RAG (Retrieval-augmented generation) ChatBot that provides answers based on contextual information extracted from a collection of Markdown files.

Personal AI with persistent memory. Turns any LLM into an entity that remembers who you are, learns from your conversations, and grows over time. Local, private, yours.

RAG-based Question Answering system using LangChain, Groq LLM, and ChromaDB that processes PDFs and retrieves context-aware answers with source references.

I understood in practical way and tried to explain same.

RAG-based customer support assistant using LangGraph, ChromaDB, and Groq with human-in-the-loop escalation.

Agentic trend analysis system for app reviews using local vector embeddings and semantic deduplication.

Offline-first, multilingual clinical AI for Community Health Workers in Africa — Gemma 4 + RAG over WHO & MSF guidelines

Production RAG system using LangChain, ChromaDB, and GPT-3.5

Sovereign-RAG is a Private Local Intelligence Engine. It allows you to talk to your PDF documents without ever sending that data to the internet. It uses Retrieval-Augmented Generation (RAG), which means the AI "reads" your specific files to give accurate answers instead of guessing.

A minimal, fully local Retrieval-Augmented Generation pipeline built from scratch. Covers document chunking, embedding with sentence-transformers, vector storage via ChromaDB, and LLM generation through Ollama.

A multilingual and multimodal Retrieval-Augmented Generation (RAG) system that enables organizations to query internal documents using AI while keeping data secure. The system processes text, tables, and images from documents and generates grounded answers with citations using modern LLMs.

🧳 智能旅行规划 Agent | LangGraph 编排 + FastAPI + Vue3 | MCP 多工具自主调用 | ChromaDB RAG 知识库 | 用户长期记忆 | Redis 分布式会话 | LangFuse 全链路追踪 | 自我反思质检 | CI/CD 自动化 | 支持流式 SSE 与多方案对比

RAG PDF Chatbot using Python, ChromaDB, Sentence Transformers and Gemini API