#huggingface

Local AI model manager

Windows GUI for llmfit — find, download, and benchmark local LLMs that fit your hardware

This course is designed to take you from the basics to advanced concepts, providing hands-on experience in building, deploying, and optimizing AI models using Langchain and Huggingface. Perfect for AI enthusiasts, developers, and professionals

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.

Fine-tuning an open 7B LLM into a GST question-answering assistant, with a reproducible eval harness measuring the gain over the base model.

A RAG pipeline that reads PDFs and answers questions using LangChain and ChromaDB. The Streamlit app uses Qwen/Qwen2.5-7B-Instruct while a quantized Zephyr-7B LLM is used in the notebook.

LangGraph agent for the GAIA benchmark — multi-LLM rotation, tool routing, Chroma-based retrieval.

Production-grade LLM fine-tuning with LoRA/QLoRA — dataset synthesis, rigorous eval, cost analysis

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.

I Build a Healthcare retrieval system using GLiNER2, Neo4j, Qdrant, and QQL to convert doctor–patient conversations into structured medical intelligence. Implemented healthcare entity and relation extraction, constructed a knowledge graph, and enabled hybrid semantic and graph-based retrieval for efficient healthcare data search and analysis.

Federal Acquisition Regulation Retrieval-Augmented Generation (RAG) Chatbot

Identify bird species from images along with audio and explore them with AI-powered insights.

Agente de RR. HH. con LangGraph, RAG, FAISS, Groq y Llama 3.3 para responder consultas internas, solicitar información adicional y generar tickets de soporte.

AI-powered PDF Question Answering Chatbot using RAG and Mistral AI

Retrieval-Augmented Generation chatbot that answers questions from PDF documents with source citations and evaluation.

台灣長照 2.0 資格初篩與補助試算 agent：模型只負責對話與意圖理解，金額與級別由版本化 Python 規則引擎計算，另有全文 PII 遮蔽、fail-closed 保守 intake 與 HITL 逐字鎖定發布。20 題固定診斷集下，3B 台灣地端模型端到端由 0/20 提升到 20/20、金額題 13/13、PII 洩漏 0 筆；586 項測試全過

AI-powered full-stack tool that converts Figma designs into React + Tailwind code with a FastAPI backend, Ollama LLM integration, and a React/Vite frontend.

Conversational AI assistant built with Python, Gradio and OpenRouter API.

AI-powered PDF chatbot using RAG, React, FastAPI, FAISS, and LLMs. Upload PDFs, ask questions, search documents, and get AI-generated answers with source citations.

An AI chatbot built with Streamlit, LangChain, Google Gemini, Groq, and FAISS featuring conversational AI and intelligent PDF question answering.

An instruction-tuned conversational chatbot (Qwen2.5-0.5B-Instruct) with multi-turn memory, feedback-driven continuous learning, and a full MLOps pipeline (MLflow, FastAPI, GitHub Actions CI/CD) — DEPI Generative AI capstone project.

A PDF Question Answering chatbot built with LangChain, FAISS, Hugging Face, and Streamlit using RAG

A CPU-friendly AI chatbot built with Python and Hugging Face Transformers — includes knowledge-base search, a Gradio web interface, guardrails, and persistent memory.

A tool that transforms audio or video files into text transcripts and generates concise meeting minutes. Stay organized and efficient in your meetings, and get ready for Phase 2 where we'll be open for contributions to enable real-time meeting transcription!

🐝 State-of-the-art Python AutoML metaframework — fuses GenAI (built on Firefly Agentic / Pydantic AI) with classical ML & Deep Learning. Hexagonal, secure-by-default, governed.

Reproducible QLoRA SFT and DPO experiments for open-weight LLM reasoning, with locked selection, matched controls, and audit-grade provenance.

Hands-on LangChain examples for chat models, LLMs, embeddings, and semantic similarity with OpenAI, Anthropic, Gemini, and Hugging Face.

A modular YouTube RAG chatbot built with LangChain, FAISS, Hugging Face, and Qwen. Retrieves relevant transcript chunks to generate accurate, context-aware answers.

🥖 Offline sourdough bread baking assistant powered by an on-device micro-LLM on ESP32-S3 with OpenAI-compatible WiFi API

Pick the best local AI model for your hardware and task, using live Hugging Face data

Provider-agnostic VLM query flow: one Agent that dispatches to OpenAI / Anthropic / Gemini / vLLM / Claude Code CLI / local HuggingFace model backends, returning parsed answers. Used by 3D-CoT.