Local-first RAG platform for technical document libraries. Features FastAPI, ChromaDB, and active retrieval (FLARE) powered by Ollama.
One canonical schema for every document parser. Engine-agnostic adapters for Docling, Tesseract, and PaddleOCR — swap OCR/layout engines without rewriting your pipeline. Built for RAG and LLM document ingestion.
Production-grade document-intelligence RAG agent template — AWS Bedrock Knowledge Bases, OpenSearch-backed metadata/audit, dual-mode JWT + Azure AD SSO, multi-team isolation, and LibreOffice document conversion. Advanced tier of the Document Intel Agent Template family.
Intel Nexus – An enterprise-grade document intelligence platform that ingests PDFs, extracts structured knowledge (text, tables, images), and enables semantic search & RAG-based querying using FastAPI, Streamlit, and modern AI pipelines.
Production-grade banking document processing pipeline using Azure AI Document Intelligence, GPT-4o, and OpenCV. Extracts structured data from cheques, invoices, KYC forms, ID cards, and trade finance documents with KYC/AML compliance validation. Deployable as Azure Web App
Leverage Azure AI Document Intelligence to extract text, tables, and key data from complex forms and automatically update your enterprise database.
A high-performance, production-grade pre-LLM document intelligence operating system that transforms unstructured documents into synchronized mathematical representations to build budget-aware, optimized context for AI agents.
Add a description, image, and links to the document-intelligence-rag topic page so that developers can more easily learn about it.
To associate your repository with the document-intelligence-rag topic, visit your repo's landing page and select "manage topics."