Re:Show HN: GPTDuck – Ask questions about any GitHub repo
by penguinten on Thursday January 05, 2023 @02:11PM
(#34264902)
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.
Re:Show HN: GPTDuck – Ask questions about any GitHub repo
by LunaticDragon on Thursday January 05, 2023 @03:27PM
(#34266053)
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.
Re:Show HN: GPTDuck – Ask questions about any GitHub repo
by iamflimflam1 on Thursday January 05, 2023 @03:41PM
(#34266227)
Would love some more information on how to do this. Can you share details or point to a resource?
Re:Show HN: GPTDuck – Ask questions about any GitHub repo
by joshka on Thursday January 05, 2023 @09:05PM
(#34270015)
I'm curious if can share LoC -> token count metrics?
Re:Show HN: GPTDuck – Ask questions about any GitHub repo
by realYitzi on Thursday January 05, 2023 @05:27PM
(#34267775)
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
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?