Skip to content

The agent engineering platform.

community: Fix the problem of error reporting when OCR extracts text from PDF. (#29378)

江同学呀a1e62070d03c
diff --git a/libs/community/langchain_community/document_loaders/parsers/pdf.py b/libs/community/langchain_community/document_loaders/parsers/pdf.py
index 254849df80..eb65b73f1d 100644
--- a/libs/community/langchain_community/document_loaders/parsers/pdf.py
+++ b/libs/community/langchain_community/document_loaders/parsers/pdf.py
@@ -311,6 +311,12 @@ class PyPDFParser(BaseBlobParser):
)
elif xObject[obj]["/Filter"][1:] in _PDF_FILTER_WITH_LOSS:
images.append(xObject[obj].get_data())
+ elif (
+ isinstance(xObject[obj]["/Filter"], list)
+ and xObject[obj]["/Filter"]
+ and xObject[obj]["/Filter"][0][1:] in _PDF_FILTER_WITH_LOSS
+ ):
+ images.append(xObject[obj].get_data())
else:
warnings.warn("Unknown PDF Filter!")
return extract_from_images_with_rapidocr(images)