Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

🦆🦆🦆 GPTDuck - question answering against any Github repository. Simply type in a Github repo, and then ask questions about the repo. Here's me asking a questiont about how GPT News works. Try it out here: or in Slack via

333,664 Aufrufe • vor 3 Jahren •via X (Twitter)

10 Kommentare

Profilbild von Gary Wu
Gary Wuvor 3 Jahren

Biggest limitation right now is repo size - only supports repos smaller than 100MB. Support for private repos is in beta - retweet and comment for free access. Am playing with code generation as well, but results are a bit finicky. Feel free to DM me if any issues / questions.

Profilbild von Gary Wu
Gary Wuvor 3 Jahren

Built with @langchain and @OpenAI embeddings. The name comes from 'rubber duck debugging' - this is an AI duck that is hopefully more helpful.

Profilbild von Gary Wu
Gary Wuvor 3 Jahren

ok I've been GitHub rate limited - fixing now

Profilbild von Gary Wu
Gary Wuvor 3 Jahren

Rate limits fixed - sign up and add your own Github access token to get around 500 errors. Now my @supabase instance is struggling to stay alive💀

Profilbild von Jerry Liu
Jerry Liuvor 3 Jahren

@gpt_index Nice! Do you just scrape the README or all files within the repo? Depending on which queries you'd want to support, I wonder if @gpt_index could help you synthesize some of these answers through an index struct

Profilbild von Gary Wu
Gary Wuvor 3 Jahren

@gpt_index It indexes the entire repo! So you have access to functions as well if needed. Absolutely - want to add it for larger repos especially.

Profilbild von Harrison Chase
Harrison Chasevor 3 Jahren

@gpt_index very cool! are you using some sort of vector db + semantic search under the hood?

Profilbild von Gary Wu
Gary Wuvor 3 Jahren

@gpt_index yup, exactly that!

Profilbild von Charly Wargnier
Charly Wargniervor 3 Jahren

@gpt_index Great app! I've got this issue, is this expected?

Profilbild von James M
James Mvor 3 Jahren

@gpt_index Love it, I've built something similar that indexes Confluence Spaces and Zendesk Academy (but only in memory) Are you taking all the code in chunks of up to 2046 tokens or splitting down by file/function?

Ähnliche Videos