Data, search & knowledge

RAG & retrieval pipelines

5,258 agents · most starred first

RAG & retrieval pipelines, page 23 of 53

DocuMind★ 7

Local-first RAG platform for technical document libraries. Features FastAPI, ChromaDB, and active retrieval (FLARE) powered by Ollama.

halo-plugin-ai-suite★ 7

Halo AI 智能套件:RAG 智能问答、AI 搜索、脑图、摘要、写作辅助、意图路由、评测与运营智能体

macpages★ 7

macOS /manpages skill for AI agents. 15,299 macOS commands = 0 hallucinated terminals

Chatbot-PDF★ 7

streamlit region:us

RAG-with-LangChain-GenAI-Any-url★ 7

streamlit region:us

PDF-RAG★ 7

streamlit region:us

gradio_multi_file_rag★ 7

gradio region:us

PDF_chat_GPT★ 7

gradio region:us

Qwen2.5-0.5B-Rag-Thinking★ 7

safetensors qwen2 text-generation conversational pt base_model:Qwen/Qwen2.5-0.5B-Instruct

Phi-3-Context-Obedient-RAG-GGUF★ 7

transformers gguf mistral quantized 2-bit 3-bit

PDF-RAG-Chat-bot★ 7

gradio region:us

AI-Chatbot-With-Retrieval-Augmented-Generation★ 7

gradio region:us

ragtrack★ 7

RagTrack is a lightweight Git-like version control layer for RAG knowledge bases. It basically helps you track changes across different documents in your RAG Application

svoi-oss-rag★ 7

Desktop client for Svoi's external RAG ('My PC') — indexes local folders and uploads them end-to-end-encrypted over a blind relay. The server holds no keys.

AI-Companion★ 7

A modular, local AI companion featuring a RAG pipeline with FAISS and SentenceTransformers for semantic long-term memory. Powered by GGUF models via llama-cpp-python

financial-rag★ 7

Financial domain RAG QA system with hybrid retrieval + self-correction, powered by SiliconFlow Qwen3-8B and ChromaDB | 金融领域 RAG 问答系统,混合检索 + 自我修正,SiliconFlow Qwen3-8B + ChromaDB

Clarus★ 7

Clarus is a RAG system for maximum retrieval accuracy on religious texts. It combines dense semantic search with multi-agent LLM synthesis to provide scholarly-quality comparative analysis across the Quran (8 Turkish translations) and Bible (English KJVA + Turkish).

Ragworks★ 7

Ragworks — a self-hosted, low-code workbench for building transparent, traceable RAG pipelines. Wire up ingestion and retrieval visually, then see exactly what every run did.

iftree-editor★ 7

本地优先的文档数据管理工具:把大规模语料整理成带稳定地址的条件树,精确定位片段且可回溯出处;关键词 + bge-m3 语义检索,经 MCP 开放给外部 AI agent。

GoldPan★ 7

Privacy-first Multimodal Data Refinery, Repo Context Firewall (Prompt Injection & Trojan Source Defense), Offline Vietnamese OCR, Multilingual E5 ONNX + SQLite FTS5 RAG & 9-Tool MCP Server.

llm-mcp-rag-typescript★ 7

A lightweight, framework-free Augmented LLM Agent powered by LLM + MCP + RAG

OpenCone★ 7

Apple-native cloud-hybrid RAG client for PDFs and personal files using SwiftUI, Vision OCR, OpenAI embeddings and Responses API, and Pinecone vector search.

rag-ferrite★ 7

Personal RAG engine — simple, fast, Rust. One binary (15 MB), one DB, native collections. MCP-native.

openrag★ 7

OpenRag - OpenRAG turns private documents into a secure AI knowledge system

RAG-Evolution-Playbook★ 7

Turn RAG system evolution into solution packages you can review, port - and reject. Two independently adoptable design packages (knowledge compilation / governed improvement), 40 claims with evidence coordinates, contracts, governance gates, D0-D5 handoff. Docs only: no runtime code, no unverified benefit numbers.

Spring-AI-Rag★ 7

A Rag App with Spring AI and MongoDB

piekbs★ 7

Agent-native LLM Wiki (Karpathy-style) RAG: distill raw docs → structured Markdown wiki → hybrid search via MCP

sovena★ 7

Zotero → Markdown 语义文献包 → 向量检索 · 本地文献流系统 · MCP 服务

AWS-BEDROCK-PROJECT★ 7

Terraform-deployed RAG application using Amazon Bedrock, Aurora PostgreSQL/pgvector, S3, and Python.

RAG-smart-flowpai★ 7

A production-grade Retrieval-Augmented Generation (RAG) system for intelligent document processing, semantic search, and conversational AI.

multiagent_rag_movieRec★ 7

A 4-step multi-agent RAG system (preference understanding, semantic alignment, contextual summarization, ranking) leveraging user watch history, mood, and movie metadata; deployed via Streamlit UI and evaluated using NDCG@5 and HIT@5.

atlas-agentic-rag-platform★ 7

ATLAS — industrial Agentic RAG platform (LangGraph): routing, query decomposition, Corrective RAG, Self-RAG reflection. FastAPI + SSE, pluggable vector stores, auth, rate limiting, tracing, Docker, CI. Academic webinar kit on archive/academic-labs branch.

pdf-qa★ 7

An AI-app that allows you to upload a PDF and ask questions about it. It uses OpenAI's LLMs to generate a response.

av★ 7

Video Memory CLI: index once, search/ask forever (dense captions + transcripts + timestamps). Built for agents.

LeetRAG★ 7

AI-powered LeetCode analytics platform — syncs your solving history and uses RAG (Gemini + ChromaDB) to answer personalized questions about your strengths, weaknesses, and growth areas. Built as a Turborepo monorepo with real-time SSE sync, BullMQ background jobs, and full observability (Prometheus/Loki/Grafana)

cookbookLM★ 7

An Open Source alternative of Google's NotebookLM

IntelliRAG★ 7

A domain-specific OFFLINE RAG system for intelligence analysis, built to retrieve and rank terrorism incident data from the Global Terrorism Database. Uses hybrid semantic + keyword retrieval, metadata scoring, and attack-type reranking, achieving 95.2% Precision@5 on evaluation queries.

inovel-agent★ 7

A conversational agent over a private corpus of 7,655 Chinese web novels (plain TXT, ~36 GB). LLM-built book cards and a Qwen3 multi-vector index turn the raw text into searchable artefacts; the agent searches, verifies constraints per book, recommends with reasons and answers in-book questions. Two-stage evaluation: index supply, agent protocol.

Cymatix-Context★ 7

Same query, same answer: deterministic RAG for agents. Local-first: one SQLite knowledge store, no LLM call on the retrieval path, CLI + HTTP + MCP, and a know/miss contract on every response.

exegete★ 7

Exegete: agentic qualitative data analysis application. You work in conversation with your AI assistant. Extensive human oversight routines and integrity checks are built-in. Files can be pseudonymised before the agent reads them. Works with cloud and local models. Projects remain compatible with QualCoder so that work can continue there as well.

nextcloud-ai★ 7

AI assistant for Nextcloud with cited file search, local and hosted models, and app integrations

fRAG★ 7

fRAG is a RAG tool without GPU and paid clouds dependencies

genpark-cosine-bm25-reciprocal-rank-fusion-skill★ 7

Zero-dependency hybrid retrieval engine fusing sparse lexical BM25 Okapi and dense Cosine vector similarities via Reciprocal Rank Fusion.

genpark-rag-semantic-boundary-chunker-skill★ 7

Semantic boundary preserving text chunker maintaining markdown headers, code fences, and paragraphs with token overlap

VN_AI_Innovation★ 7

AI Public Service Assistant for VAIC 2026 (Team Lead · MindSync). Grounded RAG, statutory verification & citizen workflows.

genpark-bm25-okapi-document-ranker-skill★ 7

Okapi BM25 information retrieval document scoring and search engine with document length normalization.

ai_bidding_power_grid★ 7

电力行业 AI 标书编制工作台:招标文件解析、RAG 知识库、AI 辅助写作、合规检查与 DOCX 导出,支持私有化部署。

Afterglow-Desktop★ 7

基于 RAG(免微调)重现语气与记忆的 Afterglow 桌面端。让曾经对话的温度,延续为往后的陪伴。 | Official Desktop client for Afterglow, powered by RAG (no fine-tuning needed). Let the warmth of past conversations continue into companionship.

RAG_ChatBot★ 7

Local PDF RAG chatbot built with Streamlit, LangChain, and Ollama, with Vosk voice input and text-to-speech.

content-lake-app★ 7

App for OpenArch: semantic search and RAG over Alfresco and Nuxeo content on Hyland OpenArch. AlfrescoLabs project, not supported by Hyland.

ComplianceRAG★ 7

Multi-agent RAG with a critic agent that scores groundedness and flags hallucinations in real time. FAISS + sentence-transformers + Gradio.

frontiertour27-ILL392-build-agentic-ai-postgres-apps-on-azure-horizondb★ 7
garage-rag★ 7

A utility for reading in the corpus of your life...

langchain-agent★ 6

These #LangChain-powered apps include a Research Assistant that generates reports using web scraping and GPT-4o-mini, and Chat With Video, a #Streamlit app that #transcribes videos and enables content-based Q&A via #embeddings.

llamachirp★ 6

Engage in dynamic conversations with PDFs to extract and comprehend information using locally hosted LLM variants of Ollama by integrating RAG.

MemeMind★ 6

FastAPI Local RAG Q&A Demo

rag-forge★ 6

Production-grade RAG pipelines with evaluation baked in

RAG-Retail-Inventory-Agent★ 6

Use a RAG Langchain agent that connects to your supermarket's inventory database and get information about product stocks and locations.

github-guide★ 6

Master GitHub with a Qwen AI app built on LangChain, Hugging Face & FAISS.

RAGenius★ 6

AI-powered knowledge base chatbot with RAG. Upload docs, ask questions, get accurate answers with sources. Supports OpenAI/local LLMs.

vc.ai★ 6

A simple implementation of the RAG architecture on an Investor database to give you a VC fund raising assistant

echo-intellect★ 6

Voice-first personal knowledge assistant powered by RAG. Upload docs, ask via voice or text, get answers grounded in your own knowledge base.

youtube-transcript-rag★ 6

This is a YouTube Q&A Chatbot powered by a Large Language Model (LLM) and FastAPI. Users can enter a YouTube video URL and ask questions — the system generates accurate answers using the video transcript.

nicolay★ 6

Nicolay is a digital history experiment that uses artificial intelligence to explore the speeches of Abraham Lincoln.

RAG-Raptor-RE-Ranker-demo★ 6

The method of re-ranking involves a two-stage retrieval system, with re-rankers playing a crucial role in evaluating the relevance of each document to the query. RAG systems can be optimized to mitigate hallucinations and ensure dependable search outcomes by selecting the optimal reranking model.

rag-assistant-ollama★ 6

A RAG assistant using Ollama (Mistral), Qdrant vector DB, and Streamlit UI. Upload documents, scrape web pages, and interact with your data using real-time, session-isolated chat.

Document-Question-Answering-GenAI★ 6

This is a document question answering app made with LangChain and deployed on Streamlit where you can upload a .txt or .docx file, ask questions based on the file and an LLM like Falcon-7B or Dolly-V2-3B answers it. ChromaDB is used as the vector database.

genai-kendra-langchain★ 6

GenAI demo with Amazon Kendra, 🦜️🔗 LangChain and Amazon SageMaker JumpStart

KONSPECTO-LLM★ 6

LLM agent that provides tools for convenient work with personal documents using voice or text.

llm-recommender-system★ 6

Interactive Book Recommendation System using RAG and RecSys

RAG-over-Audio-Data★ 6

Python-based system designed to transcribe audio files, split the transcripts into manageable chunks, create text embeddings using HuggingFace models, and employ advanced question-answering models for retrieval-based QA.

Chat-With-Multiple-PDF★ 6

A Langchain app that allows you to chat with multiple PDFs

biophenotype-rag★ 6

This project implements a RAG (Retrieval-Augmented Generation) application to answer questions about phenotypes using biological and genomic data. The pipeline integrates information retrieval with response generation via language models (LLM), facilitating accurate analysis of phenotypic data.

RAG-MultiFile-QA★ 6

A RAG (Retrieval-Augmented Generation) AI chatbot that allows users to upload multiple document types (PDF, DOCX, TXT, CSV) and ask questions about the content. Built using LangChain, Hugging Face embeddings, and Streamlit, it enables efficient document search and question answering using vector-based retrieval.

gpt4-langchain-pdf-chatbot★ 6

GPT4 & LangChain & Chroma - Chatbot for large PDF docs

MedAssistant★ 6

This is a toy Web application written in Flask, featuring a Medical Assistant Chatbot powered by Large Language Models (LLMs) and Retrieval Augmented Generation (RAG).

DocForge★ 6

A RAG pipeline that doesn't trust its own answers. 4 AI agents collaborate to route queries, retrieve docs, synthesize answers, and catch hallucinations automatically.

pokemon-agent★ 6

This is a AI Agent developed during a college project for the Machine Learning class. It is trained using the PokeAPI with the PokeBase library from Python and RAG documentation provided by Bulbapedia.

RAG_with_lm_studio★ 6

LM Studio에서 실행하는 로컬서버의 LLM과 임베딩을 이용하여 RAG 웹 챗봇 만들기

SmartRAG★ 6

SmartRAG is a terminal-based RAG system using LangGraph. It processes queries by retrieving relevant content from markdown or PDFs, then responds using OpenAI GPT. Supports webpage-to-PDF conversion, vector DB search, and modular flow control.

rag-with-knowledge-base-management★ 6

RAG (Retrieval-Augmented Generation) app integrated with a voice assistant and knowledge base management system.

Athina-AI★ 6

Creating RAG from Scratch . Creating RAG using the langchain. Creating RAG using llama indexing and Qdrant db

langchain-chatyuan★ 6

基于本地知识库的轻量化对话机器人

Documentor-pdfChatbot★ 6

DocuMentor is a sophisticated chatbot application designed to assist users in extracting valuable information from uploaded PDF documents. Users can upload PDF files, chat with the AI chatbot to ask questions or seek information related to the document, and receive well-informed responses.

ABC-RAG★ 6

This project implements an Agentic RAG (Retrieval Augmented Generation) Chatbot, initially accessible via a web interface. The bot's primary role is to serve as a genuine and professional company assistant, capable of engaging with clients, understanding their needs, and effectively guiding them towards purchasing our services and products.

gdrive-chatgpt★ 6

Interactive ChatGPT model for querying Google Drive content. Extract insights from your documents effortlessly.

FileQueryBot_Open★ 6

An Open source version of FileQueryBot. Unleash the power of conversational AI on any document. Upload or link files in any format - PDF, TXT, PPTX, DOCX, and more - and let FileQueryBot answer your questions with precision and ease.

Onboarding-Chatbot★ 6

A Flask-based onboarding chatbot utilizing Retrieval-Augmented Generation (RAG) with Llama 3.1:8b, powered by LangChain. Designed to assist new employees with onboarding tasks through intelligent, context-aware responses.

ask-my-docs-langchain-gradio★ 6

Upload PDFs, ask questions, and get answers with source references using LangChain, Gradio, and local document storage. An open-source AI-powered Q&A tool with source transparency.

bible_chats★ 6

RAG (Retrieval-augmented generation) app made with Flutter, Firebase, Gemini, LangChain and Pinecone.

cargo★ 6

Cargo is an AI-powered advanced multimodal RAG chatbot designed to enable automotive companies to interact effectively with their extensive user manuals.

ochabot★ 6

Rag Tools for Retrieval QA

rag-recipes★ 6

This repository contains various techniques for Retrieval-Augmented Generation (RAG) systems.

gemini-langchain-rag★ 6

A demo project to build a Google Cloud Certifications Chatbot using Langchain, Google Cloud AI Platform, and Vertex AI.

nextjs-langchain-gemini-rag-pdf-chatbot★ 6

Next.js LangChain Gemini RAG Chatbot: An advanced Retrieval-Augmented Generation (RAG) chatbot that enables users to upload multiple PDFs and receive precise answers to their questions based on the content. Powered by LangChain and Gemini, this chatbot is built with Next.js and offers efficient PDF-based query handling for enhanced user engagement.

rag-with-human-support★ 6

Check out the blogppost!

BedrockChat★ 6

BedrockChat acts as a conversational interface, leveraging generative AI models fine-tuned on your content.

selfhosted-llm-rag-app★ 6

A RAG App on Self hosted kubernetes platform

axonode-chunker★ 6

Advanced semantic text chunking with custom structural markers, whole-text coherence preservation, and flexible token management. Features async processing, LangChain integration, and dynamic drift detection. Ideal for RAG systems, augmented text processing, and domain-specific document analysis.

prod-rag-with-gemini-pro-and-pinecone★ 6

Gemini Pro LLM and Pinecone Vector Database for fast and performant Retrieval Augmented Generation (RAG) with LlamaIndex

More in Data, search & knowledge