5 comments

  • Oras18 hours ago
    One of the challenges I have with RAG is excluding table of contents, headers/footers and appendices from PDFs.

    Is there a tool/technique to achieve this? I’m aware that I can use LLMs to do so, or read all pages and find identical text (header/footer), but I want to keep the page number as part of the metadata to ensure better citation on retrieval.

      • Oras14 hours ago
        Thank you, this is a mix of OCR and LLM, I was thinking if there might be a library to avoid using that.

        A better approach will be using Textract as it maintains the flow, such as if you have a table going across multiple pages.

        Btw, tesseract is not that good in getting accurate data from tables. Use it with caution especially in financial context.

        I have made an open source tool to show missing data from tesseract and easy ocr https://github.com/orasik/parsevision/

        • prsdm11 hours ago
          Nice I really liked it!
    • jonathan-adly13 hours ago
      I would check out vision models as a technique to go around OCR errors.

      ColPali is the standard implementation & SOTA. Much better than OCR. We maintain a ready to go retrieval API that implements this: https://github.com/tjmlabs/ColiVara

    • throwup23813 hours ago
      You’ll need other heuristics for ToC and indices but headers/footers are easy to detect via n-gram deduplication. You’ll want to figure out some rolling logic to handle chapter changes though.
      • ellisv10 hours ago
        Headers/footers are also positional.
  • jonathan-adly13 hours ago
    I would strongly advise against people learning based on LangChain.

    It is abstraction hell, and will set you back thousands of engineers hours the moment you want to do something differently.

    RAG is actually very simple thing to do; just too much VC money in the space & complexity merchants.

    Best way to learn is outside of notebooks (the hard parts of RAG is all around the actual product), and use as little frameworks as possible.

    My preferred stack is a FastAPI/numpy/redis. Simple as pie. You can swap redis for pgVector/Postgres when ready for the next complexity step.

    • ellisv10 hours ago
      I'd like to hear more about this – both your reasoning against LangChain and suggestions for alternatives.

      My experience with LangChain has been a mixed bag. On the one hand it has been very easy to get up and running quickly. Following their examples actually works!

      Trying to go beyond the examples to mix and match concepts was a real challenge because of the abstractions. As with any young framework in a fast moving field the concepts and abstractions seem to be changing quickly, thus examples within the documentation show multiple ways to do something but it isn't clear which is the "right" way.

    • jackmpcollins10 hours ago
      I'd be really interested to hear what abstractions you would find useful for RAG. I'm building magentic which is focused on structured outputs and streaming, but also enables RAG [0], though currently has no specific abstractions for it.

      [0] https://magentic.dev/examples/rag_github/

    • pchangr12 hours ago
      Those were exactly my thoughts.. however I haven’t been able to find much material on how to implement this without relying on LangChain.. do you know of any beginners material I could use to fill my gaps?
  • krawczstef20 hours ago
    +1 for vanilla code without LangChain.
    • hbamoria19 hours ago
      I believe you're looking for notebooks w/o Langchain. We plan to publish them in next few days :)
    • imworkingrn18 hours ago
      whats wrong with langchain ?
      • ErikBjare17 hours ago
        I haven't used it in a year, but my experience was it frequently broke in all sorts of ways. I have since avoided it like the plague.
        • imworkingrn16 hours ago
          I hear you. Had the same experience. It's matured a lot since then though. Got back to it a few weeks ago and it feels surprisingly stable.
          • chompychop14 hours ago
            Does it still have the "abstraction hell" issue when trying to work with it for custom, non out-of-the-box use cases?
          • prsdm15 hours ago
            it's much more stable now.
            • sauwan12 hours ago
              Does it still put you in dependency hell though, where you can't add new packages without causing tons of version conflicts?
              • efriis7 hours ago
                Howdy! Erick from LangChain here. If anyone is seeing version conflicts on particular packages, please let me know!

                These usually stem from overly strict constraints in the underlying sdks for the integrations, and in general we've been pretty successful asking for those constraints to be loosened. The main "problem" constraint we've seen in the past has been on httpx. Curious if you've seen others!

    • chompychop19 hours ago
      Huh? All of their notebooks use LangChain.
  • dmezzetti13 hours ago
    Thanks for sharing.

    If you want notebooks that do some of this with local open models: https://github.com/neuml/txtai/tree/master/examples and here: https://gist.github.com/davidmezzetti

    • prsdm11 hours ago
      Thanks for sharing these resources! We’ll definitely take a look.
  • 12 hours ago
    undefined