RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Get your documents ready for gen AI

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Parse files for optimal RAG

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

A Repo For Document AI

Improved file parsing for LLM’s

Parse PDFs into markdown using Vision LLMs

Complex data extraction and orchestration framework designed for processing unstructured documents. It integrates AI-powered document pipelines (GenAI, LLM, VLLM) into your applications, supporting various tasks such as document cleanup, optical character recognition (OCR), classification, splitting, named entity recognition, and form processing

Tutorial on how to deskew (straighten) text images

A Python pipeline tool and plugin ecosystem for processing technical documents. Process papers from arXiv, SemanticScholar, PDF, with GROBID, LangChain, listen as podcast. Customize your own pipelines.

The invoice, document, and résumé parser powered by AI.

An OCR based document parser to extract information from identity document images

An open source framework for Retrieval-Augmented System (RAG) uses semantic search helps to retrieve the expected results and generate human readable conversational response with the help of LLM (Large Language Model).

Resume Parsing app to extract information using AI

DF Extract Lib

Graphlit Platform

Build a RAG preprocessing pipeline

Extract text from your DOCX documents.

Python client library for Graphlit Platform