Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn to build a complete AI assistant application from scratch using Docker's new Model Runner to serve open-source LLMs locally, combined with a Streamlit chat interface that maintains conversation memory across both local and cloud-based models. Master the setup of Docker Desktop and Model Runner CLI, then progress through creating a containerized Python application using Docker Compose that integrates Langchain for LLM operations. Develop a clean chat GUI with Streamlit that stores conversation history in user sessions, enabling seamless context switching between a lightweight local model and powerful cloud models via OpenRouter. Implement conversation memory that allows both local and cloud models to maintain awareness of the entire chat history, including messages from other models. Explore best practices for environment variables, requirements management, and health checks in a fully containerized setup. Build a production-ready foundation that can be extended for more advanced AI applications, with all dependencies packaged in Docker containers for easy deployment and scalability.
