[wizeman]

This appears to be quite nice assuming it works, but I wonder: how does this work?

I thought ChatGPT could only process a very limited context (a few thousand words or so) and this claims to work for repositories <100 MB, which is gigantic in comparison.

The site says: "we will download [the repo] to the server and create embeddings against the code". What kind of embeddings are these?

[penguinten]

It uses the OpenAI embedding models to get around the context window problem. You can compress large amounts of text/code into just a few tokens.

[LunaticDragon]

Can you elaborate on this? What is the input to the GPT in that case? I was under the impression that GPT is given an array of tokens and it produces one token as its output.

[iamflimflam1]

Would love some more information on how to do this. Can you share details or point to a resource?

[cipherpro]

https://beta.openai.com/docs/guides/embeddings/use-cases

[joshka]

I'm curious if can share LoC -> token count metrics?

[realYitzi]

I don't know about embeddings, but it was able to decode a URL encoded string into a javascript animated SVG. So larger texts can be encoded and still "understood." You probably wouldn't even have to declare your encoding method. https://www.tiktok.com/@y.i.t.z.i/video/7184820436839042306