Self-Evolving RAG System with ChromaDB for continuous knowledge updates (6x daily), designed to overcome Large Language Model data cutoff limitations.

An AI-powered crypto analytics platform integrating forecasting, sentiment, and on-chain intelligence, built with FastAPI, MCP protocol, and MLflow in a monolithic architecture.

Turn any LLM into a self-extending knowledge agent powered by a graph-structured memory - complete with PDF-to-graph ingestion, budget-aware optimisation, and dual-engine orchestration.

酒店评论分析与智能问答系统。复旦管院《大模型技术原理与商业应用》课程项目可复用开发模板见 Branch 001 或 Release v1.0.0。由于后端服务器部署在海外，又需要调用国内阿里云服务，因此下方项目网站智能问答可能存在较大延迟；若本地部署则首字延迟可以控制在 3 秒左右。

🧮 PINN Enterprise Platform - AI-Powered Physics Simulations with CopilotKit-style Research Canvas UI. Complete serverless architecture with RAG-powered code generation, 3D visualization, and global edge deployment.

ByteShaala 2.0 🚀 More powerful. More unified. Where code meets creativity — now built as one solid system. ⚡💻🔥

icron YOUR lightweight Personal AI Assistant - permanent Markdown memory with hybrid BM25 + vector search

Terminal-based platform where specialized AI experts (Legal, Tech, Business) engage in real-time debates and collaborative problem-solving to provide multi-perspective analysis for complex decisions.

Enterprise-grade AI voice assistant with RAG-powered customer support, real-time phone integration, and advanced conversation management

Retrieval Pivot Attacks in Hybrid RAG (Vector → Graph)

An AI-powered assistant that learns Dungeons & Dragons (D&D 5e) rules from PDFs, answers rules questions using a RAG (Retrieval-Augmented Generation) pipeline, and falls back to web search + a cloud LLM when local context is not enough.

DiagnoAI: Medical RAG Assistant - Educational AI system for healthcare information retrieval using multi-source medical knowledge and advanced search. FOR LEARNING AND RESEARCH ONLY.

An AI-powered cognitive health analytics platform that monitors burnout risk through intelligent activity classification and metabolic insights. Uses RAG-based LLM analysis to detect cognitive decline patterns and provide personalized wellness recommendations.

RAG-Chat-Assistant is a complete Retrieval-Augmented Generation (RAG) system packaged as a sleek web app. Built with a Flask backend, it enables users to drag and drop documents (PDFs, Word, TXT) and chat with an AI assistant that understands their content. It processes files by chunking and embedding them with Google Gemini models, stores embeddin

Enterprise AI ERP - Plataforma Inteligente de Gestão para Agências (Vyron System).

Secure RAG-based AI assistant for FinTech, using FastAPI & LangChain to deliver departmental data through Role-Based Access Control (RBAC)

Agentic Personal Medical Assistant - a safety-first advisory AI that reasons over medical records and imaging using multi-agent orchestration with relational and vector databases.

Multi-agent AI system combining RAG, web search, fact-checking, and synthesis to produce well-cited research reports. Demonstrates agentic design patterns in action.

AI-powered research assistant with voice interaction, multimodal RAG, and intelligent routing. Explore academic papers effortlessly using LLMs & ChromaDB.

A multilingual Retrieval-Augmented Generation (RAG) system built for an assessment. It features text processing, intelligent document chunking, semantic search with multilingual embeddings, and conversation memory management. Leverages FastAPI, LangChain, and ChromaDB for efficient knowledge base querying.