News for hackers. Stuff that matters.
Re:Ask HN: Is RAG the Future of LLMs? by mark_l_watson on Monday April 15, 2024 @10:39AM (#40041153)
I wrote a book on LangChain and LlamaIndex about 14 months ago, and at the time I thought that RAG style applications were great, but now I am viewing them as being more like material for demos. I am also less enthusiastic about LangChain and LlamaIndex; they are still useful, but the libraries are a moving target and often it seems best to just code up what I need by hand. The moving target issue is huge for me, updating my book frequently has been a major time sync.

I still think LLMs are the best AI tech/tools since I started getting paid to be an AI practitioner in 1982, but that is a low bar of achievement given that some forms of Symbolic AI failed to ever scale to solve real problems.

Re:Ask HN: Is RAG the Future of LLMs? by cl42 on Monday April 15, 2024 @03:47PM (#40044848)
Do you have a problem with LangChain and LlamaIndex due to their changing codebases/APIs/etc., or do you think there's a fundamental issue with RAG itself?
Re:Ask HN: Is RAG the Future of LLMs? by mark_l_watson on Monday April 15, 2024 @04:59PM (#40045513)
Maybe a mixture of both?

I think both projects were super useful, grateful for them. There is a lot of utility tucked away in both projects.

A year ago,I started using LLM APIs in non-Python languages and realized that sometimes building from scratch is better.

Re:Ask HN: Is RAG the Future of LLMs? by cl42 on Monday April 15, 2024 @05:19PM (#40045720)
Thanks for clarifying. I generally agree with you -- I prefer direct API calls versus weird/poor abstractions. The only abstraction I use is one that standardizes the API calls/data structures between Gemini/GPT-x/Llama 2/Claude.

That being said, I do use RAG a lot (though generally code most of the implementations myself).

Re:Ask HN: Is RAG the Future of LLMs? by shuss on Wednesday April 17, 2024 @10:21PM (#40072318)
Fast changing libraries are a huge pain. That's why a no-code approach like Unstract (https://github.com/zipstack/unstract) makes sense.