Run LLMs Locally with Python: Build Private AI Apps

About this course

This course teaches you how to run LLMs locally with Python and build practical AI applications without depending on cloud APIs, subscriptions, or sending your data to external services.

You’ll set up a local LLM environment on Windows, macOS, or Linux, connect to local models using Python, and progressively build real LLM capabilities including prompting, conversations, tools, function calling, and Retrieval-Augmented Generation (RAG).

Run Local LLMs and Build Practical AI Applications with Python

You’ll start by understanding the hardware and software requirements for running LLMs locally. Then you’ll install and configure the required tools, run your first local model, and verify that everything works on your computer.

From there, the course moves from setup into practical LLM application development. You’ll learn how LLM roles, tokens, context windows, prompts, and message flows work, and apply these concepts through Python-based examples.

You’ll also build practical capabilities including:

• Running open-source LLMs locally on Windows, macOS, and Linux
• Setting up a local AI development environment with Python and Poetry
• Connecting Python applications to local LLMs
• Understanding tokens, context windows, roles, and message flows
• Applying prompt engineering with practical coding examples
• Building multi-turn conversations with local LLMs
• Using tools and function calling to build an LLM-powered customer support agent
• Understanding Retrieval-Augmented Generation (RAG)
• Building a practical RAG application using a local LLM
• Working with concepts such as embeddings, vector databases, and retrieval
• Building privacy-focused AI applications that can operate locally
• The course follows a hands-on, local-first approach.

Read the full description on Udemy on Udemy (opens in a new tab)

Prices, discounts and availability are set by Udemy. We may earn a commission when you purchase through links on this site.