gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Refactor PDF file handling in pipeline_enqueue_file function to streamline dependency checks and improve readability

Browse source
This commit is contained in:
Mohit Tilwani 2025-10-23 18:48:14 +02:00
parent a9fb0a43f3
commit 7dfc224be9
1 changed files with 7 additions and 16 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

23
lightrag/api/routers/document_routes.py
View file

@ -1050,24 +1050,15 @@ async def pipeline_enqueue_file(
case ".pdf":
try:
if global_args.document_loading_engine == "DOCLING":
if not pm.is_installed("docling"): # type: ignore
pm.install("docling")
from docling.document_converter import DocumentConverter # type: ignore
converter = DocumentConverter()
result = converter.convert(file_path)
content = result.document.export_to_markdown()
else:
if not pm.is_installed("pypdf2"): # type: ignore
if not pm.is_installed("pypdf2"): # type: ignore
pm.install("pypdf2")
from PyPDF2 import PdfReader # type: ignore
from io import BytesIO
from PyPDF2 import PdfReader # type: ignore
from io import BytesIO
pdf_file = BytesIO(file)
reader = PdfReader(pdf_file)
for page in reader.pages:
content += page.extract_text() + "\n"
pdf_file = BytesIO(file)
reader = PdfReader(pdf_file)
for page in reader.pages:
content += page.extract_text() + "\n"
except Exception as e:
error_files = [
{