🖼️📄E2E Multi-modal Document Preprocessing with Azure Document Intelligence
-
Updated
Oct 22, 2025 - Python
🖼️📄E2E Multi-modal Document Preprocessing with Azure Document Intelligence
Workshop for Azure OpenAI Service
An application that automatically parses bank statements to visualize current income and spending compared to budgeting and savings targets
This is a collection of various document parsers and hands-on to construct structured data for your RAG applications.
Solución inteligente para la digitalización y gestión de facturas. Transforma documentos PDF no estructurados en datos SQL procesables mediante IA, optimizando el flujo de trabajo financiero.
Multi-agent parallel document extraction using Gemini LLM and Azure Document Intelligence OCR, running locally in Docker.
PDF extraction samples comparing Azure Document Intelligence (layout model) 🏢 vs Markitdown ✍️vs Apache Tika
Scribbly - Convert your boring notes into interactive flashcards using Azure Text Analytics, Azure Document Intelligence
🚀 Intelligent document extraction system powered by Azure AI & Gemini 2.5. Transform any form into structured JSON with real-time editing and enterprise-grade validation.
OCR-enabled PDF text extraction in Python with pypdf and Azure Document Intelligence.
Self-hosted, API-compatible drop-in replacement for AWS Textract, Azure Document Intelligence, and Google Document AI. Runs a local/quantized VLM. ~16–40× cheaper. Docs never leave your machine.
A simple Python Tk app to automate the process of uploading invoices to the Evelstar courier portal.
self rag sample
Serverless invoice extraction API using Azure Document Intelligence and Azure Functions. Upload a PDF invoice and receive normalized JSON output including line items, totals, dates, and vendor details.
Uses OCR and PII detection models to mask PII in .tiff files. Configurable to use Azure and AWS OCR and PII detection models
Multi-source document ingestion pipeline to ingest digital PDFs, scanned PDFs (Azure OCR), and JSON exports into a unified PostgreSQL + pgvector schema with semantic search via FastAPI and MCP tools for Cursor/Claude Desktop.
An Enterprise RAG pipeline using Azure AI Document Intelligence, Translator, and OpenAI GPT-4o to query complex, multi-lingual PDFs with strict source citations and conversational memory.
A dual-agent, feedback-driven document extraction system using GPT-5 and Azure Document Intelligence that automatically improves its own prompts, reducing manual rule updates and adapting to evolving business requirements.
To associate your repository with the azure-document-intelligence topic, visit your repo's landing page and select "manage topics."