Structured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM
-
Updated
Aug 26, 2026 - Python
Structured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.
Collection of open-source libraries and tools for Robotic Process Automation (RPA), designed to be used with both Robot Framework and Python
Enterprise-ready Document Analysis with Large Language Models
99.156% Accuracy from Agentic Document Extraction DPT-2 model on DocVQA val split
Production-grade Multi-PDF RAG Intelligence System with FastAPI, Streamlit, LangChain, Gemini, ChromaDB, BM25, CrossEncoder, and RAGAS.
Receipts to texts using NodeJS and Google Document AI
AI Paper or PDF Invoices to Excel Consolidation 📄 ➡️ 🧠 ➡️ 📁
Production patterns for running Model Context Protocol servers in regulated business domains. Apache 2.0.
Google document AI automation artifacts using python
An Agentic application to review building plans against the California Building Standards Code and Santa Clara County reach codes
Analyse de devis via IA
AI-powered engineering document comparison with delta analysis, grounded RAG chat, OCR, and visual diff generation.
DocRAG is a fully offline, private document intelligence assistant that lets you permanently store and query PDF, DOCX and TXT files. Powered by Qwen2.5 and bge-m3 through llama.cpp, it searches your entire personal library and provides citation-grounded answers with source and page references.
Document AI pipeline that extracts structured claims data from PDF reports and outputs formatted Excel exhibits, and JSON data.
To associate your repository with the documentai topic, visit your repo's landing page and select "manage topics."