RYDE-WORK/Langchain-Chatchat
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/Langchain-Chatchat.git synced 2026-02-07 07:23:29 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

update pdf_loader.py

Browse Source
This commit is contained in:
imClumsyPanda 2023-05-31 18:03:37 +08:00
parent 99ee2e9fd8
commit 5c0c1eed93
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
loader/pdf_loader.py
View File

@ -39,7 +39,8 @@ class UnstructuredPaddlePDFLoader(UnstructuredFileLoader):
result = ocr.ocr(img_name) result = ocr.ocr(img_name)
ocr_result = [i[1][0] for line in result for i in line] ocr_result = [i[1][0] for line in result for i in line]
fout.write("\n".join(ocr_result)) fout.write("\n".join(ocr_result))
os.remove(img_name) if os.path.exists(img_name):
os.remove(img_name)
return txt_file_path return txt_file_path
txt_file_path = pdf_ocr_txt(self.file_path) txt_file_path = pdf_ocr_txt(self.file_path)