A simple, browser-based application for transcribing audio files using the Speechmatics API.

Config files for my GitHub profile.

Script extracting data from the Czech invoices in JSON and checking validity of VAT tax payer

Convert complex structured PDF documents with tables, formulas without OCR to clear markdown using Google's vision models. Markdown files are suitable for RAG pipeline.

This Python script uses the Google Gemini API to extract structured information from PDF or image files representing financial receipts.

A simple Node.js script to split a PDF into individual pages and create JPEG thumbnails.

Extract structured data from receipt images using Groq's Vision API. Automatically processes financial receipts and outputs VAT information, prices, and transaction details in JSON format.

Convert batch of pictures with structured data like tables, formulas, charts to markdown using vision capable models. Markdown files are highly suitable for RAG pipeline.

A versatile command-line tool for processing PDFs and images with Mistral's OCR API.