I'd love to try it, but pretty much all my repos are >10mb. It's not because there is that much code, but because I am doing bioinformatics and the test files (for the unit tests) inflate the repo size. It would be great if there was a way to test it on just 1 large repo for perhaps a week or something, because I balk at the idea of spending $20 a month on something that I don't even know works well. This is importan…
Launch HN: Greptile (YC W24) - RAG on codebases that actually works
41–50 of 173 posts
Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#42Looks good, but there are many competitors that do exactly the same thing (even opensource ones)
Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#43Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#44Earlier quoted context omitted.
Thanks! Yeah, it’s strangely worded for what it is. We’ve emailed GitHub about it. Our permissions are read-only but since we read “on your behalf” this is technically true.
Why don't you read on your own behalf. You don't need this permission at all. It's just to harvest email addresses right?
Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#45“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…
The latter is typically the realm of requirements, design documentation, and possibly test plans.
Generating such documentation from code seems quite impossible, or at least wrong.
It is unfortunate that most open source software is lacking in such documentation, giving off bad signals to junior developers.
Edit: not to take away from the product being discussed here, which seems very useful! I am merely supporting the parent here.
Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#46“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
#47Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#48I tried asking a question about Porter and I see the error: > Oops > We couldn't access this repo. > You may need to log in to view this repository, or it might not exist.
Hey looked into this error, Porter was not processed by us yet, it does take a while for a repo to be processed initially but this link should give you the progress report + you can chat with it when its done: https://app.greptile.com/chat/github/porter-dev/porter
It also appears that the vote buttons do nothing if one is not logged in, so I'd recommend eliding them unless logged in since it's just frustrating to wonder if some JS error ate the vote or what
Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#49Earlier quoted context omitted.
Hey looked into this error, Porter was not processed by us yet, it does take a while for a repo to be processed initially but this link should give you the progress report + you can chat with it when its done: https://app.greptile.com/chat/github/porter-dev/porter
I followed the link because I was curious and it still said processing, so I navigated to the homepage and clicked "Try a popular repo" leading to https://app.greptile.com/chat/3t4qpefuh9eqckcdt0b8i?repo=pos... > which then said "We couldn't access this repo." It seems the actual syntax is app.greptile.com/chat/github/postgres/postgres -> https://app.greptile.com/chat/lfbc034nkj7w03v2kb5zp?repo=git... so wherever tha…
Re: Launch HN: Greptile (YC W24) - RAG on codebases that actually works
#50“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…