oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-04-05 14:45:28 +00:00
Code Issues Projects Releases Packages Wiki Activity

Replace PyPDF2 with pymupdf for PDF text extraction

Browse source 
pymupdf produces cleaner text (e.g. no concatenated words in headers),
handles encrypted and malformed PDFs that PyPDF2 failed on, and
supports non-Latin scripts.
This commit is contained in:
oobabooga 2026-03-04 06:43:37 -08:00
parent f4d787ab8d
commit f010aa1612
15 changed files with 18 additions and 20 deletions
Download patch file Download diff file Expand all files Collapse all files

10
modules/chat.py
View file

@ -657,15 +657,13 @@ def add_message_attachment(history, row_idx, file_path, is_user=True):
def extract_pdf_text(pdf_path):
"""Extract text from a PDF file"""
import PyPDF2
import pymupdf
text = ""
try:
with open(pdf_path, 'rb') as file:
pdf_reader = PyPDF2.PdfReader(file)
for page_num in range(len(pdf_reader.pages)):
page = pdf_reader.pages[page_num]
text += page.extract_text() + "\n\n"
with pymupdf.open(pdf_path) as doc:
for page in doc:
text += page.get_text() + "\n\n"
return text.strip()
except Exception as e: