Coursera MOOC / Non-credit 0

Harnessing Ollama – Create Local LLMs with Python

Name: Harnessing Ollama – Create Local LLMs with Python
Price: 49 USD
Availability: InStock

About this course

Updated in May 2025. This course now features Coursera Coach! A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course. In this course, you will learn how to create local language models using Ollama and Python. By the end, you will be equipped with the tools to build LLM-based applications for real-world use cases. The course introduces Ollama's powerful features, installation, and setup, followed by a hands-on guide to exploring and utilizing Ollama models through Python. You'll dive into topics such as REST APIs, the Python library for Ollama, and how to customize and interact with models effectively. You'll begin by setting up your development environment, followed by an introduction to Ollama, its key features, and system requirements. After grasping the fundamentals, you'll start working with Ollama CLI commands and explore the REST API for interacting with models. The course provides practical exercises such as pulling and testing models, customizing them, and using various endpoints for tasks like sentiment analysis and summarization. The journey continues as you dive into Python integration, using the Ollama Python library to build LLM-based applications. You'll explore advanced features like working with multimodal models, creating custom models, and using the show function to stream chat interactions. Then, you'll develop full-fledged applications, such as a grocery list categorizer and a RAG system, exploring vector stores, embeddings, and more. This course is ideal for those looking to build advanced LLM applications using Ollama and Python. If you have a background in Python programming and want to create sophisticated language-based applications, this course will help you achieve that goal. Expect a hands-on learning experience with the opportunity to work on several projects using the Ollama framework.

81/100

CourseAsk score

What the provider tells you: 45/45
Who stands behind it: 20/35
How complete the listing is: 16/20

Scores how much the provider publishes and who stands behind it — not how well it is taught.

What you'll learn

Install and configure Ollama for local LLM deployment
Interact with Ollama models using both CLI commands and REST APIs
Build LLM-based applications using the Ollama Python library
Create custom language models tailored to specific use cases
Work with multimodal models that process different types of input
Implement a RAG (Retrieval-Augmented Generation) system with vector stores and embeddings
Stream chat interactions programmatically using Python
Develop practical applications like sentiment analyzers and text categorizers

Course objectives

Set up a local development environment for running LLMs without cloud dependencies
Master the Ollama framework for managing and customizing language models
Integrate LLM capabilities into Python applications through REST APIs and native libraries
Build end-to-end applications that solve real-world text processing problems

Machine Learning Artificial Intelligence #python #rest api #prompt engineering #sentiment analysis #llm deployment #text summarization #retrieval-augmented generation #ollama #local llm #language models #rag systems #vector embeddings #multimodal models #model customization #cli tools

$49.00

Price shown by Coursera — confirm on their site.

Enroll on Coursera

You'll be redirected to Coursera to complete enrollment.