Hugging Face

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/科技新闻聚合，30分钟自动更新

Automated Hugging Face talent sourcing with n8n + Claude + Airtable

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

🚀 Self-host your own AI agent platform on Hugging Face Spaces for FREE. Run Claude Code, OpenAI GPT, and Google Gemini agents with persistent PostgreSQL storage, auto backup to HF Dataset, Cloudflare proxy, and keep-awake. Zero server needed.

AI-powered Story Generator built with TinyLlama, Hugging Face Transformers, PyTorch, and Gradio.

My Claude Code toolkit — curated skills, MCP servers, and optimized configurations

A Retrieval-Augmented Generation (RAG) chatbot that answers customer support questions over WhatsApp, powered by Hugging Face embeddings, ChromaDB, Groq, and the Meta WhatsApp Cloud API.

Production-grade Agentic Multi-Document RAG Assistant built with LangChain, LangGraph, Gemini, ChromaDB, and Hugging Face Embeddings. Supports PDF, DOCX, PPTX, and TXT ingestion, semantic search, source-aware responses, conversational memory, and multi-user document isolation.

A full-stack AI chatbot application featuring an asynchronous FastAPI backend microservice and an interactive Streamlit UI. Utilises a custom sliding-window truncation filter for memory management and meta-llama-3 remote inference via Hugging Face.

Simple AI chatbot built with Python and Hugging Face API

An AI-powered PDF ChatBot built with LangChain, Groq, FAISS, and Streamlit. Upload PDF documents, ask questions in natural language, and get accurate, context-aware answers using a Retrieval-Augmented Generation (RAG) pipeline with Hugging Face embeddings and semantic search.

An AI-powered RAG chatbot that lets users upload PDF documents and ask natural language questions using LangChain, Groq Llama 3.1, and Hugging Face embeddings.

Production-ready Retrieval-Augmented Generation (RAG) chatbot built with DeepSeek, LangChain, Hugging Face BGE-M3, and ChromaDB for intelligent document question answering.

Hands-on Generative AI Engineering repository covering LLMs, Prompt Engineering, RAG, Vector Databases, Fine-Tuning, Multimodal AI, AI Agents, LLMOps, Evaluation, Deployment, and production-ready GenAI applications using OpenAI, Hugging Face, LangChain, LangGraph, and modern AI engineering practices.

A Retrieval-Augmented Generation (RAG) chatbot using LangChain, FAISS, Hugging Face Embeddings, and Groq Llama.

Local-First AI Support Agent built using LangGraph, Hugging Face, FAISS and RAG for the OrbitDesk

Public reconstruction of an LLM-powered robotics support chatbot developed during my AI research work. Demonstrates context-augmented prompting, Hugging Face LLM integration, Flask deployment, and conversational AI evaluation.

AI Executive Assistant is a multi-agent platform built via IBM BOB using LangGraph, LangChain and LLMs. It enables email management, RAG knowledge retrieval, calendar integration, human-in-the-loop workflows, memory, task planning, analytics, and observability. Supports Ollama, OpenAI, Anthropic, Hugging Face.

AI-powered PDF Question Answering Chatbot using Python, LangChain, Streamlit, Hugging Face, and Groq LLM.

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

A Python Question Answering Chatbot built with Streamlit and Hugging Face Transformers. It uses the DistilBERT model to answer Python-related questions from predefined notes through a simple and interactive interface.

Python QA Chatbot is a lightweight NLP application built using Streamlit and Hugging Face Transformers. It answers user questions about Python programming by extracting answers from a predefined knowledge base using the DistilBERT SQuAD question-answering model.

RAG-powered document Q&A assistant built with Streamlit, LangChain, ChromaDB, Hugging Face Embeddings, and Groq LLM.

A Retrieval-Augmented Generation (RAG) chatbot built with LangChain, Ollama (Llama 3.2), FAISS, and Hugging Face embeddings for answering questions from custom documents.

Built an Educational RAG Assistant using Python, LlamaIndex, ChromaDB, Hugging Face Transformers, and Gradio to enable conversational question answering over PDF documents with vector search and chat memory.

Retrieval-Augmented Generation (RAG) System using LangChain, Mistral, ChromaDB and Hugging Face Embeddings

AI-powered PDF chatbot using RAG, LangChain, FAISS, Hugging Face embeddings, and Google Gemini for intelligent document-based question answering.

AI-powered College Assistant built using LangChain, Google Gemini, Hugging Face Embeddings, ChromaDB, and Streamlit. Implements Retrieval-Augmented Generation (RAG) to answer questions from college documents through semantic search and conversational AI.

Multi-stack AI platform for content analysis using .NET, Python, Java, TypeScript, and JavaScript with OpenAI and Hugging Face integration