Goopt VS codesearch.ai

https://github.com/jokenox/Goopt procedurally generated

https://codesearch.ai/

- Brave (recently started its own index but often falls back on Google's)

Love to see projects like Marginalia and now this. These projects also make meta search engines like Searx[0] that much more powerful.

Anyways since I'm in the business of listing out relevant projects, other code-centered search engines you might wanna check out are searchcode.com[1], codesearch.ai[2], symbolhound[3], and publicwww.com[4] (some of these are often down, but might still be good to learn from)

[0] https://searx.tuxcloud.net/

[1] https://searchcode.com/

[2] https://codesearch.ai/

[3] http://symbolhound.com/

[4] https://publicwww.com/

Hey, I'm Rok, a software engineer at Sourcegraph, and I've been working on an experimental AI-powered code search engine called codesearch.ai as a side project. It answers natural language queries with functions indexed from GitHub.com and StackOverflow.

It's not a pure CoPilot alternative, but I'd put https://codesearch.ai into the mix (disclaimer, it's my side project).

It is a semantic code search tool that can be queried using natural language. It provides decent answers to a variety of questions, and I've been finding myself using it quite often to "autocomplete" various mundane tasks. For example, plotting with matplotlib, making http requests in Go, running multiple goroutines, etc. - things where I would usually reach for Google. It doesn't provide a straightforward ready-to-run answer like CoPilot, but it does provide a way to help yourself. It all depends on what you prefer and how you learn. Arguably, having to read the code before you use it makes it more likely it will stick in your brain.

Great read, thanks for sharing. Would love to see the natural language + code mixed in there :)

I've been interested in contrastive learning for a while, mainly as a means to train semantic code search models. OpenAI released a great paper on this topic called Text and Code Embeddings by Contrastive Pre-Training[1] that outlines the approach. I've used it as a base to build https://codesearch.ai [2] with pretty good results.

[1] https://arxiv.org/pdf/2201.10005.pdf

It looks like the UI for https://codesearch.ai/ was developed in [some combination of Go and React javascript](https://github.com/sourcegraph/codesearch.ai/tree/main/codesearch-ai-data/cmd/web)?