Streamlit

Hands-on Generative AI: 15 RAG modules from document loaders to guardrails, plus Papeer — a research paper assistant with citations and claim verification. Also LangGraph workflows and LangSmith tracing.

Dual-track AI reference architecture: RAG system design & AI Security Engineering (EN/ZH) | 双轨 AI 参考架构：RAG 系统设计与 AI 安全工程

Explainable, retrieval-based medical question answering chatbot built on NIH-sourced data

Production RAG platform — multi-notebook document Q&A with Keycloak SSO, ChromaDB, Claude, Google Drive ingestion

An AI-powered PDF Chatbot built with Streamlit, Ollama, ChromaDB and Llama 3.2.

A Go-native, Streamlit-inspired framework for data apps, dashboards, and AI tools.

Personal study tool — LangChain RAG pipeline for note Q&A + LangGraph stateful quiz agent. Free-tier stack: Groq LLM, HuggingFace embeddings, Chroma vector store, Streamlit UI.

An AI-powered Multi-Document RAG (Retrieval-Augmented Generation) chatbot built with Streamlit, LangChain, FAISS, Hugging Face Embeddings, and Groq LLM. Supports PDF, DOCX, PPTX, and TXT files with automatic OCR fallback for scanned PDFs using Tesseract OCR.

AI Video Intelligence & Knowledge Synthesis Platform built with LangChain,LangSmith, ChromaDB, Whisper, and LLMs.

End-to-end Medical Retrieval-Augmented Generation (RAG) chatbot built with LangChain, FAISS, HuggingFace Embeddings, Groq Llama 3.1, and Streamlit.

Real-time voice chatbot powered by Mistral AI — speak to it, it thinks and talks back. Built with Python, Streamlit & Web Speech API.

Finance-NLP-Chatbot: AI-powered finance tracker for expense insights. Features Financial-Language-Model integration for chat/call data interaction.

AI document assistant with a production RAG pipeline — hybrid BM25 + semantic search, cross-encoder reranking, and streaming answers. Built with FastAPI, Streamlit, ChromaDB, and DeepSeek LLM. Fully Dockerized and deployed on Railway.

Snowflake Cortex demo: 11-lever cost+quality optimization framework for legal-PDF document AI workloads

AI blog studio powered by a multi-agent LangGraph pipeline — route, research (Tavily), plan, parallel section writers, revision, and FLUX.1-schnell diagram generation — wrapped in a light Streamlit editorial UI with a SQLite library.

🍿 A premium AI-powered movie discovery platform. Features Content-Based Filtering using TF-IDF, a high-performance FastAPI backend, and a modern Streamlit "Netflix-style" frontend. Integrated with the TMDB API for live trending data and metadata. 🎬✨

An AI-powered Streamlit dashboard designed to compare and evaluate responses from multiple Large Language Models (LLMs) side-by-side.

Autonomous paper trading bot for Polymarket prediction markets — LLM-powered market analysis (Claude / Ollama), multi-source news ingestion, risk management engine, real-time Streamlit dashboard and Discord alerts.

AI-powered IVF Patient Support Chatbot using RAG, LangChain, Hugging Face, ChromaDB, Streamlit, Prometheus, and Grafana with voice assistance and confidence scoring.

Agente RAG conversacional sobre IA Generativa con Google Gemini, ChromaDB y LangGraph. Memoria por thread, interfaz Streamlit y base de conocimiento propia. Práctica final del Máster en Data Science e IA.

AI-powered opportunity recommendation platform using Streamlit, Python, and Mistral LLM.

🧠 A persistent memory RAG chatbot that never forgets. Uses Phi-3-mini LLM, ChromaDB vector database, and Ebbinghaus memory decay curves.

An interactive Q&A chatbot using Streamlit, LangChain ChatPromptTemplate, and GROQ's Llama 3.1 model for fast and accurate responses.

AI-powered healthcare analytics platform featuring disease prediction, health risk assessment, medicine recommendations, explainable AI, sentiment analysis, and interactive Streamlit dashboards.

A local, Ollama-powered Streamlit application** that demonstrates four key AI patterns in one unified interface: conversational chat,MCP, prompt engineering, RAG (Retrieval-Augmented Generation) over PDFs, and a multi-agent research workflow.

An agentic RAG chatbot built with LangGraph & Streamlit — combines PDF retrieval, long-term memory, web search, and tool-calling (stock prices, calculator, MCP tools) in a single conversational agent.

A local-first multi-agent AI orchestrator with routing, validators, resilience, metrics, retrieval/research scaffolding, coding-agent tools, and release gates.

A secure RAG-powered Text-to-SQL interface built with Gemini 2.5 Flash, ChromaDB, and Streamlit.