dwata icon indicating copy to clipboard operation
dwata copied to clipboard

Import Markdown files

Open brainless opened this issue 1 year ago • 3 comments

As a user I would like to import Markdown files, for example from my company documentation. A folder containing Markdown files should become a data source.

brainless avatar Apr 29 '24 14:04 brainless

I will look at three Rust crates for this and select one that has the friendliest API:

  • https://github.com/wooorm/markdown-rs
  • https://github.com/kivikakk/comrak
  • https://github.com/pulldown-cmark/pulldown-cmark

We need support to traverse the AST.

brainless avatar Apr 29 '24 14:04 brainless

We need to import content into some kind of structure which helps in generating embeddings. We also need to track the source file and paragraph from emebeddings so sections can be sent to AI models.

brainless avatar May 04 '24 03:05 brainless

I am using Comrak as the Rust library for this.

brainless avatar May 06 '24 13:05 brainless