Building an open source AI Assistant

Here we will discuss about the strategies to get Local LLMs working and using Local AI to build beautiful functional products. The current stack include building simple tauri / electron apps with ollama to perform inference locally and get outputs.

We will discuss voice assistant, real time Chatbots and build/ show a quick demo on the same. We will be using a tiny qwen0.5 B / moondream 0.5 B and other local Models that you can use daily, model to play around with.