Personal Engineering Server & Microservices
A fully local, containerized AI assistant running on a Mac Mini. Uses LLM inference to analyze and explain C/C++ embedded code, and generate unit tests.
Tech Stack: Python, FastAPI, Docker, Ollama (Qwen)
Launch ApplicationUpload any microcontroller or sensor datasheet. The system embeds the text into a local FAISS vector database and uses LLM to answer technical queries with precise context.
Tech Stack: Python, LangChain, FAISS, Ollama (Nomic + Qwen)
Launch RAG SystemAn interactive 3D motor simulation rendered with Three.js. Live telemetry streams over WebSockets while an LLM operator interprets natural-language commands to control the machine in real time.
Tech Stack: Python, FastAPI, WebSockets, Three.js, Ollama (Qwen)
Launch SimulationA neon oscilloscope that streams live signals over WebSockets, shows an FFT spectrum, and injects faults that an AI diagnoses in real time. Decodes simulated I²C/SPI/UART bus traffic with AI explanations.
Tech Stack: Python, FastAPI, NumPy, WebSockets, Canvas, Ollama (Qwen)
Launch OscilloscopeA secure, local vision analysis tool. Drag and drop engineering schematics, hardware photos, or any image into the scanner zone. A local Vision Language Model analyzes and explains the contents in real-time.
Tech Stack: Python, FastAPI, JavaScript (Base64), Ollama (Moondream)
Launch Vision AIRészletes, interaktív technikai leírás a projektről: architektúra-diagramok, szolgáltatások, API-referencia és üzemeltetés.
Tartalom: Áttekintés, Architektúra & Docker Compose, Reverse proxy, AI Code Linter, Datasheet RAG, AI Digital Twin (3D), Sötét mód, Ollama, Telepítés, API referencia, Fájlstruktúra, Hibaelhárítás.
Megnyitás