constantly got Error: Internal error while processing request.
Launch HN: Greptile (YC W24) - RAG on codebases that actually works
161–170 of 173 posts
Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#162“Where we going we don’t need docs”. That scares me… docs are among other things there to provide context and info for things not clear from why certain choices were made or not made… no way your AI is going to guess that I put that restriction because of an explicit request from product, despite it looking wrong…
Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#163Also I am getting the 'Error: Internal error while processing request'
Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#164Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#165You’re going to want to define the acronym RAG before you use it a dozen times in your marketing copy. Presumably it’s great news that I can RAG on my codebase. But I’m not sure whether I’ve ever ragged anything in my career or whether I’ll want to now. If you told us what it meant, we could probably understand what your thing does.
Thanks Jason, you're right. We spend so much time around RAG that we forget this is niche term. RAG -> retrieval augmented generation. Given a query, finding the parts of the codebase most relevant to the query, and supplying it to the LLM so it can answer the query. The typical way to do this is semantic similarity, or chunking + embedding the corpus being searched, embedding the query and finding the k most cosine-…
Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#166Earlier quoted context omitted.
I like to use different email addresses for different services. Please just ask me for an email address to use instead of using the one on github.
That makes sense, we should change that. Thanks for pointing it out.
Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#167Earlier quoted context omitted.
Thanks Jason, you're right. We spend so much time around RAG that we forget this is niche term. RAG -> retrieval augmented generation. Given a query, finding the parts of the codebase most relevant to the query, and supplying it to the LLM so it can answer the query. The typical way to do this is semantic similarity, or chunking + embedding the corpus being searched, embedding the query and finding the k most cosine-…
Thanks. Even that is pretty dense for someone who hasn’t been living and breathing LLMs for the last year. https://xkcd.com/2501/ You’ll want to find a balance between telling people what your thing does with no jargon or acronyms whatsoever, while signaling to people who know as much as you about this stuff (all four of them) that it’s got those cool ingredients. All the best.
Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#168“Where we going we don’t need docs”. That scares me… docs are among other things there to provide context and info for things not clear from why certain choices were made or not made… no way your AI is going to guess that I put that restriction because of an explicit request from product, despite it looking wrong…
Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#169I only get 'Error: Internal error while processing request.' when I try to run queries. I tested three different repos, same error message appeared for each repo.
Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#170very nice! FYI the 'free coffee' link ( https://calendly.com/dakshgupta/free-coffee ) identifies you as " Daksh, co-founder/CEO at Onboard." Also I am getting the 'Error: Internal error while processing request'