Drazen

Results 37 comments of Drazen

Currently mostly pinecone but have been looking into open source ones as well. PDFs, MS Office docx and ppt mostly. Starting to look into audio transcriptions as well using https://github.com/guillaumekln/faster-whisper

I think HTML documents should be chunked just like any other document. Extract all text from `` and chunk based on chunk size. Not use HTML tags as a delimiter....

Same issue here - $request_env always nil. Did you figure this out?

This issue does not only impact Rust. Any chance this can be done for Ruby / ERB templates as well? Tailwind support just seems broken for weeks now - https://github.com/zed-industries/zed/issues/27118...

Giving this a bump. Would love to see it

Thanks a lot for the explainer. > Using Model.reindex! is the intended way, and can be optimized with: > > Defining a meilisearch_import scope to limit queried attributes and relationships...