Collection of PDF parsing libraries like AI based docling, claude, openai, gemini, meta's llama-vision, unstructured-io, and pdfminer, pymupdf, pdfplumber etc for efficient snapshot, text, table, and metadata extraction.

synthetic dataset generation workflow using local file resources for finetuning llms.

This is a collection of various document parsers and hands-on to construct structured data for your RAG applications.

Extract data from images, pdf, invoices, receipts | Extract tables from pdf, images and convert to Excel/CSV | OCR complex pdfs, images.

📄 Extract detailed text, tables, and layout data from machine-generated PDFs with ease using pdfplumber, built on pdfminer.six for reliable results.

A minimal Mistral API wrapper to OCR images and PDFs with images embedded in the markdown result.

A python package with graphical user interface for processing images with the Mistral OCR API

A helper LLM app with RAG and Mistral OCR for very long reports like 10-Q, 10-K filed with the SEC.

Prototype Mistral OCR pipeline. Upload your PDF and download in English.

Implemented an automation workflow that saves me >90% of time spent logging expenses!

A Python helper for extracting text from PDFs and images using Mistral OCR

Podcast AI backend built with FastAPI, powered by Mistral for LLM summarization, and MCP.

Mistral OCR App es una aplicación web basada en Streamlit que utiliza la API OCR de Mistral para extraer texto de documentos PDF e imágenes. Los usuarios pueden proporcionar una URL o cargar un archivo local. La aplicación detecta automáticamente el tipo de archivo, muestra el documento original (o imagen) en una vista previa.

Self-hosted AI Suite, GDPR-compliant, featuring Multi-LLM Chat (Mistral, Nebius, etc), Audio Transcription (Gladia, Deepgram, AssemblyAI, Voxtral, Whisper, etc), Image Gen (Flux, etc), Cloud Storage integration, OCR, etc

Automatic Legal Document Analysis - A simplified and focused legal document analysis tool developed during the Hackathon AI & GenAI - Legal & Compliance @ATOS.

Downloads PDFs from a URL and extracts text using OCR with the Mistral API.