Ollama in Google Colab

This repository provides instructions and code snippets for using Ollama in Google Colab notebooks.

Installation

To install Ollama in your Colab environment, follow these steps:

Run the following command in a code cell to install the required dependencies:
```
! sudo apt-get install -y pciutils
```
Run the installation script provided by Ollama:
```
! curl https://ollama.ai/install.sh | sh
```

Import the necessary libraries and define the Ollama function:

import os
import threading
import subprocess
import requests
import json

def ollama():
    os.environ['OLLAMA_HOST'] = '0.0.0.0:11434'
    os.environ['OLLAMA_ORIGINS'] = '*'
    subprocess.Popen(["ollama", "serve"])

Usage

Once Ollama is installed, you can use it in your Colab notebook as follows:

Start the Ollama server by running the following code:

ollama_thread = threading.Thread(target=ollama)
ollama_thread.start()

Run the Ollama model of your choice. For example, to use the mistral model, execute:
```
! ollama run mistral
```
After seeing this message Send a message (/? for help), stop the execution and proceed to the next step.
Now you need to start the Ollama server again by running the following code:
```
ollama_thread = threading.Thread(target=ollama)
ollama_thread.start()
```
Now, you can interact with Ollama by sending prompts and receiving responses. Here's an example:
```
prompt = """
What is AI?
Can you explain in three paragraphs?
"""
```

Then, run the following code to receive the response based on your prompt. Here, stream is set to False, but you can also consider a streaming approach for continuous response printing:

url = 'http://localhost:11434/api/chat'
payload = {
    "model": "mistral",
    "temperature": 0.6,
    "stream": False,
    "messages": [
        {"role": "system", "content": "You are an AI assistant!"},
        {"role": "user", "content": prompt}
    ]
}

response = requests.post(url, json=payload)
message_str = response.content.decode('utf-8')
message_dict = json.loads(message_str)
print(message_dict['message']['content'])

This will send the prompt to the Ollama model and print its response.

License

This content is licensed under the MIT License - see the LICENSE file for details.

Support Us

If you find it helpful, consider supporting us in the following ways:

⭐ Star this repository on GitHub.
🐦 Follow us on X (Twitter): @AITwinMinds
📣 Join our Telegram Channel: AITwinMinds for discussions and announcements.
🎥 Subscribe to our YouTube Channel: AITwinMinds for video tutorials and updates.
📸 Follow us on Instagram: @AITwinMinds

Don't forget to share it with your friends!

Contact