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

Post by spirobelv2 » Sun, Jul 21, 2024, 4:32 AM UTC

oshams wrote: post #36

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.

it is though being the little guy.

But that is not my problem. I am just a consumer. I will use what ever is the best and pragmatic solution to my problem.

I even logged in to phind after a while because it is nice to have access to my old chats.

But you need to provide value first before I bother with this.

Why do I need to explain these basic things?

pls dont get defensive when you get free feedback. not a good sign

Post by zbyforgotp » Sun, Jul 21, 2024, 6:50 AM UTC

janalsncm wrote: post #19

zbyforgotp wrote: post #17

Earlier quoted context omitted.

What you describe sounds like Agetic RAG https://zzbbyy.substack.com/p/agentic-rag

> The traditional way to do RAG is to find information relevant to a query - and then incorporate it into the LLM prompt together with the question we want it to answer. Technically this is incorrect. The original RAG paper used a seq2seq generator (BART) and involved two methods: RAG sequence and RAG token. RAG sequence used the same fixed documents and appended them to the input query (note, this is different from…

Traditional does not equate original. The original technique was never used widely and cannot be called the traditional way.

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

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