Hacker News new | ask | show | jobs
by mrg3_2013 1266 days ago
How did you implement this ? Would love to learn more
1 comments

From what I can see, they download the repo to their server, generate per-function semantic embeddings (which will no doubt cost them at scale) [1], then use some combination of GPT-3 and Codex prompted with something like "Here's the source code of a git repo. Answer the following questions about it: {USER_QUESTION}."

[1] https://beta.openai.com/docs/guides/embeddings

Thanks for sharing this!

I found this guide/example from OpenAI which was pretty clear:

https://github.com/openai/openai-cookbook/blob/main/examples...