Data, search & knowledge

RAG & retrieval pipelines

5,258 agents · most starred first

RAG & retrieval pipelines, page 7 of 53

rag-api★ 68

Multi-tenant RAG API powered by LightRAG/RAG-Anything. Auto-selects best parser (DeepSeek-OCR/MinerU/Docling) via complexity scoring

cognite★ 67

Create and share chatbots with external knowledge ✨

php-rag★ 67

This application uses LLMs like DeepSeek, GPT-5, Claude, Gemini or Llama, Mixtral (locally) in order to generate text based on the user input. The user input is used to retrieve relevant information from the database and then the retrieved information is used to generate the text. This approach combines power of LLMs and access to source documen

CtrlA★ 67

This includes the original implementation of CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control.

Cosmic-Food-RAG-app★ 67

A chat-based recommendation application that revolutionizes the culinary experience.

php-rag★ 67

An AI assistant built with PHP, Solr and LLM backend of choice. Proof of concept mostly.

simple-rag★ 67

Too many docs? Quickly search over any PDF or Markdown documents

llmnet★ 67

The Offline Internet.

LLM_Powered_Video_Search★ 66

[SOICT 2024] LLM-Powered Video Search: A Comprehensive Multimedia Retrieval System

bedrock-kb-rag-workshop★ 66

Bedrock Knowledge Base and Agents for Retrieval Augmented Generation (RAG)

RAG-examples★ 66

Retrieval Augmented Generation Examples - Original, GPT based, Semantic Search based.

End-To-End-Agentic-RAG-Workflow-for-Answering-Vietnamese-Legal-Traffic-questions★ 66
BRAD★ 66

Bioinformatics Retrieval Augmented Digital (BRAD) Assistant - A LLM powered agent for bioinformatics 🤖

embedchain-fastdash★ 66

Chat with your knowledge base — a conversational RAG agent (LangGraph + OpenRouter) built on Fast Dash's native chat mode. A modern rebuild of the original Embedchain demo.

edu-rag★ 66

Edu-RAG:面向 K12 / 学科教育场景的轻量化 RAG 智能助教开源框架,依托教材、教辅知识库实现精准答疑、习题解析与个性化导学,有效抑制大模型知识幻觉,开箱即用快速落地 AI 教育应用

LawGPT★ 65

A RAG based Generative AI Attorney fed with Indian Penal Code data. Developed using Streamlit, LangChain and TogetherAI API.

sef★ 65

On premise enterprise-grade RAG-powered agentic workflow chatbot platform with multi-provider support

spring-ai-alibaba-agent★ 65

参考spring-ai-alibaba-examples示例,实现了一个具备记忆、RAG 、函数调用能力和MCP服务调用的对话式电商 AI 智能体。

DeepRead★ 65

[DeepRead] This is the official implementation of the DeepRead paper.

langchain-ask-the-doc★ 64

Ask the Doc app built using Langchain and Streamlit.

shoppy-gpt★ 64

A Nextjs + Pinecone + OpenAI GPT site to surface answers to Shopify help center content

time-geekbang-org-rag★ 64

the source code of RAG course at https://time.geekbang.org/column/intro/100817901

LRAT★ 64

The implementation for SIGIR 2026: Learning to Retrieve from Agent Trajectories.

ParamMute★ 64

[NeurIPS 2025] ParamMute (a.k.a. PIP-KAG): suppressing knowledge-critical FFNs for faithful retrieval-augmented generation (RAG knowledge conflicts)

splunk-mltk-container-docker★ 63

Splunk App for Data Science and Deep Learning - container images repository

private-rag-example★ 63

Private RAG app sample using Llama3, Ollama and PostgreSQL

NetPulse★ 63

NetPulse: Crossing the event horizon of information

barq★ 63

Dabarqus is incredibly fast RAG that runs everywhere.

Archive-Agent★ 63

Find your files with natural language and ask questions.

UniKB★ 63

面向企业知识管理场景的 RAG 知识库平台 · Multi-Agent + MCP + Hybrid Search

Medical-RAG-using-Meditron-7B-LLM★ 62

Medical RAG QA App using Meditron 7B LLM, Qdrant Vector Database, and PubMedBERT Embedding Model.

TrustRAG★ 62

Code for "TrustRAG: Enhancing Robustness and Trustworthiness in RAG" AAAI 2026 Workshop on Trust and Control in Agentic AI (TrustAgent)

agentic-kb★ 62

法规/规程知识库智能体:混合检索(bge-m3 稠密+稀疏 → 服务端 RRF → 交叉编码器重排)+ GraphRAG + 带三道闸与审计的 ReAct 智能体。含检索质量评测设施、FastAPI 接口与 React 界面。

rag-api-server★ 61

A RAG API server written in Rust following OpenAI specs

llamav2_local★ 61

Projeto de GenAI usando LLAMA V2 Local estilo ChatPDF

chat-mylib★ 61

基于OpenAI的私有资源库问答系统

rag-chatbot★ 61

Build an embeddable RAG Chatbot for your website using Cloudflare Workers.

agentic_rag_workshop★ 61
Agentic-RAG-project★ 61

Production-grade Agentic RAG system for arXiv paper curation

Multi-Agent-RAG-Template★ 60

This template demonstrates how to create a collaborative team of AI agents that work together to process, analyze, and generate insights from documents.

rag-with-amazon-bedrock-and-opensearch★ 60

Opinionated sample on how to build and deploy a RAG application with Amazon Bedrock and OpenSearch

Multi-Agent-Deep-RAG★ 60

Multi-Agent Deep RAG

LocalMind★ 60

Private AI research agent — web search, document ingestion, RAG memory. Runs entirely in your browser.

vidxp★ 60

VidXP (Video eXPlain) - Video Indexing Engine. Search in videos in natural language. 👀 Connect your Hermes / Claude / OpenClaw agents, allow them to understand videos with low token cost.

ask-neon★ 59

Chatbot: Search your own knowledge base by semantic similarity

easyRAG★ 59

Build your own RAG and run it locally on your laptop: ColBERT + DSPy + Streamlit

RAG-on-GCP-with-VertexAI★ 59

Create a Chatbot app on your own data with GCP tools

bella-rag★ 59

基于llama-index框架的 RAG 最佳实践,通过业界领先的PDF结构化文档解析能力、混合检索、small2big、Contextual rag等策略实现了高精度的传统rag模式问答效果,同时支持基于plan and solve agent执行pipline的Deep RAG模式,提供多格式文档支持与数据安全的存储架构。

RAG-Enterprise★ 59

🚀 100% local RAG system with one-command setup. Your data never leaves your server.

RAG★ 59

DeepBlue Brain:一个面向 RAG 全链路教学与理解的白盒化交互平台,支持各类文档上传、混合检索、实时检索日志流、提示词原文溯源与流式问答。

Build-An-LLM-RAG-Chatbot-With-LangChain-Python★ 58

Build-An-LLM-RAG-Chatbot-With-LangChain-Python

AnyChat★ 58

Chat with your Documents(PDF, TXT, DOCX, ODT, PPTX etc), Websites and Youtube Chat too!, CSV files. Uses langchain, Ollama, Groq, Gemini, Streamlit. Llama3 available

Novel-Assistant★ 58

로컬 또는 클라우드 LLM을 사용해 문서 폴더 기반으로 검색·답변하는 RAG 어시스턴트

LevelRAG★ 58

The official implementation of "LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers"

LangChain-Pinecone-RAG★ 58
conversational-retrieval-agent★ 58
quackling★ 57

Build document-native LLM applications

confidence-weighted-rag★ 57

Confidence-Weighted Multi-Agent Retrieval-Augmented Generation (CW-MARAG) — a contradiction-aware RAG system that uses multiple retrieval agents with confidence-based arbitration to generate grounded, non-hallucinated answers from PDFs.

ragcoon★ 57

Agentic RAG to help you build a startup🚀

User-Centric-RAG-Using-Llamaindex-Multi-Agent-System-and-Qdrant★ 57

This project involves using llamaindex Multi Agents concierge system and Qdrant vector database to customize the RAG application with user preferences over LLMs, Embeddings, Search types, and Reranking Models.

tree-of-clarifications★ 57

🌲 Code for our EMNLP 2023 paper - 🎄 "Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models"

openthairag★ 57

OpenThaiRAG is an open-source Retrieval-Augmented Generation (RAG) framework designed specifically for Thai language processing. This project combines the power of vector databases, large language models, and information retrieval techniques to provide accurate and context-aware responses to user queries in Thai using OpenThaiGPT 1.5 as LLM.

adaptive-rag-workbench★ 57

Sample for context-aware Agentic RaG, Q&A with multi-source verification, and self-curating knowledge base. Powered by Azure AI Foundry Agent Service, Azure AI Search with agentic retrieval and query rewrite, Semantic Kernel and LangGraph agents running in Azure Container Apps, and ready for Copilot Studio

pgedge-rag-server★ 57

A simple API server for performing Retrieval-Augmented Generation (RAG) of text based on content from a PostgreSQL database using pgvector.

yahont-ce★ 57

Self-hosted AI-платформа с расширенными возможностями: RAG, агенты, веб-поиск, исследования, коннекторы, любые LLM и гибкие настройки

HydraRAG★ 56

[EMNLP 2025] HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoning

WebRAgent★ 56

WebRAgent is a retrieval-augmented generation (RAG) web application featuring agent-based query decomposition, vector search with Qdrant, and integration with leading LLM providers for context-rich, dynamic responses.

dify-with-classical-search★ 56

Example Go external-data tool that connects Dify to Meilisearch for a movie-recommendation RAG demo.

fastapi-langchain-rag★ 56

(Let's start with a) Scalable question-answering system utilizing FastAPI, LangChain (LCEL), and PGVector, featuring an ingestion pipeline. Deployed on GCP Cloud Run via Terraform.

searchbox★ 56

Airgapped closed-corpus QA loop: a self-hosted Qwen3.6 agent explores a .zip dataroom under a token budget with local tools

rag-architectures★ 56

Sistema RAG con 6 arquitecturas implementadas como microservicios independientes en FastAPI + Docker: Naïve RAG, Advanced RAG, Modular RAG, GraphRAG, Agentic RAG y Hybrid RAG. Cada una incluye embeddings locales con sentence-transformers y se conecta a cualquier LLM vía API compatible OpenAI. Ideal para aprender, comparar y prototipar patrones RAG.

docq★ 56

Local document Q&A in your terminal — powered by on-device LLMs.

CodeRuleNexus★ 56

这个项目最终形成了两个不同的知识系统,并用一个统一入口把它们连接起来: 1. 文档 RAG:处理制度、规范、说明和业务资料。 2. Code Wiki:处理项目源码、配置、符号、调用和架构事实。 3. Knowledge Agent:根据用户问题和当前权限,决定先查哪一类知识、是否换查询继续找、什么时候回答或拒答。 此外还完成了用户注册登录、工作空间、成员角色、邀请、离职数据交接、文档生命周期和代码项目管理。换句话说,它不只是一个“把 PDF 丢给大模型”的 Demo,而是一个有数据边界、有证据来源、有多步查询能力的内部知识工作台。

Vue3_WUT_RAG★ 56

武理小精灵是一个面向武汉理工大学校园场景的全栈agent,基于 Vue 3 + Pinia + Express + Qdrant + SQLite 构建。系统通过JEV 决策模型双引擎路由(影子/灰度/强制三模式)自动识别用户意图,在普通对话、知识库检索(RAG)和 Agent 工具调用三种模式间智能路由,并以 SSE 流式返回回答、来源引用与执行轨迹。

rag-crawler★ 55

Crawl a website to generate knowledge file for RAG

nesis★ 55

Your AI Powered Enterprise Knowledge Partner. Designed to be used at scale from ingesting large amounts of documents formats such as pdfs, docx, xlsx, png, jpgs, tiff, mp3, mp4, jpeg. Integrates with s3, Windows Shares, Google Drive and more.

ChatBot★ 55

ChatBot, show how to implement a RAG based on OceanBase or OceanBase seekdb AI capabilities escpecailly hybrid search and AI embedding.

netai-chat-with-your-data★ 55
LangGraphA2A★ 55

LangGraph+A2A+MCP 实现的Agent RAG

dynamous-ai-coach★ 55

AI Coach Powered by Cole's Content (RAG AI Agent)

Simple-RAG-Chatbot★ 55

Build a simple RAG chatbot with LangChain and Streamlit

Agentic_RAG★ 55
production-rag-assistant★ 55

RAG for legal and academic documents with quote-level verification: each claim cites a source chunk, the quoted text is checked word for word, and the app abstains when the sources fall short.

bubble-rag★ 54
banking-faq-bot★ 54

This is retrieval based Chatbot based on FAQs found at a banking website.

navalmanac★ 54

Chatbot based on Almanac of Naval Ravikant. Uses OpenAI's chat completion API

dcup★ 54

Dcup - Advanced RAG for Personal Knowledge ☕

RAG_local_tutorial★ 54

Simple RAG tutorials that can be run locally or using Google Colab (only Pro version).

AI-Cloud-Go★ 54

A Golang-Based Cloud Drive & Knowledge Base System 一个基于Golang开发的LLM应用平台

HybridRAG★ 54

A hybrid retrieval system for RAG that combines vector search and graph search, integrating unstructured and structured data. It retrieves context using embeddings and a knowledge graph, then passes it to an LLM for generating accurate responses.

wiki-rag★ 54

An experimental Retrieval-Augmented Generation (RAG) system specialised in ingesting MediaWiki sites via their API and providing an OpenAI API interface to interact with them.

RAW-RAG★ 54

Implementation and experimental code for "Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought".

Article-Assistant--RAG-Telegram-Bot★ 53

A sophisticated RAG (Retrieval-Augmented Generation) Telegram bot that transforms articles and documents into interactive knowledge bases. Upload PDFs/URLs and get AI-powered answers with source citations.

langchain-chromadb-rag-example★ 53

My attempt at implementing retreival augmented generation on Ollama and other LLM services using chromadb and langchain while also providing an easy to understand, clean code for others since nobody else does

Building-and-Evaluating-Advanced-RAG-Applications★ 53

Jupyter notebooks for course Building and Evaluating Advanced RAG Applications, taught by Jerry Liu (Co-founder and CEO of LlamaIndex) and Anupam Datta (Co-founder and chief scientist of TruEra).

RagUltimateAdvisor★ 53

A complete Retrieval-Augmented Generation (RAG) application that demonstrates modern AI capabilities for answering questions about Ultimate Frisbee rules and strategies. This project showcases how to build a production-ready RAG system using cutting-edge technologies.

customgpt-starter-kit★ 53

CustomGPT.ai’s RAG API’s Starter Kit, including multi-instance embedded widgets, floating buttons, and standalone application.

temporal-rag★ 53

A post-retrieval temporal layer for RAG systems — validity filtering, time decay, document kind classification, and hybrid reranking in one pipeline.

AI-RAG-Assistant-Chatbot★ 53

👨🏻‍💻 Meet Lumina – my personal AI assistant powered by hybrid RAG with Pinecone vector search and Neo4j graph traversal, Google AI, LangChain, and an MCP server with 30+ tools. Features real-time streaming, conversation branching, and a multi-agent agentic AI pipeline for intelligent, grounded responses with inline citations.

hands-on-rag★ 53

Repository for code examples for the book "Hands-on RAG for production"

More in Data, search & knowledge