Michal Pstrag
Michal Pstrag
Please check the docs again and make sure they're consistent with what we already have, and before the next review, please build it and check that everything renders correctly. Thanks!
This will be implemented in #62
This is related to #10, the current version of `fastmcp` simply doesn't support resource templates listing
@zzstoatzz thanks my bad, seems to be fixed but not released yet
@espoirMur why do you want to implement `pymupdf` parser? It has more restrictive license, is potentially slower and has some quality issues (https://arxiv.org/pdf/2408.09869). If you can prove that it works...
There is an option to turn off OCR in docling. Maybe we can expose more params in our parser so that it can cover more use cases.
@pngwn Infinite scrolling is fine for small data frames. If you have a few rows that make the whole component too big, you can hide them and let the user...
ref lib with pipeline primitives: https://github.com/the-pocket/PocketFlow
We can close #330 then
> And mathematically, embeddings are representation in a vector space. The same content will be represented the same way in the same embedding space, regardless of the embedding model they...