An AI-powered metadata-first document intelligence system for complex PDFs that detects and turns critical information into searchable, structured data, always traceable to the source document. The system combines fast metadata-based retrieval with semantic search as a secondary layer for flexible and unstructured discovery.

Project Type: tech / AI Document Pipeline

Role: Full-Stack Developer

Tech Stack: Next.js, TypeScript, React, OpenAI Embeddings, pgvector, TailwindCSS

Status: Deployed 2023; Updated Prototype 2026

Live Demo: upload-flow

document-intelligence

Source-Grounded Extraction · Validated Output · Human Review