Ragas: assessing RAG recall QA accuracy and answer correlation
综合介绍 Ragas是一个专门用于评估和优化检索增强生成（RAG）系统的工具。它通过分析查询、检索上下文和生成答案之间的关系，提供了一套全面的评估指标。这些指标包括忠实度、答案相关性、上下文相关性、上...
Sorting
Orama: a high-performance full-text book and vector search engine
综合介绍 Orama 是一个开源的高性能搜索引擎，完全用 TypeScript 编写，支持全文本搜索、向量搜索和混合搜索。Orama 旨在在任何 JavaScript 运行时环境中工作，提供快速、可靠...
Needle: an AI search and job automation platform with access to private data sources
综合介绍 Needle 是一个专为企业设计的人工智能平台，旨在通过高效的信息搜索和自动化工作流程来提升企业的生产力。该平台能够连接企业内部的各种数据源，提供统一的搜索和数据管理功能。用户可以通过简单的...
XRAG: A Visual Evaluation Tool for Optimizing Retrieval Enhancement Generation Systems
综合介绍 XRAG（eXamining the Core）是一个专为评估高级检索增强生成（RAG）系统的基础组件而设计的基准框架。通过剖析和分析每个核心模块，XRAG提供了不同配置和组件如何影响RAG...
RAG Web UI: Building an Intelligent Documentation Q&A System and Simply Building a Private Web-Side Knowledge Base
综合介绍 RAG Web UI 是一个基于 RAG（检索增强生成）技术的智能对话系统。它帮助企业和个人构建基于自身知识库的智能问答系统。通过结合文档检索和大语言模型，RAG Web UI 提供准确可靠...
Kheish: multi-actor intelligences that review, validate and format output to produce high quality results
Comprehensive Introduction Kheish is an open source multi-role agent designed for Large Language Model (LLM) tasks that require structured, step-by-step collaboration.Kheish is more than just a simple coordinator, it is an intelligent agent in its own right, requesting modules on demand, integrating user-reversal...
Unigraph: building locally running knowledge graphs and personal search engines
综合介绍 Unigraph 是一个本地优先的通用知识图谱和个人搜索引擎，旨在为用户提供一个集成的工作空间，帮助管理和搜索个人生活中的各种数据。通过 Unigraph，用户可以将不同来源的数据整合到一个...
MaxKB: Out-of-the-box AI Knowledge Base Q&A System for Smart Customer Service and In-house Knowledge Base
综合介绍 MaxKB（Max Knowledge Base）是一款基于大语言模型和RAG（检索增强生成）的开源知识库问答系统。该系统广泛应用于智能客服、企业内部知识库、学术研究与教育等场景。MaxKB...
MiniRAG: Simplified Retrieval Enhanced Generation Framework, Entity Graph Index Recall Relevant Text Blocks
综合介绍 MiniRAG是一个极其简单的检索增强生成（RAG）框架，旨在通过异构图索引和轻量级拓扑增强检索，使小模型也能实现良好的RAG性能。该项目由香港大学数据科学实验室（HKUDS）开发，主要解决...
cognee: a RAG open source framework for knowledge graph based construction, core prompts learning
综合介绍 Cognee是一个专为AI应用和AI代理设计的可靠数据层解决方案。旨在加载和构建LLM(大型语言模型)上下文，通过知识图谱和向量存储创建准确和可解释的AI解决方案。该框架有利于成本节约、可解...
SimGRAG: Knowledge Graph-Driven Retrieval Enhancement Generation Using Similar Subgraphs
综合介绍 SimGRAG（SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented G...
RAGFlow: an open source RAG engine based on deep document understanding, providing efficient retrieval-enhanced generation workflows
Comprehensive Introduction RAGFlow is an open source Retrieval Augmented Generation (RAG) engine based on deep document understanding technology. It provides an efficient RAG workflow for organizations of all sizes, incorporating a large-scale language model (LLM) capable of delivering data in complex formats based on real...
Vanna: Generating Accurate SQL Queries from Text Using RAG Techniques
综合介绍 Vanna是一个MIT许可的开源Python框架，专注于通过RAG（检索增强生成）技术生成SQL查询。用户可以通过训练RAG模型，将其应用于自己的数据，然后提出问题，Vanna会返回相应的S...
Simple, effective RAG retrieval strategy: sparse + dense hybrid search and rearrangement, and use "cue caching" to generate overall document-relevant context for text chunks.
为了让 AI 模型在特定场景中发挥作用，它通常需要访问背景知识。例如，客户支持聊天机器人需要了解其服务的具体业务，而法律分析机器人需要掌握大量的过往案例。 开发者通常使用检索增强生成（Retrieva...
GroundX: Building a RAG (Retrieval Augmentation) API Based on Real, Illusion-Free Data
Comprehensive Introduction GroundX is a full-stack solution designed for building real-data based LLM (Large Language Model) applications, specifically designed to build a full suite of RAG applications. It solves the phantom that traditional vector databases produce when processing complex documents through dynamic chunking and context generation...
Vision is All You Need: Building an Intelligent Document Retrieval System Using Visual Language Models (Vision RAG)
Comprehensive Introduction Vision-is-all-you-need is an innovative visual RAG (Retrieval Augmented Generation) system demonstration project that breaks new ground in applying Visual Language Modeling (VLM) to the document processing domain. Unlike traditional text chunking methods, the system directly makes...
Visual RAG for PDF with Vespa - a Python demo application
Introduction Thomas joined Vespa in April 2024 as a Senior Software Engineer. In one of his last previous assignments as an AI consultant, he actually built a RAG application based on Vespa's massive PDF collection...
HelpLook: one-stop AI knowledge base building system, website quickly integrates AI customer service robot
General Introduction HelpLook is a tool to quickly build a free help center and knowledge base system. It provides users with the ability to create content such as product documentation, corporate blogs, FAQs, usage guides and troubleshooting with zero code. By integrating AI Q&A bots and AI search capabilities, Hel...
AutoFlow: GraphRAG-based conversational knowledge base/deep web search tool with dialogs that can be integrated into other websites
General Introduction AutoFlow is an open source tool developed by PingCAP to build graph-based knowledge bases with TiDB serverless vector storage. It integrates LlamaIndex and DSPy frameworks to support complex dialog search and knowledge graph...
English 
简体中文 
日本語 
한국어 
Español 
Deutsch 
Français 
Português do Brasil