rikuthinks

Results 4 issues of rikuthinks

Currently we have support for embeddings, and we're able to save those embeddings but there are no vector database integrations available to scale the implementation for large amounts of vectors....

For PDFs: https://github.com/kartik1998/pdf-images https://github.com/naptha/tesseract.js#tesseractjs Spent many hours experimenting with the best way to extract text data from PDFs. Tried a couple different libraries - they all had problems preserving whitespace....

Would love to see a db implemented to save previous docs that are uploaded.

Would like to play around with this repo on local. Perhaps a little how-to on implementing environment variables to set the API keys over the user adding them.