RAG & retrieval pipelines
5,258 agents · most starred first
RAG & retrieval pipelines, page 28 of 53
AI-powered ConstructionRetrieval-Augmented Generation system built with FastAPI, Streamlit, Groq LLMs.
A Repository for Intelligent Agents Integrated with Retrieval-Augmented Generation for Querying Automotive Manuals.
Open-source platform for university students
A production-grade Retrieval-Augmented Generation (RAG) system built for 10,860+ Indian Legislative Acts. tackling the unique challenges of processing Indian legal documents—spanning multiple languages, diverse formats, and complex legislative structures
嘉立创EDA专业版扩展:基于本地Embedding模型的RAG知识库。EasyEDA Pro Extension: The local RAG knowledge base based on an embedding model.
Free offline AI with complete Wikipedia knowledge - 100% private
Lightweight Python package for Ollama & 10+ open-source LLMs. No install, no login, no API keys. Free cloud RAG development.
Production Modular RAG System: a compact, production-minded Retrieval‑Augmented Generation (RAG) service built with FastAPI: file ingestion, chunking, embeddings, vector indexing, semantic search, and configurable LLM backends (built with strong software base).
Local-first AI document-intelligence desktop app for Windows (.NET 8 / WinUI 3). Turns your documents into a queryable, RAG-augmented knowledge base — HNSW vector store, hybrid semantic/lexical search, HyDE, LLM reranking. Built-in local Llama 3.2, Ollama, and opt-in OpenAI/Anthropic. No telemetry; local by default.
Open-source local-first AI study workspace for course-material RAG, source-linked answers, and Office/PDF preview.
An AI-workspace starter kit for creating and operating specialized, evidence-grounded context compilers. Includes a local VS Code extension.
Graph-guided RAG interview prep — FastAPI, pgvector, Next.js, eval harness
Knowledge retrieval (RAG) decorators for Azure Functions Python v2
Private, local-first library for your saved Instagram content with an AI chatbot — powered by Ollama, exports to Obsidian
Unified ingestion tool for Google's Open Knowledge Format (OKF): validate, load into a portable DuckDB catalog, and semantically search bundles — from R or Python.
Local-first semantic search, Related Notes & RAG chat for your Obsidian vault — an Obsidian plugin (vault-search-obsidian) and an MCP server (vault-search-mcp) over one LanceDB + Ollama index, with Personalized-PageRank graph retrieval.
Local-first engine that grounds an AI agent's answers in your own Markdown and captures what it learns back into the KB — Node · TypeScript · MCP.
面向中小企业的开源私有化知识库:单实例部署、数据本地可控、LLM 中立。LangChain4j RAG、PgVector 混合检索、Docker 一键部署。
AI and data architecture portfolio: temporal legal search, Azure agentic RAG, and production engineering.
Self-hostable RAG chatbot for networks with no internet access, such as Japan's LGWAN. LDAP authentication, chat history, and admin tools over in-house documents.
An offline knowledge library on a USB drive. Wikipedia, Stack Exchange, Gutenberg, and Khan Academy, plus a local LLM that answers questions using those sources as context. Works on any computer, no internet required.
Local-first literature RAG workbench for PDF, Zotero, Chatbox, and OpenAI-compatible APIs
A RAG pipeline engine for scale
transformers safetensors qwen2 text-generation retrieval-augmented-generation text-generation-inference
Self-healing RAG system that retrieves, verifies, and grades its own answers. Automatically rewrites queries and retries when outputs are weak, ensuring accurate, hallucination-free responses.
Mook - a full-stack RAG proof of concept. FastAPI backend with document ingestion (PDF, Excel, URL) and vector search, a React/Vite front end, and pluggable LLM providers: Claude CLI, Azure OpenAI, OpenAI, or an offline mock for testing.
AI-powered startup intelligence agent — hand-built ReAct loop, parallel tool execution, live web search, and RAG-grounded document analysis. No frameworks. Full understanding.
Lightweight RAG library with ONNX embeddings, DuckDB storage, and three-tier hybrid search (semantic + BM25 + FTS
Local multimodal semantic search for large documents with complex diagrams (like datasheets)
DataBrain is a powerful, modular, and local-first knowledge management and learning platform designed to help you organize, learn, and create interactive content effortlessly. Built with a block-based architecture, it combines the flexibility of a notebook with the interactivity of a modern webapp.
DocsGPT is a powerful web app that allows you to embed your documents then query them using natural language
Fully offline RAG system for PDF question answering and summarisation — Ollama, LangGraph, Qdrant. No cloud calls.
A Retrieval-Augmented Generation (RAG) system for semantic search over PDF documents, powered by Pinecone vector database.
本地优先的桌面 RAG 知识库应用,基于 Tauri、Next.js、FastAPI 构建,支持本地 Embedding、SQLite、Qdrant 向量存储、Ollama/OpenAI 兼容 LLM,将本地文档转化为可检索、可追问、可引用来源的私有 AI 知识库。
AI search over your own X/Twitter bookmarks. Runs entirely on your machine. No account, no API key.
SerenAI is a self-hosted AI chatbot platform that turns your documents into intelligent conversational assistants. Upload PDFs, Word docs, or text files—and instantly create chatbots that can answer questions about your content using RAG (Retrieval-Augmented Generation).
transformers safetensors gguf llama text-generation arabic
NeuraX is a production-ready offline multimodal Retrieval-Augmented Generation (RAG) system designed for NTRO's SIH 2025 problem statement. It provides secure, air-gapped document intelligence with advanced multimodal capabilities and enterprise-grade security features.
This repository contains SupplyChain-AI: An AI-powered generative chatbot leveraging LLMs, RAG architecture, and predictive analytics to answer conversation queries in supply chain management.
Production-oriented Netflix movie recommendation engine built with machine learning, recommendation systems, GenAI, RAG, and MLOps.
Air-gapped enterprise RAG workstation — local inference, zero cloud egress. Built with Microsoft Foundry Local.
Stop searching your documents. Start asking them. Transform Paperless-ngx into a conversational AI assistant using Agentic RAG and the Model Context Protocol (MCP).
AI-powered Medical Assistant using RAG, FAISS, and LLMs to process medical documents, retrieve relevant information, generate grounded answers, and provide source citations.
The project fulfills all requirements by demonstrating a four-node agent workflow and using purely open-source components for RAG and deployment, ideal for learning and testing advanced agent architectures.
A self-hosted, widget-first RAG knowledge base for websites — throw your web pages and local files at it, and it'll answer with cited sources😶🌫️.
A local-first LLM knowledge-base engine that compiles documents into an OKF-conformant, citation-backed wiki
Local-first RAG over your own document library (PDFs, papers, books, notes). Grounded answers with inline citations, eval harnesses that measures retrieval quality, epistemics and per-answer provenance.
Local-first desktop app (macOS & Windows) to chat with your own projects — offline RAG over your files, grounded answers with sources. No cloud, no accounts.
RAG systems, LLM agents, and production pipelines for legal and financial document intelligence.
Working demos built with SuperDoc - document RAG, AI redlining, and more.
Setup your RAG agent using FastAPI with this ONE package!
RAG-tool for workshops and pilotprojects.
Production-grade RAG system for AEC design management with GraphRAG, Ollama, and FastAPI. Supports CAD/PDF parsing, version tracking, and impact analysis.
A local-first desktop workspace that turns your notes, documents, and workflows into context for AI.
A complete Retrieval-Augmented Generation (RAG) pipeline designed for Vietnamese documents. This project implements a full system architecture from document ingestion and hybrid retrieval to grounded generation and automated evaluation, utilizing local LLMs and async operations.
Financial Q&A for Indian equities. Deterministic ratio engine + RAG-powered LLM for NSE/BSE companies. CLI, API, dashboard.
Demo application to chat with a book (using LangChain and Open AI GPT LLM)
制造业 RAG 与设备运维智能体:支持企业知识问答、故障诊断、工单生成及 FastAPI 系统集成。
1,206 Bro. William Branham sermons in structured JSON format. Open dataset for Message developers, researchers, and worship applications.
OjuIye is a provenance-verified, multilingual fact-checking system for Nigeria's 2027 elections. Uses cryptographic source signing to defend against RAG corpus poisoning, with hybrid retrieval across English, Hausa, Yoruba, and Igbo.
Search your Mac by what a page looks like. ColQwen2 over page images, everything local.
Harness & recipes for efficient retrieval LLM agents
OpenBook is an AI-powered research workspace that connects to your PDFs, articles, and videos to deliver precise, citation-grounded answers without hallucinations. It automatically transforms your library into interactive flashcards, quizzes, mind maps, and two-host debate podcasts you can interrupt in real time.
A basic RAG chatbot using LangChain, ChromaDB & Streamlit with Multi-LLM support to answer questions from uploaded PDFs.
Reasoning-based document retrieval using hierarchical tree indexing. No vector databases - LLM navigates a structured document tree to find precise answers.
Local RAG PDF chatbot using n8n, Ollama, Qdrant, and Llama 3.1 for private document-based question answering.
🕌 Hadith RAG — Arabic Retrieval-Augmented Generation Pipeline - Hadith RAG is an AI-powered retrieval and reasoning engine designed for Islamic text understanding — specifically Hadith corpora like Sahih Bukhari, Sahih Muslim, and others. It leverages semantic chunking
Enterprise agentic RAG over the EU AI Act & GDPR: hybrid retrieval, article-level citations, durable human-in-the-loop approvals, grounding checks, evals & audit trail
End-to-end Palantir Foundry & AIP program — pipelines, ontology, Workshop UI, RAG application
A living, unofficial Chinese translation of Wills' Mineral Processing Technology (8th ed.) — faithful, terminology-accurate Markdown built for human study and for vectorising into a mineral-processing AI Agent's knowledge base. Continuing updates welcome.
AI PDF Assistant that extracts, chunks, and answers questions grounded strictly in an uploaded document — with built-in hallucination control. Week 3 of a 90-day AI Engineering roadmap.
Plone Volto addon that integrates Onyx chatbot agents
A FastAPI application combining AI question-answering with PostgreSQL storage. Built with LangChain and OpenAI's GPT models for intelligent responses, using SQLAlchemy ORM for data persistence. Features RESTful API endpoints for CRUD operations with Pydantic validation and Swagger documentation.
RAGKNO — A production-grade RAG system with semantic reranking, hybrid retrieval, multi-source ingestion (Google Drive, PDF, URL), persistent multi-session memory, and source-cited answers. Built with FastAPI, FAISS, and Google Generative AI.
基于 RAG(Retrieval-Augmented Generation) 技术的服装领域知识管理系统。将服装搭配、洗涤养护、尺码推荐等知识文档向量化存储,支持通过 Web 界面上传新知识并自动去重。
A type-theoretic, production-grade retrieval (RAG) engine in modern C++ — hybrid BM25+HNSW, GraphRAG, RAPTOR, rerankers, and a conformant RCP/1 protocol server.
ai个人工作站
Self-hosted knowledge bases for AI agents: hybrid RAG over MCP and REST, one static binary, declarative pipelines
Turn recorded expertise into machine-actionable rules with a local LLM — plus a measured record of every way that LLM lied along the way.
Ohno Ring
Open-source study studio in the spirit of NotebookLM: turn your sources into narrated decks, video and audio overviews, mind maps and notes, every claim cited.
UniGuide is a university-focused RAG API that helps students find grounded answers from academic documents.
本地 RAG 知识库示例:Ollama / BGE-M3 + Chroma + FastAPI,提供 PDF/Excel 检索与 Dify 外部知识库接口。
App for OpenArch: Docker Compose deployment. Not supported by Hyland.
一个基于 RAG 的开源个人知识库,支持文档解析、混合检索、引用溯源和 AI 问答。
Offline Android research assistant with local inference, cited retrieval, and reproducible corpus tooling
LlamaTalks is a Spring Boot-based chatbot application leveraging LangChain4j and Ollama for advanced conversational AI with Retrieval-Augmented Generation (RAG) capabilities. It supports streaming responses, conversation management, document ingestion, and persistent chat history.
RAG for Fiori apps and metadata
Self-hosted MinerU to WeKnora pipeline for parent, child, and raw question-bank retrieval, with read-only ChatGPT MCP access
基于 LangGraph 的企业知识与数据 AI Agent,集成 Hybrid RAG、MCP Tool Calling、Context / Memory、Trace 与离线评测。
Searchable SOLIDWORKS 2026 drawing API database for macros, scripts, and automation
Self-hosted, permission-aware RAG for internal knowledge bases: hybrid search, rerank, cited answers, full traces. One process, one embedded database.
AWS Bedrock RAG tutorial: document Q&A on Bedrock Knowledge Bases + S3 Vectors, streamed through CloudFront. Deploy with CDK or Terraform (same stack), Next.js UI, citations, and a diagnostic that proves it streams.
On-device Retrieval-Augmented Generation using Qdrant Edge, Qwen3 embeddings, and Gemma4.
Multi-agent RAG with a critic agent that scores groundedness and flags hallucinations in real time. FAISS + sentence-transformers + Gradio.
Folio — self-hosted knowledge workspace with RAG, source citations, and LLM observability.
Production-grade hybrid RAG backend built with FastAPI, ChromaDB Cloud, and Postgres (Neon) full-text search. Features structure-aware chunking, cross-encoder re-ranking via RRF, in-process conversation memory with rolling summaries, and a dual-mode runtime (zero-cost local DEV vs. Gemini-powered PROD).
Lumen turns an Obsidian vault from a passive store of notes into an active research collaborator. It runs entirely on local hardware — vault contents never leave the machine.
Awesome list of retrieval-augmented generation (RAG) resources: frameworks, vector databases, embeddings, chunking, reranking, advanced patterns, evaluation, papers — with machine-readable data.
Official implementation of Hi-Q (NeurIPS 2026)