How Can I Run Terminal in Google Colab?

Google Colab is a cloud-based Jupyter Notebook environment that allows you to write and execute Python code efficiently. It runs on cloud-based virtual machines, meaning users don’t need to configure local environments. This makes it an excellent choice for data science, machine learning, and general Python scripting. However, sometimes you may need to execute shell commands directly, such as installing packages, managing files, or running system-level utilities. While Colab provides a way to execute shell commands within notebooks, it also allows access to a full terminal environment. In this guide, we’ll show you how to access the terminal in Google Colab, install and use Ollama to pull machine learning models, and then run inference with LangChain and Ollama.

Step 1: Install and Load colab-xterm

To access the terminal in Google Colab, you need to install and enable the colab-xterm extension. Run the following commands in a Colab cell:

!pip install colab-xterm
%load_ext colabxterm

Once installed and loaded, you can launch the terminal by running:

%xterm

This will open a terminal interface directly within your Colab environment.

Install the Ollama in the terminal using Linux command.

curl -fsSL https://ollama.com/install.sh | sh

Step 2: Pulling a Model Using Ollama

Once you have access to the terminal, you can download and use machine learning models. For example, to pull the deepseek-r1:7b or llama3  model using Ollama, run the following command in the terminal:

!ollama pull deepseek-r1:7b

or 

!ollama pull llama3

This will download the model and prepare it for usage in your Colab notebook.

Step 3: Installing Required Libraries

After downloading the model, install the necessary Python libraries to interact with the model. Run these commands in a new Colab cell:

!pip install langchain
!pip install langchain-core
!pip install langchain-community

These libraries are essential for working with large language models in a structured way.

Step 4: Running Inference with LangChain and Ollama

Once all dependencies are installed, you can use LangChain to interact with the model. Add the following code in a Colab cell:

from langchain_community.llms import Ollama

# Load the model

llm = Ollama(model="llama3")

# Make a request to the model

from langchain_community.llms import Ollama

llm = Ollama(model = "llama3")

llm.invoke("tell me about Analytics Vidhya")

Analytics Vidhya!\n\nAnalytics Vidhya is a popular online community and
platform that focuses on data science, machine learning, and analytics
competitions. The platform was founded in 2012 by three data enthusiasts:
Vivek Kumar, Ashish Thottumkal, and Pratik Jain.\n\nHere\'s what makes
Analytics Vidhya special:\n\n1. **Competitions**: The platform hosts regular
competitions (called "challenges") that are open to anyone interested in
data science, machine learning, or analytics. Participants can choose from a
variety of challenges across various domains, such as finance, marketing,
healthcare, and more.\n2. **Real-world datasets**: Challenges often feature
real-world datasets from well-known organizations or companies, which
participants must analyze and solve using their skills in data science and 
machine learning.\n3. **Judging criteria**: Each challenge has a set of
judging criteria, which ensures that submissions are evaluated based on
specific metrics (e.g., accuracy, precision, r

This will load the llama3 model and generate a response for the given prompt.

Also Read: How to Run OpenAI’s o3-mini on Google Colab?

Conclusion

By following these steps, you can easily access a terminal in Google Colab, enabling you to install dependencies, download machine learning models using Ollama, and interact with them via LangChain. This transforms Colab into a versatile AI development environment, allowing you to experiment with cutting-edge models, automate workflows, and streamline your machine learning research—all within a cloud-based notebook.

Frequently Asked Questions

Hi, I am Pankaj Singh Negi – Senior Content Editor | Passionate about storytelling and crafting compelling narratives that transform ideas into impactful content. I love reading about technology revolutionizing our lifestyle.