githubnext VS gpt-repository-loader

GitHub Copilot Labs is a tool run by the GitHub Next team, the R&D team of GitHub, to figure out new paths and methods to enable developers to benefit from Copilot in a new way.

Check Github Next [0], much more AI to come. All the broad features working together, while delighting users, create ever more vendor lock-in. Github is allowed to become this huge one-stop-shop online development platform. With increasing platform dominance, the enshittification inevitably follows.

[0] https://githubnext.com

GitHub Next

A few notable examples of these leaps in AI technology include GPT-3.5, GPT-4, ChatGPT, Midjourney, Dall-e 2, AutoGPT, and Github Next.

You can keep an eye on GitHub Next to see what they're currently working at and sign in for the waitlists.

The GitHub Next (their Skunkworks) page has a card for this under 'GitHub Copilot for your codebase'. It's currently WIP.

FYI, after digging down a few links from there and winding up at the GitHub Next org page[1], seeing the verified email [email protected] and the official site link to https://githubnext.com was enough validation for me.

Can't wait for Voice Copilot :)

1: https://github.com/githubnext

As an industry, we’re learning to prioritize accessibility for the user. But, what about the developer? The GitHub Next team is making coding more accessible for developers of all backgrounds with the following experimental features:

Hey GitHub is part of GitHub Next, and if you don't know what it is let me quote their website:

A good approach is to use a tool like this that turns an entire repo into a single file you can upload to GPT: https://github.com/mpoon/gpt-repository-loader (not my own repo). I find that much cleaner than doing a bunch of copy-and-pasting or uploading files one-by-one.

I have made an AI-bot that knows ALL of NextJS set up on my localhost. I can ask anything and it outputs the answer, context, examples and references. I used https://github.com/mpoon/gpt-repository-loader to create the files and loaded them into https://github.com/dabit3/semantic-search-nextjs-pinecone-langchain-chatgpt , then added OpenAI API to shape the { result } to my wishes. Works decently

You might start with this: https://github.com/mpoon/gpt-repository-loader

You may be interested in this: https://github.com/mpoon/gpt-repository-loader

I've had access to the 32k model for a bit and I've been using this to collect and stuff codebases into the context: https://github.com/mpoon/gpt-repository-loader

It works really well, you can tell it to implement new features or mutate parts of the code and it having the entire (or a lot of) the code in its context really improves the output.

The biggest caveat: shit is expensive! A full 32k token request will run you like $2, if you do dialog back and forth you can rack up quite the bill quickly.

https://github.com/mpoon/gpt-repository-loader here is open source take on part of this concept