You can upload invoices, have them parsed, and correct the parsed data. The corrections are saved, and the next time you upload a similar invoice, the agent may apply them automatically if they make sense.

You can provide feedback on the automatically applied corrections. Rejected corrections are immediately reverted, and you can add an explanation, which will be taken into account the next time the agent encounters a similar invoice.

Here's a 4 min demo showing the full feedback loop in action: https://www.youtube.com/watch?v=txaJ0OhOFVw

Export as JSON or CSV. You can also use it via the API.

Tech stack: Postgres (with pgvector), FastAPI, Claude for extraction, Celery + Redis for background processing, TypeScript with React, Voyage AI for embeddings, Mistral for OCR (with pymupdf fallback).

It's pay-as-you-go, no subscription required, just top up your account and use as needed. You can try it for free.

I'd really appreciate hearing what you think, especially if you deal with invoices regularly. Is the correction/feedback loop something that would actually save you time?

Thanks! Martim

Comments URL: https://news.ycombinator.com/item?id=47693967

Points: 1

# Comments: 0

I was a bit overwhelmed with the different ways that you can process documents to create embeddings for RAG, so I wanted to create a tool to experiment with different OCR models, refining the OCR results, different chunking methods, and different embedding models.

You can: - search processed documents in the playground - evaluate the retrieval results using an llm-as-judge (not perfect, but can be a useful signal) - compare different datasets (using aggregate metrics or by side by side comparison in the playground)

You can also manually inspect the results of each query, and of each intermediate document processing result.

To get a better idea, check out one of the use cases: https://ragbandit.com/use-cases/optimizing-insurance-documen...

To be completely fair, I haven't added that many options for the different stages of the document processing pipeline! There are tons of features that I'd like to add, but I've already spent quite a bit of time on this, so I'd really appreciate it if you could let me know if this is something that could be useful for you/you find interesting. Would you use something like this?

Tech stack: Postgres (with pgvector), fastapi, [ragbandit-core](https://github.com/MartimChaves/ragbandit-core) (the document processing core is open source), typescript with react, celery for background tasks (and redis as the broker).

It's currently a credits-based subscription with optional top-ups. You can get 1000 credits to try it out (I ask for card info for these 1000 credits as a spam filter).

Thanks, Martim

Comments URL: https://news.ycombinator.com/item?id=47542679

Points: 2

# Comments: 0