You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
ML system for sales prediction leveraging PyTorch and LightGBM models, managed by an MLOps pipeline using DVC and Prefect for data lineage and orchestration. Deployed as a serverless microservice on AWS Lambda via ECR/Docker. Secured by a CI/CD pipeline w/ Synk and quality gates.
A Python library to help monitor solar charge controllers typically used in off the grid applications. This fork has been modified and containerized to run on a Raspberry Pi.
Real-time video broadcasting backend built with Django and WebRTC. Implements WebSocket signaling with Django Channels and supports unique stream IDs for live video streams. Designed for containerized deployment with Docker and seamless integration with a React frontend.
The Ollama Chatbot is an AI-based chatbot that utilizes the llama3.2:3B model or alternative models. It can incorporate Retrieval-Augmented Generation to deliver enhanced automated responses when desired. The project is managed through Podman containers, allowing for efficient and scalable deployment.
A containerized, offline-capable LLM API powered by Ollama. Automatically pulls models and serves them via a REST API. Perfect for homelab, personal AI assistants, and portable deployments.