High-performance retrieval engine for unstructured data

[ICLR 2025] Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

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

Awesome-RAG: Collect typical RAG papers and systems.

GNN-RAG: Graph Neural Retrieval for Large Language Modeling Reasoning

HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

HuixiangDou2: A Robustly Optimized GraphRAG Approach

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

The code for LaRA Benchmark

SimpleQuestions code corresponding to publication at https://arxiv.org/abs/1604.00727

一个基于langchain实现RAG的简单示例

Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph-based retrieval-augmented generation.

A Toolbox for MultiModal Recommendation. Integrating 10+ Models...

Pytorch implementation for "Bootstrap Latent Representations for Multi-modal Recommendation"-WWW'23

Convert PDF to markdown + JSON quickly with high accuracy

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

Python tool for converting files and office documents to Markdown.

The official implementation of Self-Play Fine-Tuning (SPIN)

The implementation project with Pytorch for the paper Can LLMs be Good Graph Judger for Knowledge Graph Construction?

🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library

Empowering RAG with a memory-based data interface for all-purpose applications!

Docs2KG: A Human-LLM Collaborative Approach to Unified Knowledge Graph Construction from Heterogeneous Documents

The docker-compose files for setting up a SearXNG instance with docker.

LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & k…

A modular graph-based Retrieval-Augmented Generation (RAG) system

An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.