Popular GitHub Repositories for Document Analysis

Open-source platform for extracting structured data from documents using AI.

Code for the paper "PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks" (ICPR 2020)

Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding (ACL 2022)

A package for parsing PDFs and analyzing their content using LLMs.

Powerful web application that combines Streamlit, LangChain, and Pinecone to simplify document analysis. Powered by OpenAI's GPT-3, RAG enables dynamic, interactive document conversations, making it ideal for efficient document retrieval and summarization.

An on-premises unstructured data extraction tool powered by vision language models.

Improving Document Binarization via Adversarial Noise-Texture Augmentation (ICIP 2019)

Code for ICPR2022 paper: "Graph Neural Networks and Representation Embedding for table extraction in PDF Documents"

Service to import data from various sources and index it in AI Search. Increases data relevance and reduces final size by 90%+. Useful for RAG scenarios with LLM. Hosted in Azure with serverless architecture.

Document understanding with GPT 3.5 integrated with Telegram

High-quality synthetic text data generation for Urdu Text Recognition

一个完全离线的自然语言处理流程，利用本地大型语言模型 (LLMs) 来提取、分块、嵌入、查询、摘要和翻译研究文档。受虚构的X博士神秘事件的启发，该系统支持多种格式的文件、基于本地检索增强生成 (RAG) 的问答、阿拉伯语翻译和基于ROUGE的摘要生成——所有这些都无需依赖云服务。

This Document Analysis pipeline is a comprehensive document analysis system, designed to automate the processing and analysis of documents from acquisition to consumption. It integrates advanced machine learning & AI models like RAG (Retrieval Augmented Generation) & Mistral LLM to efficiently extract, match, enrich, process document

A web application that enables users to upload documents and utilize AI techniques like semantic search and text summarization for efficient analysis. Built with Python, FastAPI, Svelte, PostgreSQL, and LangChain.