Data, search & knowledge

RAG & retrieval pipelines

5,258 agents · most starred first

RAG & retrieval pipelines, page 33 of 53

RAG★ 4

BARC PROJECT

ChatGPT-and-LangChain-The-Complete-Developer-s-Masterclass★ 4

Application that summarizes pdf documents using LangChain and GPT models

Corrective_RAG_Project★ 4

-Basic Corrective Rag System

enterprise-knowledge-assistant★ 4

AI Powered Enterprise Knowledge Assistant (RAG Chatbot) built with FastAPI, ChromaDB and Ollama.

Research-Paper-Assistant★ 4

Citation-grounded RAG agent over arXiv papers: section/table-aware chunking, vector search + cross-encoder re-ranking, FAISS, tool-calling agent, groundedness check and an evaluation harness.

rag-nexus★ 4

Hybrid semantic + keyword search RAG pipeline

ai-rag-chat-bot★ 4

A serverless rag chatbot solution that uses Azure OpenAI, Azure AI Search, and Semantic Kernel to provide intelligent responses from your own data sources with accurate citations.

cfn-rag-backend★ 4

闪客快打7重置版 (CFN) 的 RAG 智能对话后端:基于游戏资源做检索增强,支持与 NPC 流式对话、任务发布、好感度、立绘与知识库管理。

openfiles★ 4

Open-source AI assistant for your local files. Search, understand, and chat with PDFs, docs, code, and more.

Enspira★ 4

Enspira is a RAG-powered LLM interface, complete with reranking, summarization, classification, and TTS capabilities. While not documented too well at the moment, feel free to ask questions.

mkdocs-chatbot★ 4

AI-powered chatbot for MkDocs — chat with your docs and get instant answers

pdf-rag-chatbot★ 4

An AI PDF Chatbot built with Retrieval-Augmented Generation (RAG) that lets you upload PDFs and ask questions using local embeddings (sentence-transformers), FAISS vector store, and the Claude API.

eu-ai-act-rag★ 4

Grounded question answering over the EU AI Act, with retrieval, faithfulness and hallucination measured on 45 hand-written questions.

minerva★ 4

RAG platform for educational use at DSV, Stockholm University. Rust/Axum backend, React frontend, Qdrant vector search.

BushfireReadyGPT★ 4

Australian location + scenario to reviewable preparedness drafts. Hybrid RAG, evidence trails and human review. Local Ollama; password-protected cloud demo. Not emergency decisions.

context-window★ 4

A simple RAG toolkit.

youtube-rag-system★ 4

A professional Retrieval-Augmented Generation (RAG) system for YouTube videos. Features timestamp-preserving analysis, smart intent routing (Summary vs. Detailed Q&A), and multi-video comparison capabilities. Built with LangChain, ChromaDB, and Gemini/Ollama for deep semantic understanding of video content.

chatsite-ai★ 4

Chat with any website. Scrape a page, ground Gemini on its content, and have a persistent AI conversation. Built with Next.js, Prisma, Firecrawl, and PostgreSQL.

PocketRAG★ 4

A zero-dependency, drop-in hybrid RAG engine for PHP 8+ with SQLite.

micro-bot★ 4

Ask and get answers with their sources, straight from the Micro Club's documents.

medical-rag-assistant★ 4

A domain-specific Medical AI Assistant using RAG — answers health questions from curated documents with source citations and ReAct reasoning.

zautte★ 4

RAG assistant that answers questions using only your website's content, citing its sources — embeddable JS widget, FastAPI, Claude, Ollama embeddings, numpy vector store. Piloted by the Comune di San Benedetto del Tronto (Italy).

METEORA★ 4

Traditional RAG pipelines rely on similarity-based re-ranking with arbitrary top-k cutoffs: opaque, rigid, and vulnerable to adversarial content. METEORA replaces the re-ranking step entirely: a LLM generates rationales that guide evidence selection, explain every decision, and power a verifier that filters poison that filters poisoned chunks.

Heros★ 4

Heros is a production-grade, Django-powered assistant platform built for reliability, security, and extensibility. Baymax handles intent-aware routing with a 3-tier model fallback (Gemini → OpenRouter → Groq) to stay always available. Includes encrypted keys (Fernet), OAuth + persistent/temporary chats, and Infinsight RAG analytics for Dataset.

GmailRAG★ 4

A Gmail RAG system for answering questions about your personal inbox.

kssrag★ 4

An AI RAG agent package.

sample-s3-vectors-rag-pipeline★ 4

A RAG pipeline sample built on Amazon S3 Vectors and Amazon Bedrock that answers questions about your own documents by calling the s3vectors API directly.

potiguana★ 4

Chatbot para Acesso a Documentos da UFRN

AegisRAG★ 4

AegisRAG is a security-first, auditable enterprise RAG backend for teams that care more about access control,traceability, and governance than drag-and-drop workflow building.

capsuleers.ia★ 4

An expert AI assistant for EVE Online — a standalone desktop app, cross-platform, 100% local and GPU-accelerated. Ask about skills, fitting, terminology, PVE missions, wormholes, sovereignty, exploration, industry and more, and get answers with cited sources, in Italian or English (auto-detected). Powered by Capsuleers.app

rag-server★ 4

High-performance RAG server in Rust. Hybrid BM25 + vector search, dual rerankers (BGE/Mxbai), exact BPE tokenization, MCP tools for Goose/Aider, LRU query cache, 100% local. 800% iGPU speedup on Void Linux + Intel Vulkan.

RAG-playground★ 4

Local-first web app for experimentation with LLMs

locah-ai★ 4

LOCAH.ai — an assistant over Wilfrid Laurier University's public information. Cited answers, surfaced contradictions, and evidence on where Laurier's information fails students.

InfiniAIBook★ 4

Self-hosted Agentic Notebook: chat with your sources, grounded in citations, with reports, infographics, quizzes, flashcards, mind maps and audio overviews.

paperless-search★ 4

Semantic search for Paperless-ngx documents using RAG. Hybrid keyword + vector search with a web UI; supports Ollama (local) or Google Gemini (cloud) providers.

agentic-rag-for-practice★ 4

An engineering-oriented Agentic RAG system built with FastAPI, LangGraph and Qdrant, featuring multi-user document isolation, hybrid retrieval, reranking, corrective retrieval, document-version-aware conversations and streaming Web UI.

pdf-chat★ 4

A production-ready AI PDF chat application built with LangChain, FastAPI, FAISS, and the OpenAI Responses API, enabling intelligent document conversations through Retrieval-Augmented Generation (RAG).

ChemLib-AI★ 4

AI assistant for a university chemistry library: grounded RAG chat + structured extraction

digital-grid-agent★ 4

🏆 二等奖作品|基于 HiAgent、多智能体协作与 RAG 的社区治理诉求闭环系统

rag-doctor★ 4

本地化医学文献 RAG 问答系统。覆盖毕业论文文献调研、科研综述撰写、临床指南查阅、药学信息查询等场景 ,同时具备小数据量下的生产级可用性。支持多篇中英文医学论文 PDF(糖尿病、心血管、BMI 等)的智能检索与生成式问答。基于 Faiss 语义向量 + BM25 关键词 + Cross-Encoder 重排序三重检索 pipeline,模块化设计可自由切换嵌入模型、生成模型与重排序模型。全程不依赖任何第三方 API,基于 Ollama 本地部署 bge-m3 嵌入模型与 qwen2:7b 生成模型,确保医学数据隐私安全。实现了多会话隔离、流式 SSE 输出、异步 PDF 上传、前端历史持久化等生产级特性。

youtube_bot★ 4

Advanced YouTube RAG Chatbot built with LangChain, FastAPI, Qdrant, BM25, Cross-Encoder Reranking, Ollama Phi3, LangSmith tracing, and RAGAS evaluation for timestamp-aware AI question answering over YouTube videos.

NityaGeeta★ 4

Open-source Multi-LLM Ensemble & Scripture RAG platform delivering Bhagavad Gita guidance with zero-hallucination, page-level citations across 5,000+ commentary pages. Built with FastAPI, Next.js 15, and Weaviate.

University-AI-Study-Assistant★ 4

A RAG-based AI study assistant that helps university students ask questions and get answers from their study materials.

recall★ 4

Self-hosted hybrid search + RAG QA (KO/EN) — BM25 + vectors + RRF + rerank on Elasticsearch, Kafka ingestion with DLQ replay, CI-gated retrieval evals, free local LLM via Ollama. No API key needed.

uzbek-legal-corpus★ 4

25 audited Uzbek legal codes, article-level JSONL, CC0

ReferenceRAG★ 4

REFRAG - An implementation of the REFRAG paper from Meta Superintelligence Labs

simple-pdf-rag★ 4

A beginner-friendly Retrieval-Augmented Generation system for chatting with PDF documents using embeddings, vector search, and local LLMs.

rag-agent★ 4

Agente RAG para levantar un sistema RAG con AWS BedRock

knowledge-retrieval-with-imgs★ 3

AI chat app to response data in Markdown format with text and images. Tutorial from: https://youtu.be/qKtM2AlDTs8

RAG-System★ 3

A Retrieval-Augmented Generation (RAG) system using Milvus and LangChain

Neuroplex-Agent★ 3

Neuroplex is a cutting-edge AI Agent platform that combines FastAPI, Vue.js, an AI Engine, Neo4j, and Milvus to enable smart knowledge management and intelligent Q&A.

chatgpt-style-RAG-bot★ 3

This is minimal and clean RAG search project with chatgpt design

ragpipe★ 3

RAG pipeline library for Python. Ingest files, git repos, web pages into vector databases with 3 functions: ingest(), query(), pipe(). CLI + YAML configs. Works with Qdrant, Pinecone, Ollama, OpenAI.

StrunzKnowledge★ 3

This project aims to create a comprehensive, searchable knowledge base from the online articles and forum posts of Dr. Ulrich Strunz. The final application will be a Dockerized service that uses a Large Language Model (LLM) accessed via the Meta-Cognitive Prompting (MCP) protocol to provide users with intelligent access to this knowledge.

rag-pdf-qa★ 3

RAG-powered PDF QA system with self-reflection and multiple retrieval strategies (Stuff/Map Reduce/Refine). Includes monitoring via Langfuse & LangSmith and containerization with Docker

MilvusPaperAgentCRAG★ 3
reliable-agentic-rag★ 3

Project exploring RAG LLM agents

Server-with-AI★ 3

Server with an AI agent powered by an LLM, with tools for internet search, Wikipedia, and RAG database access.

fijian-rag-app★ 3

Public-benefit GenAI platform for the Fijian language — combining Claude + RAG + OpenSearch to build verified datasets, preserve culture, and unlock AI access in the Pacific. LLM Fine-Tuning, RAG, Generative AI and learning

personal-ai★ 3

Chat with your Documents! OpenAI powered pdf-aware chat bot demo

streamlit-langchain-csv-qna★ 3

A streamlit based chatbot for custom CSV data.

NEPSE-Chatbot-Using-Retrieval-augmented-generation-and-reranking★ 3

This project will develop a NEPSE chatbot using an open-source LLM, incorporating sentence transformers, vector database and reranking.

traffic-flow★ 3

Traffic Congestion Prediction on highways in Taiwan

rag-pipeline-app★ 3

Implement RAG using LangChain and HuggingFace embedding models

picky-rabbit★ 3

LLM RAG Project for Food Content Information Chatbot

nexusAI★ 3

Store Your Documents and chat with them using AI-powered chat all in one place.

RAGify★ 3

A full-stack Retrieval-Augmented Generation (RAG) application that enables intelligent document querying and answer generation. Upload PDFs, build semantic search indexes, and get AI-powered answers grounded in your documents.

MentorMate-SSS★ 3

Production RAG chatbot serving 3,232 Q&As with <3s latency and ~95% accuracy using LangChain and ChromaDB

student-rag-api★ 3

A FastAPI RAG pipeline that ingests PDF files, makes embeddings and stores them in a Vector Store (Postgres + pgvector database), then when a query is made performs a similarity search and builds the context to pass to the LLM to generate accurate bibliography-backed answers to the questions using langchain.

RAG-PDF-DeepSeek★ 3

A Streamlit-based Retrieval-Augmented Generation (RAG) application using DeepSeek, FAISS, and LangChain to answer natural language questions from uploaded PDF documents.

PDF-Chat-with-LangChainRAG★ 3

Implement LangChain RAG to chat with PDF with more accuracy.

Chatbot-Service-with-FastAPI-LangChain-and-PostgreSQL★ 3

A simple Python-based chatbot service using FastAPI, LangChain for embeddings, and PostgreSQL with pgvector for storage.

chatbot-rag-pdf★ 3

Este projeto é um chatbot construído com Streamlit e LangChain, que utiliza a técnica de RAG (Retrieval-Augmented Generation) para responder perguntas baseadas em arquivos PDF enviados pelo usuário.

rlm-agent★ 3

Production-grade Recursive Language Model (RLM) agent — gives an LLM a sandboxed Python REPL, sub-LLM recursion, vector search, grep, and divide-and-conquer tools to reason over ingested PDFs. Built with FastAPI, LangChain, Qdrant, and OpenRouter.

rag_for_tang_poems★ 3

唐诗三百首RAG检索增强生成

websitechatbot★ 3

This tool is a web application that utilizes Streamlit and OpenAI language models to enable users to interact with website content through a conversational interface. Users can enter the URL of their desired website, pose their questions, and receive precise and relevant answers.

AI-URL-Read★ 3

A Python-based documentation assistant that uses local LLMs to crawl websites, process content, and provide intelligent Q&A capabilities with source citations.

beacon-offline-agent★ 3

Offline AI for emergencies with local context and cited answers from community Knowledge Packs.

blazy-build★ 3

Blazy is an AI assistant to learn about any markdown documentation through a question-answer interface. Blazy-build is the API exposing the model.

Multiple-RAG-Systems★ 3

A comprehensive library for Retrieval-Augmented Generation (RAG), featuring both basic and advanced RAG implementations. Built with LangChain for sophisticated RAG pipelines and LlamaIndex for a lightweight, simple RAG setup. Ideal for developers exploring knowledge retrieval and augmentation with LLMs. 🚀

LLM_QA_Using-RAG★ 3

Script leveraging RAG (Retrieval-Augmented Generation) for Question Answering tasks.

wahl-o-chat★ 3

Chatbot zu den Wahlprogrammen zur BTW 2025

moviebot★ 3

A code sample that shows how to use 🦜️🔗langchain, FAISS and a hosted LLM endpoint to do Q&A about 500+ movies in the Kaggle Rotten Tomatoes Top Movies dataset

rag-chatbot★ 3

Farmers' own virtual farmer

docling_RAG_langchain_colab★ 3

This repo contains codes for RAG using docling on colab notebook with langchain, milvus, huggingface embedding model and LLM

Harry-Potter-In-Depth-Query-Bot★ 3

A LLM-powered RAG application designed to answer any query related to the Harry Potter series.

MyKBS★ 3

基于本地大模型+RAG的知识库问答系统

chat-memory★ 3

A notebook to ask GPT-3.5-Turbo questions about a PDF document while keeping track of the previous questions (memory).

Basic-RAG-Chatbot★ 3

This is a basic RAG chatbot made using LangChain, Streamlit, FAISS, Cohere's embed-english-v3.0 and OpenAI's gpt-3.5-turbo or Cohere's command-r

QueryPDF★ 3

QueryPDF is a full-stack application designed to facilitate PDF document analysis through natural language processing. Users can upload PDF documents, ask questions about their content, and receive generated answers.

QABot-with-Conversational-Memory★ 3

Natural Language Query Agent over some web data and some pdf which has conversational memory using Groq Cloud API

ASK-MY-PDF★ 3

Ask-My-Pdf is a user-friendly Streamlit application designed to enhance the way individuals interact with their PDF documents. Whether you're a student, researcher, or professional, this app provides powerful tools to simplify document management.

BioRAG-Oocyte-Agent★ 3

Explore cutting-edge Q&A capabilities with OocyteRAG, a dynamic platform powered by LangChain and HuggingFace technologies.

huggingface-ragflow★ 3

This project implements a classic Retrieval-Augmented Generation (RAG) system using HuggingFace models with quantization techniques. The system processes PDF documents, extracts their content, and enables interactive question-answering through a Streamlit web application.

Bruno_V2★ 3

A Contextual Retrieval RAG application to chat with a PDF or Text file

algo-ai★ 3

AlgoAI is a chatbot (RAG) for answering questions about Data Structures and Algorithms. Built with FastAPI, LangChain, and supports OpenAI or Cohere as LLM providers. Includes features like streaming responses, vector storage with Datastax Astra DB, and message persistence using Postgres.

RAG-Bot★ 3

A Retrieval-Augmented Generation (RAG) chatbot that provides accurate, context-aware responses to hospital-related queries using LLMs and document retrieval.

PaperChat★ 3

PaperChat is an AI-powered chat application designed to handle PDF documents through a user-friendly interface. Users can upload PDF files, ask questions related to the content within those documents, and receive responses generated using advanced natural language processing (NLP) techniques.

wx-rag-airplane-maintenance★ 3

Simple implementation of RAG using watsonx.ai, capturing the chat history to keep track of the conversation context and answer follow up questions.

DocTalk-llm-Powered-PDF-Chatbot★ 3

This repository features DocTalk, an innovative chat application harnessing the power of LangChain, Groq, RAG, and Gemma models for dynamic interaction with PDF documents. Users can effortlessly upload their PDF files, pose inquiries related to the content, and promptly obtain precise responses extracted from the documents.

More in Data, search & knowledge