forked from open-webui/open-webui
Merge pull request #1050 from jannikstdl/rag-pdf-ocr
feat: added ocr functionality to the pdf loader
This commit is contained in:
commit
8fb5f54751
2 changed files with 2 additions and 1 deletions
|
@ -425,7 +425,7 @@ 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":
|
||||||
|
|
|
@ -34,6 +34,7 @@ pandas
|
||||||
openpyxl
|
openpyxl
|
||||||
pyxlsb
|
pyxlsb
|
||||||
xlrd
|
xlrd
|
||||||
|
rapidocr-onnxruntime
|
||||||
|
|
||||||
faster-whisper
|
faster-whisper
|
||||||
|
|
||||||
|
|
Loading…
Reference in a new issue