Hands-On: Prompt Engineering with Ollama and Google Colab

Author(s): Sayanteka Chakraborty

Originally published on Towards AI.

This member-only story is on us. Upgrade to access all of Medium.

Prompt Engineering is like giving instructions to an AI model to get the best possible answers or results. The way you phrase your prompt can greatly influence the quality of the response.

Types of Prompt:

Zero Shot PromptOne-Shot PromptFew-Shot PromptChain-of-Thought Prompting

Ollama is a framework designed to simplify working with LLMs. It allows users to run these models locally on their own machines supporting GPU acceleration and eliminating the need for cloud services.

It supports variety of Open-source models like Llama, DeepSeek, Phi, Mistral, Gemma.

Using the free version of Google Colab, we can work with models up to 7B parameters. Therefore, we will utilize the Mistral 7B model.

Source: Ollama Website

Enter the following command in a code cell to open a terminal within a Colab notebook:

!pip install colab-xterm%load_ext colabxterm%xterm

The terminal gets launched within a notebook. Next you can type following commands in the terminal:

#Ollama installation command in linuxcurl -fsSL https://ollama.com/install.sh | sh#After installation start Ollama server on local machine and run mistral 7bollama serve & ollama run mistral:7bollama list

Output of “Ollama list Command”

GIN] 2025/02/01 – 14:47:45 | 200 | 62.545µs | 127.0.0.1 | HEAD "/"[GIN] 2025/02/01 – 14:47:45 | 200 | 613.28µs | 127.0.0.1… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI