document-ai

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

LLM-Driven Extraction of Unstructured Data — Built for API 部署 & ETL Pipeline Workflows

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

可私有部署的多租户知识智能体平台：统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.

A Repo For Document AI

开箱即用的AI标书编写工具，标书AI生成工具，投标工具箱、知识库、标书查重、废标项检查，完全开源免费，欢迎使用

在保留版面、公式与结构的前提下进行 PDF 翻译，适用于科研与技术文档

A curated list of resources for Document Understanding (DU) topic

Turn documents into AI-ready Markdown with visual understanding

TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC

PDF to markdown using vision LLMs — tables, layouts, and structure preserved

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

ParseBench - A Document Parsing Benchmark for AI Agents

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

Visual document analysis studio powered by Docling — configure the extraction pipeline, inspect text, tables and bounding boxes in the browser, then chunk, embed and index into Open搜索 and Neo4j.

Algorithms, papers, datasets, performance comparisons for Document AI.

Conversion from Excel to structured JSON (tables, shapes, charts) for LLM/RAG pipelines, and autonomous Excel reading/writing by AI agents via CLI and MCP integration.

Local-first document parsing workbench for five OCR models: PDF/Office to Markdown with WebUI, model switching, CLI and Apple Silicon support.

ReadingBank: A Benchmark Dataset for Reading Order Detection

German-OCR is specifically trained to extract text from German documents including invoices, receipts, forms, and other business documents.