Rajeshdevandla/ai-document-intelligence-platform

An end-to-end document processing platform that ingests PDFs/images, runs OCR, extracts structured fields via an LLM, stores results, and exposes a React dashboard. Built as a portfolio project to demonstrate combining Java microservices, a Python OCR pipeline, and LLM APIs (inspired by work at Mutual of Omaha). Who uses it: developers and teams exploring practical AI automation patterns and microservice integration. Key features: React+TypeScript frontend with S3 presigned uploads; Spring Boot upload and processing services; Kafka for async events; Python FastAPI OCR using AWS Textract; OpenAI (GPT-4o) for structured extraction; PostgreSQL/DynamoDB storage; dashboard with status/history; local run via Docker Compose; CI with GitHub Actions.

AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.