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 table desc bugs, add positions to chunks (#91)

Browse Source
This commit is contained in:
KevinHuSh
2024-03-04 14:42:26 +08:00
committed by GitHub
parent 8a726fb04b
commit 685b4d8a95
13 changed files with 117 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
rag/app/presentation.py
View File

@ -48,6 +48,7 @@ class Pdf(PdfParser):
return False
def __call__(self, filename, binary=None, from_page=0, to_page=100000, zoomin=3, callback=None):
callback(msg="OCR is running...")
self.__images__(filename if not binary else binary, zoomin, from_page, to_page)
callback(0.8, "Page {}~{}: OCR finished".format(from_page, min(to_page, self.total_page)))
assert len(self.boxes) == len(self.page_images), "{} vs. {}".format(len(self.boxes), len(self.page_images))
@ -94,9 +95,10 @@ def chunk(filename, binary=None, from_page=0, to_page=100000, callback=None, **k
return res
elif re.search(r"\.pdf$", filename, re.IGNORECASE):
pdf_parser = Pdf()
for txt,img in pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page, callback=callback):
for pn, (txt,img) in enumerate(pdf_parser(filename if not binary else binary, from_page=from_page, to_page=to_page, callback=callback)):
d = copy.deepcopy(doc)
d["image"] = img
d["page_num_obj"] = [pn+1]
tokenize(d, txt, pdf_parser.is_english)
res.append(d)
return res