retrieval-augmented-generation-rag

A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

Local Llm Suite

🚀 100% local RAG system with one-command setup. Your data never leaves your server. Apache-2.0

Experimental RAG playground for exploring retrieval quality, corpus construction, and filter-chain design. Features configurable ranking and filtering pipelines, visual document grounding, chat interfaces, web search, Open WebUI integration, and rich debugging insights. Ollama and vLLM, running in Dev Containers or natively on Linux and Windows.

Client-side retrieval firewall for RAG systems — blocks prompt injection and secret leaks, re-ranks stale or untrusted content, and keeps all data inside your environment.

Paste any public website URL, ingest its content into Upstash Vector & Jina, and chat with grounded answers via a multi-provider LLM fallback chain (Gemini, Groq, OpenRouter free models, Hugging Face). Built with Next.js 16, React 19, & TypeScript, with live token streaming & Jina (SPA JS-heavy page ingestion), Redis-backed session history

An advanced, fully local, and GPU-accelerated RAG pipeline. Features a sophisticated LLM-based preprocessing engine, state-of-the-art Parent Document Retriever with RAG Fusion, and a modular, Hydra-configurable architecture. Built with LangChain, Ollama, and ChromaDB for 100% private, high-performance document Q&A.

Structural Memory Protocol (SMP) — live structural code graph for scalable, safe AI agents.

LLMlight is a lightweight Python library for running local language models with built-in memory, retrieval, and prompt optimization, requiring minimal dependencies.

RAGify is a modern chat application that provides accurate, hallucination-free answers by grounding responses in your documents. No more made-up information - if the answer isn't in your knowledge base, RAGify tells you so.

A powerful RAG tool that scrapes YouTube channel videos, extracts transcripts, and enables AI-powered chat interactions using Google's Gemini API.

A doctor-assistive AI system that interprets medical knowledge and patient images simultaneously. It utilizes a Dual-Encoder architecture to cross-reference textbook theory with visual pathology, generating clinically grounded diagnoses.

This AI-Powered SIEM is a next-gen security command center built with FastAPI and React. It features real-time log ingestion, an automated threat correlation engine, interactive geo-threat maps, and an integrated AI Security Analyst that streams playbooks and mitigates incidents instantly.

🩺 RAGnosis — An AI-powered clinical reasoning assistant that retrieves real diagnostic notes (from MIMIC-IV-Ext-DiReCT) and generates explainable medical insights using Mistral-7B & FAISS, wrapped in a clean Gradio UI. ⚡ GPU-ready, explainable, and open-source.

An AI-powered HR assistant that uses Retrieval-Augmented Generation (RAG) with FastAPI & Streamlit to answer employee queries, search profiles, and simplify HR resource management

AI-powered medical chatbot using RAG architecture to provide accurate healthcare responses, built with LLMs, Pinecone vector database, and deployed on AWS.

RAG PDF chatbot, retrieval-augmented QA over PDFs using FAISS and Ollama Llama 3.2:3b.

Risk-Aware Introspective RAG (RAI-RAG) is a safety-aligned RAG framework integrating introspective reasoning, risk-aware retrieval gating, and secure evidence filtering to build trustworthy, robust, and secure LLM and agentic AI systems.

A RAG-based retrieval system for air pollution topics using LangChain and ChromaDB.

Enterprise Agentic RAG platform built with FastAPI, LangGraph, LangSmith, OpenAI, PostgreSQL, Qdrant Cloud, Railway, and Streamlit. Features multi-agent orchestration, hybrid retrieval (Vector Search + BM25), CrossEncoder reranking, conversational memory, tool-calling, web-search augmentation, observability, and cloud deployment.