Reading Local Files with Python and Ollama

In this tutorial, we’ll walk through how to read local files using Python in conjunction with ollama, a tool that enables interaction with AI models on your local system. Whether you’re a beginner or looking to integrate AI locally, this guide will help you get started.


Before diving in, ensure you have the following set up:

  • Python Installation: If you haven’t installed Python yet, you can easily do so on Windows by using Win-get install Python. Verify the installation by checking the version with python --version.
  • ollama Installation: ollama is crucial for this setup. Install it using your preferred method, such as via Win-get or directly from the Microsoft Store using the provided ID.
  • Environment Variables Setup: If ollama doesn’t work out of the box, configure it in your environment variables. A simple way to do this is through Powertoys’ environment variables program, adding the installation path.

Getting Started with Ollama

  1. Exploring ollama Resources:

    • Visit ollama’s official website to explore available models and documentation. ollama acts as a host for various AI models, making it versatile for different applications.
    • Navigate to the ollama Python GitHub repository, which provides the Python library dedicated to integrating with the ollama API.
  2. Choosing a Model:

    • Review the list of models supported by ollama. Depending on your hardware capabilities and requirements, select a model that suits your needs.
    • For simplicity, this tutorial uses the Q-when-to model, known for its lightweight nature, which makes it easy to run locally.
  3. Downloading the Model:

    • Follow the provided commands to download your chosen model from ollama’s repository or library. This step ensures you have the necessary resources locally available for your AI interactions.

Setting Up Your Python Script

  1. Creating Your Python Script:
    • Open your preferred code editor and create a new Python file ( in this case).
    • Begin by importing ollama to enable interaction with the installed model.
import ollama

note = ''

with open(note, 'r') as file:
    content =

my_prompt = f'This is a personal note, what is it about? {content}'

response = ollama.generate(model='qwen:0.5b', prompt=my_prompt)
actual_response = response['response']
  1. Reading the Local File:
    • Before diving into ollama integration, ensure you have a local file to read. For this tutorial, a sample text file ( contains text that we’ll use as input for our AI model.
This is a note.

I like dolphins.

And I want to ride one, one day...
  1. Implementing the Script:

    • Use Python’s file handling capabilities to read the content of Store this content in a variable (content) to be used as input for the ollama model.
  2. Interacting with ollama:

    • Utilize ollama’s generate function to send prompts to the AI model. In this script, define a prompt (my_prompt) using the content read from
    • Call ollama’s generate method with the specified model and prompt to receive a response.
  3. Displaying the Output:

    • Extract and print the response from the ollama-generated output. This final step demonstrates how the AI interprets and generates insights based on the input provided.

Frequently Asked Questions

Here are some common queries addressed:

  • Using ollama in Python: Yes, ollama offers a dedicated Python library for seamless integration.
  • Purpose of ollama: It serves as a local AI model host, enabling secure and private AI interactions without relying on external servers.
  • ollama’s Suitability: Ideal for integrating AI locally, especially beneficial for handling sensitive data or maintaining privacy concerns.
  • ollama’s Interface: ollama supports both GUI and command-line interfaces, offering flexibility based on user preference.
  • GPU Support: ollama supports various GPUs, enhancing performance for AI tasks that benefit from GPU acceleration.


By following this straightforward guide, you’ve learned how to leverage Python and ollama to read and interpret local files using AI. This setup empowers you to explore AI applications locally, ensuring data privacy and operational efficiency. For more details, refer to ollama’s documentation and resources, or experiment with different models to suit your specific needs.

Start your journey into local AI integration today with Python and ollama, enhancing your projects with powerful AI capabilities right from your own machine.


Thanks for reading, if you like, here’s a video of the whole process too.