Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Open-Source Colab Notebooks to Implement Advanced RAG Techniques

github.com

Post reply on HN
Print view View original

21–29 of 29 posts

Re: Show HN: Open-Source Colab Notebooks to Implement Advanced RAG Techniques

#21

Post by memhole »

pchangr wrote: post #18
jonathan-adly wrote: post #15

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 framework…

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?

Start with ignoring 90% of the stuff you read about and realize you’re only manipulating strings to send to an API.

Re: Show HN: Open-Source Colab Notebooks to Implement Advanced RAG Techniques

#22

Post by prsdm »

Oras wrote: post #11
prsdm wrote: post #9

Earlier quoted context omitted.

This might help you: https://github.com/langchain-ai/langchain/blob/master/cookbo...

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…

Nice I really liked it!

Re: Show HN: Open-Source Colab Notebooks to Implement Advanced RAG Techniques

#23

Post by prsdm »

dmezzetti wrote: post #13

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

Thanks for sharing these resources! We’ll definitely take a look.

Re: Show HN: Open-Source Colab Notebooks to Implement Advanced RAG Techniques

#24

Post by ellisv »

jonathan-adly wrote: post #15

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 framework…

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.

Re: Show HN: Open-Source Colab Notebooks to Implement Advanced RAG Techniques

#25

Post by ellisv »

throwup238 wrote: post #16
Oras wrote: post #6

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.

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.

Headers/footers are also positional.

Re: Show HN: Open-Source Colab Notebooks to Implement Advanced RAG Techniques

#26

Post by jackmpcollins »

jonathan-adly wrote: post #15

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 framework…

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/

Re: Show HN: Open-Source Colab Notebooks to Implement Advanced RAG Techniques

#27

Post by dmezzetti »

pchangr wrote: post #18
jonathan-adly wrote: post #15

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 framework…

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?

An alternative you can try is txtai (https://github.com/neuml/txtai).

RAG section: https://github.com/neuml/txtai?tab=readme-ov-file#retrieval-...

Disclaimer: I'm the primary developer

Re: Show HN: Open-Source Colab Notebooks to Implement Advanced RAG Techniques

#28

Post by efriis »

sauwan wrote: post #19
prsdm wrote: post #10

Earlier quoted context omitted.

it's much more stable now.

Does it still put you in dependency hell though, where you can't add new packages without causing tons of version conflicts?

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!

Re: Show HN: Open-Source Colab Notebooks to Implement Advanced RAG Techniques

#29

Post by Jet_Xu »

Interesting discussion! While RAG is powerful for document retrieval, applying it to code repositories presents unique challenges that go beyond traditional RAG implementations. I've been working on a universal repository knowledge graph system, and found that the real complexity lies in handling cross-language semantic understanding and maintaining relationship context across different repo structures (mono/poly).

Has anyone successfully implemented a language-agnostic approach that can: 1. Capture implicit code relationships without heavy LLM dependency? 2. Scale efficiently for large monorepos while preserving fine-grained semantic links? 3. Handle cross-module dependencies and version evolution?

Current solutions like AST-based analysis + traditional embeddings seem to miss crucial semantic contexts. Curious about others' experiences with hybrid approaches combining static analysis and lightweight ML models.

Post reply on HN