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

Show HN: How we leapfrogged traditional vector based RAG with a 'language map'

twitter.com

Post reply on HN
Print view View original

31–40 of 62 posts

Re: Show HN: How we leapfrogged traditional vector based RAG with a 'language map'

#31

Post by danenania »

manishsharan wrote: post #30
anotherpaulg wrote: post #11

I agree that many AI coding tools have rushed to adopt naive RAG on code. Have you done any quantitative evaluation of your wiki style code summaries? My first impression is that they might be too wordy and not deliver valuable context in a token efficient way. Aider uses a repository map [0] to deliver code context. Relevant code is identified using a graph optimization on the repository's AST & call graph, not vect…

I tried using Aider but my codebase is a mix of Clojure Clojurescript and Java . I gave up making it work for me it as it created more issues for me. What I really hated about Aider was that it made code changes without my approval.

You might be interested in my project Plandex[1]. It’s similar to aider in some ways, but one major difference is that proposed changes are accumulated in a version-controlled sandbox rather than being directly applied to project files.

1 - https://github.com/plandex-ai/plandex

Re: Show HN: How we leapfrogged traditional vector based RAG with a 'language map'

#33

Post by oshams »

kordlessagain wrote: post #29

I've been working on Webwright[1] for a month after having prototyped a few different terminal solutions for a coding agents. Webwright manifests in a psuedo terminal in Powershell or terminal on MacOS. Using Claude.AI, I determined the `ast` package would be suitable (for Python scanning), so had Webwright author a new function module to scan the project and assemble a list of functions, function calls, imports, and…

That's awesome thanks!

Re: Show HN: How we leapfrogged traditional vector based RAG with a 'language map'

#34

Post by oshams »

tlarkworthy wrote: post #10

This is literate programming! Why not just put the codebase in the wiki and not have two representations diverging. Why can't we have diagrams and links in code??? We can, like https://observablehq.com notebooks, it's a better representation for understanding.

patience ... all part of our plan :)

Re: Show HN: How we leapfrogged traditional vector based RAG with a 'language map'

#35

Post by oshams »

lmeyerov wrote: post #23

I've been curious about this use case, so cool to see, and more so, to know it worked! This is essentially a realization of how graph RAG flavor systems work under the hood. Basically you create hierarchical summary indexes, such as topical cross-document ones, and tune the summaries to your domain. At retrieval time, one question will be able to leverage richer multi-hop concepts that span ideas that are individuall…

Nice!

Re: Show HN: How we leapfrogged traditional vector based RAG with a 'language map'

#36

Post by oshams »

spirobelv2 wrote: post #5

it wants me to login to ask a question I will just keep using phind you have vc dollars - sponsor a public free search over open source repos. Also think about what happens when your question touches multiple repos. I tried a similar "search github repo with ai" product before, but it led me right back to phind, when it couldnt answer a question that required specific information from the repositiory as well as a goo…

It's funny to see this because from my perspective we've done this on a pretty scrappy budget. That said we're thinking of adding an open access for select repos. Why is logging in so terrible? We want to get to know our users.

Re: Show HN: How we leapfrogged traditional vector based RAG with a 'language map'

#37

Post by oshams »

langcss wrote: post #8

This sort of approach always made more sense to me than RAG. I am less likely to try RAG than something that feeds the LLM what it actually needs. RAG is risky in providing piecemeal information that confuses the LLM. The way I thought would work and like to try out is ask the LLM what info it wants next from an index of contents. Like a book. That index can be LLM generated or not. Then backtrack as you don't need t…

Thanks!

Re: Show HN: How we leapfrogged traditional vector based RAG with a 'language map'

#38

Post by oshams »

magicalhippo wrote: post #25

So no free lunch? Making a detailed wiki of all the code would take several developer-years for us, and we're just a handful of developers. Or is the wiki generated somehow?

i actually think the world has many free lunches for those looking hard enough :)
Post reply on HN