| Home (Pong RL Agent) | Mike 3.0 (RAG Chatbot) |
|---|---|
| Personal Knowledge Base (PKM) | Projects |
Personal
MKK Frontend
Aug 2024
Related Projects
MKK Blog
Aug 2024 - Dec 2025POST WIP

Personal
Mike 3.0: RAG Powered LLM Model for Chatbot Backend
RAG backend chatbot service built with FastAPI and pgvector. It features real-time document ingestion and LLM-powered responses.
RAGFastAPIPythonuvPostgreSQLpgvectorPytest+6

Personal
RAG vs LoRA: LLM Fine-Tuning Comparison for Mike 3.0
An experimental comparison between RAG and LoRA for building a personal portfolio chatbot.
LoRARAGMLXOllamaGemmaLangflowSupervised Fine-Tuning+4

Personal
Pong (Reinforcement Learning) with WebSocket Backend
Training PPO agents to master Atari Pong using PyTorch and PettingZoo, served to browser via WebSockets.
RLPPOPyTorchFastAPIuvWebSocketPettingZooGymnasium+5
