codesearch VS weggli

Hi folks, I created an open-source codebase search tool.

Just enter any public Github URL and your search query to get top matching functions on the repo.

Source Code: https://github.com/rahuldan/codesearch

Made it using the OpenAI's embeddings API, FAISS and Postgres.

Currently supports only Python and vanilla Javascript projects. And the max repo size is 100MB

You can self-host using Docker setup from my Github (This would allow you to index local repos)

Would love to hear your feedback

Link: https://github.com/rahuldan/codesearch

Great project!!

I was building something on similar lines. It is a semantic search engine for codebases using Openai's embedding and FAISS https://github.com/rahuldan/codesearch

It fetches the functions in the code for a query

Hey really cool project!!

I also built a semantic search engine for codebases using Openai's embedding and FAISS https://github.com/rahuldan/codesearch

Hi, I recently created an open-source project that does semantic search on code bases. You can check it out on https://github.com/rahuldan/codesearch

Would love to hear your feedback

JPEGLI = A small JPEG

The suffix -li is used in Swiss German dialects. It forms a diminutive of the root word, by adding -li to the end of the root word to convey the smallness of the object and to convey a sense of intimacy or endearment.

This obviously comes out of Google Zürich.

Other notable Google projects using Swiss German:

https://github.com/google/gipfeli high-speed compression

Gipfeli = Croissant

https://github.com/google/guetzli perceptual JPEG encoder

Guetzli = Cookie

https://github.com/weggli-rs/weggli semantic search tool

Weggli = Bread roll

https://github.com/google/brotli lossless compression

Brötli = Small bread

I use weggli quite frequently for security analysis. Are there any plans for friendly competition in terms of equivalent features (not:, subexpressions, etc.).

Is this similar to weggli? https://github.com/googleprojectzero/weggli