pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: empty query issue. (#7551)

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

#5214

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu
2025-05-09 12:20:19 +08:00
committed by GitHub
parent d66c17ab5c
commit a14865e6bb
2 changed files with 6 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
deepdoc/parser/pdf_parser.py
View File

@ -309,7 +309,7 @@ class RAGFlowPdfParser:
"bottom": b[-1][1] / ZM,
"chars": [],
"page_number": pagenum} for b, t in bxs if b[0][0] <= b[1][0] and b[0][1] <= b[-1][1]],
self.mean_height[-1] / 3
self.mean_height[pagenum-1] / 3
)
# merge chars in the same rect
@ -355,8 +355,8 @@ class RAGFlowPdfParser:
del boxes_to_reg[i]["box_image"]
logging.info(f"__ocr recognize {len(bxs)} boxes cost {timer() - start}s")
bxs = [b for b in bxs if b["text"]]
if self.mean_height[-1] == 0:
self.mean_height[-1] = np.median([b["bottom"] - b["top"]
if self.mean_height[pagenum-1] == 0:
self.mean_height[pagenum-1] = np.median([b["bottom"] - b["top"]
for b in bxs])
self.boxes.append(bxs)