PyPDFParser does not take into account filters returned as arrays.

[haroldsnyers]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

The following Code langchain_community/document_loaders/parsers/pdf.py

class PyPDFParser(BaseBlobParser):

...

def extract_images_from_page(self, page: pypdf._page.PageObject) -> str:
        """Extract images from a PDF page and get the text using images_to_text.

        Args:
            page: The page object from which to extract images.

        Returns:
            str: The extracted text from the images on the page.
        """
        if not self.images_parser:
            return ""
        from PIL import Image

        if "/XObject" not in cast(dict, page["/Resources"]).keys():
            return ""

        xObject = page["/Resources"]["/XObject"].get_object()  # type: ignore[index]
        images = []
        for obj in xObject:
            print(f"pdf object {obj} - {xObject[obj]}")
            np_image: Any = None
            if xObject[obj]["/Subtype"] == "/Image":
                if xObject[obj]["/Filter"][1:] in _PDF_FILTER_WITHOUT_LOSS:
                    height, width = xObject[obj]["/Height"], xObject[obj]["/Width"]

                    np_image = np.frombuffer(
                        xObject[obj].get_data(), dtype=np.uint8
                    ).reshape(height, width, -1)
                elif xObject[obj]["/Filter"][1:] in _PDF_FILTER_WITH_LOSS:
                    np_image = np.array(Image.open(io.BytesIO(xObject[obj].get_data())))

                else:
                    logger.warning("Unknown PDF Filter!")
                if np_image is not None:
                    image_bytes = io.BytesIO()
                    Image.fromarray(np_image).save(image_bytes, format="PNG")
                    blob = Blob.from_data(image_bytes.getvalue(), mime_type="image/png")
                    image_text = next(self.images_parser.lazy_parse(blob)).page_content
                    images.append(
                        _format_inner_image(blob, image_text, self.images_inner_format)
                    )
        return _FORMAT_IMAGE_STR.format(
            image_text=_JOIN_IMAGES.join(filter(None, images))
        )

Error Message and Stack Trace (if applicable)

No response

Description

I am trying to parse PDF scans with PyPdfParser and PyTesseract. The image parsing is generating a bug as the the extracted objects for the /Filter returns sometimes an array, sometimes a string.

Examples
pdf object /Im1 - {'/Type': '/XObject', '/Subtype': '/Image', '/Width': 1653, '/Height': 2338, '/BitsPerComponent': 1, '/ColorSpace': '/DeviceGray', '/Filter': '/CCITTFaxDecode', '/DecodeParms': {'/K': -1, '/Columns': 1653, '/Rows': 2338}}
pdf object /I0 - {'/Type': '/XObject', '/Subtype': '/Image', '/Width': 2478, '/Height': 3488, '/BitsPerComponent': 8, '/ColorSpace': '/DeviceRGB', '/Filter': ['/DCTDecode'], '/DecodeParms': [{}]}

Suggested code fix:

if xObject[obj]["/Subtype"] == "/Image":
                filter = xObject[obj]["/Filter"][1:] if type(xObject[obj]["/Filter"]) == generic._base.NameObject else xObject[obj]["/Filter"][0][1:]
                if filter in _PDF_FILTER_WITHOUT_LOSS:
                    height, width = xObject[obj]["/Height"], xObject[obj]["/Width"]

                    np_image = np.frombuffer(
                        xObject[obj].get_data(), dtype=np.uint8
                    ).reshape(height, width, -1)
                elif filter in _PDF_FILTER_WITH_LOSS:
                    np_image = np.array(Image.open(io.BytesIO(xObject[obj].get_data())))

                else:
                    logger.warning("Unknown PDF Filter!")
                if np_image is not None:
                    image_bytes = io.BytesIO()
                    Image.fromarray(np_image).save(image_bytes, format="PNG")
                    blob = Blob.from_data(image_bytes.getvalue(), mime_type="image/png")
                    image_text = next(self.images_parser.lazy_parse(blob)).page_content
                    images.append(
                        _format_inner_image(blob, image_text, self.images_inner_format)
                    )

System Info

System Information

OS: Darwin
OS Version: Darwin Kernel Version 23.6.0: Mon Jul 29 21:14:04 PDT 2024; root:xnu-10063.141.2~1/RELEASE_ARM64_T8122
Python Version: 3.12.8 (main, Dec 3 2024, 18:42:41) [Clang 16.0.0 (clang-1600.0.26.4)]

Package Information

langchain_core: 0.3.40
langchain: 0.3.19
langchain_community: 0.3.18
langsmith: 0.1.129
langchain_google_community: 2.0.7
langchain_google_vertexai: 2.0.14
langchain_text_splitters: 0.3.6

Optional packages not installed

langserve

Other Dependencies

aiohttp<4.0.0,>=3.8.3: Installed. No version info available.
anthropic[vertexai]: Installed. No version info available.
async-timeout<5.0.0,>=4.0.0;: Installed. No version info available.
beautifulsoup4: 4.13.3
dataclasses-json<0.7,>=0.5.7: Installed. No version info available.
db-dtypes: Installed. No version info available.
gapic-google-longrunning: Installed. No version info available.
google-api-core: 2.24.1
google-api-python-client: 2.162.0
google-auth: 2.38.0
google-auth-httplib2: 0.2.0
google-auth-oauthlib: Installed. No version info available.
google-cloud-aiplatform: 1.82.0
google-cloud-bigquery: 3.30.0
google-cloud-bigquery-storage: Installed. No version info available.
google-cloud-contentwarehouse: Installed. No version info available.
google-cloud-core: 2.4.2
google-cloud-discoveryengine: Installed. No version info available.
google-cloud-documentai: Installed. No version info available.
google-cloud-documentai-toolbox: Installed. No version info available.
google-cloud-speech: Installed. No version info available.
google-cloud-storage: 2.19.0
google-cloud-texttospeech: Installed. No version info available.
google-cloud-translate: Installed. No version info available.
google-cloud-vision: Installed. No version info available.
googlemaps: Installed. No version info available.
grpcio: 1.70.0
httpx: 0.28.1
httpx-sse: 0.4.0
httpx-sse<1.0.0,>=0.4.0: Installed. No version info available.
jsonpatch<2.0,>=1.33: Installed. No version info available.
langchain-anthropic;: Installed. No version info available.
langchain-aws;: Installed. No version info available.
langchain-cohere;: Installed. No version info available.
langchain-community;: Installed. No version info available.
langchain-core<1.0.0,>=0.3.34: Installed. No version info available.
langchain-core<1.0.0,>=0.3.35: Installed. No version info available.
langchain-core<1.0.0,>=0.3.37: Installed. No version info available.
langchain-deepseek;: Installed. No version info available.
langchain-fireworks;: Installed. No version info available.
langchain-google-genai;: Installed. No version info available.
langchain-google-vertexai;: Installed. No version info available.
langchain-groq;: Installed. No version info available.
langchain-huggingface;: Installed. No version info available.
langchain-mistralai: Installed. No version info available.
langchain-mistralai;: Installed. No version info available.
langchain-ollama;: Installed. No version info available.
langchain-openai;: Installed. No version info available.
langchain-text-splitters<1.0.0,>=0.3.6: Installed. No version info available.
langchain-together;: Installed. No version info available.
langchain-xai;: Installed. No version info available.
langchain<1.0.0,>=0.3.19: Installed. No version info available.
langsmith<0.4,>=0.1.125: Installed. No version info available.
langsmith<0.4,>=0.1.17: Installed. No version info available.
numpy<2,>=1.26.4;: Installed. No version info available.
numpy<3,>=1.26.2;: Installed. No version info available.
orjson: 3.10.15
packaging<25,>=23.2: Installed. No version info available.
pandas: 2.1.1
pyarrow: 19.0.1
pydantic: 2.10.6
pydantic-settings<3.0.0,>=2.4.0: Installed. No version info available.
pydantic<3.0.0,>=2.5.2;: Installed. No version info available.
pydantic<3.0.0,>=2.7.4: Installed. No version info available.
pydantic<3.0.0,>=2.7.4;: Installed. No version info available.
PyYAML>=5.3: Installed. No version info available.
requests: 2.32.3
requests<3,>=2: Installed. No version info available.
SQLAlchemy<3,>=1.4: Installed. No version info available.
tenacity!=8.4.0,<10,>=8.1.0: Installed. No version info available.
tenacity!=8.4.0,<10.0.0,>=8.1.0: Installed. No version info available.
typing-extensions>=4.7: Installed. No version info available.

[eyurtsev]

cc @pprados -- any idea?

[pprados]

@eyurtsev
I will take this ticket.

[pprados]

@haroldsnyers
Thank you for the suggested correction. Can you send me an example of a file that fails?