shamoon
shamoon
> Just curious about one matter: why not use MCP? > > I am quite a beginner on working with LLMs. MCPs are great for external plugins, but this AI...
> I know this is another element to the long wishlist that might take quite a bit of time and effort to implement, but would it make sense to use...
> So glad to see this! > > If I'm not mistaken, it appears you are using chat requests to LLMs where you instruct to answer using json. You should...
Cool, and your project seems very interesting/ relevant. Would love to have your input here, I most certainly do not consider myself an experienced LLM dev. Yea I’ll look into...
> Thanks. Then as an **extremely grateful** user of paperless-ngx, I'll manage to find some time in the next few days to take a look at your code in more...
> I believe it’s important to clearly highlight in both the documentation and the UI that using an external LLM service may expose highly sensitive data There already was a...
> That's it for me for now. Let me know if this was helpful and have a nice day :) Thanks for taking the time to provide all that feedback....
@dependabot rebase
> Hi, If I'm not wrong, Google Document AI and Mistral OCR are capable of treating directly the whole PDF (I'm sure for Mistral, haven't tested Google). Not sure what...
OCR = optical character recognition Embedded text layer = selectable text in a PDF Paperless has always generated a PDF like this, last I checked Azure is the only one...