2026-01-16 15:32:04 +08:00
committed by GitHub
parent 2b20d0b3bb
commit 045314a1aa
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
deepdoc/parser/pdf_parser.py
View File

@ -476,7 +476,7 @@ class RAGFlowPdfParser:
self.boxes = bxs self.boxes = bxs
def _naive_vertical_merge(self, zoomin=3): def _naive_vertical_merge(self, zoomin=3):
#bxs = self._assign_column(self.boxes, zoomin) # bxs = self._assign_column(self.boxes, zoomin)
bxs = self.boxes bxs = self.boxes
grouped = defaultdict(list) grouped = defaultdict(list)
@ -553,7 +553,8 @@ class RAGFlowPdfParser:
merged_boxes.extend(bxs) merged_boxes.extend(bxs)
#self.boxes = sorted(merged_boxes, key=lambda x: (x["page_number"], x.get("col_id", 0), x["top"])) # self.boxes = sorted(merged_boxes, key=lambda x: (x["page_number"], x.get("col_id", 0), x["top"]))
self.boxes = merged_boxes
def _final_reading_order_merge(self, zoomin=3): def _final_reading_order_merge(self, zoomin=3):
if not self.boxes: if not self.boxes: