UniqAI/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui synced 2024-11-16 13:40:55 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

feat: added ocr functionality to the pdf loader

Browse Source
This commit is contained in:
Jannik Streidl 2024-03-05 22:25:25 +01:00
parent eb51ad14e4
commit 089a63e0c6
2 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
backend/apps/rag/main.py
View File

@ -419,7 +419,7 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
] ]
if file_ext == "pdf": if file_ext == "pdf":
loader = PyPDFLoader(file_path) loader = PyPDFLoader(file_path, extract_images=True)
elif file_ext == "csv": elif file_ext == "csv":
loader = CSVLoader(file_path) loader = CSVLoader(file_path)
elif file_ext == "rst": elif file_ext == "rst":

1
backend/requirements.txt
View File

@ -33,6 +33,7 @@ pandas
openpyxl openpyxl
pyxlsb pyxlsb
xlrd xlrd
rapidocr-onnxruntime
faster-whisper faster-whisper