mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-01-19 11:45:10 +08:00
Fix: duplicate content in chunk (#12655)
### 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:
@ -554,6 +554,7 @@ 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:
|
||||||
|
|||||||
Reference in New Issue
Block a user