MathpixPDFLoader doesn't work.

[Monketoo]

System Info

Getting ''' ValueError: Unable to send PDF to Mathpix''' while using MathpixPDFLoader.

Who can help?

No response

Information

• The official example notebooks/scripts
• My own modified scripts

Related Components

• LLMs/Chat Models
• Embedding Models
• Prompts / Prompt Templates / Prompt Selectors
• Output Parsers
• Document Loaders
• Vector Stores / Retrievers
• Memory
• Agents / Agent Executors
• Tools / Toolkits
• Chains
• Callbacks/Tracing
• Async

Reproduction

math_pix_loaded = MathpixPDFLoader(file_path)
load_list_mathpix = math_pix_loaded.load()

Expected behavior

A list of pages to be returned.

[dosubot]

Answer generated by a 🤖

Answer

I understand that you're encountering a "ValueError: Unable to send PDF to Mathpix" error when using the MathpixPDFLoader in the LangChain framework. This error typically occurs when the response from the Mathpix API does not contain a "pdf_id", which could be due to a variety of reasons such as incorrect API credentials, network issues, or issues with the PDF file itself.

Here's how we can address this issue:

1. Verify your Mathpix API credentials. These are set in the __init__ method of the MathpixPDFLoader class. Please ensure they are correct and have the necessary permissions.

2. Check your network connection. If there are any network issues, the request to the Mathpix API might fail, causing this error.

3. Inspect the PDF file you're trying to process. If there are any issues with the file (for example, if it's not a valid PDF file), the Mathpix API might not be able to process it, resulting in this error.

Please note that this is one potential solution based on the information provided. If you've checked all these points and the issue persists, it might be due to other factors not covered in this response.

If you believe this is a bug that could impact other users and you're confident in your solution, we encourage you to make a pull request. Your contribution would be greatly appreciated by the LangChain community.

If my response contradicts your experience or if the issue persists after trying these steps, I recommend upgrading to the latest version of LangChain, as the issue might have been resolved in a more recent update.

Sources

• langchain/document_loaders/pdf.py

---

This response is meant to be useful, save you time, and share context. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

[MatousEibich]

Hello, same issue, would appreciate some clarification, already paid MathPix sign up fee.

[jreinjr]

Hi! There's a bug in the MathpixPDFLoader class - in the init function, the processed_file_format variable is set to "mmd" by default. Change it to "md" and it works properly!

[sonnyjon]

Hi,

I have the same issue. Would someone please implement jrinjr's fix in the next release so that we don't have to maintain our own version of the MathpixPDFLoader class?

[efriis]

Should be fixed in 0.0.305! Thanks @jreinjr for fixing