Performing Data Science Tasks with LLM-Based Agents CrewAI

Author(s): Cornellius Yudha Wijaya

Originally published on Towards AI.

Trying out the agents to do data scientist activity
Image generated by DALL-E 3

LLM-based Agents or LLM Agents are agent structures that could execute complex tasks with LLM applications that have an architecture that combines LLMs with components like planning and memory. In simpler terms, LLM Agents is a tool where LLM is the brain and orchestrates the decision to achieve the goals.

One of the LLM-based agent frameworks that are easy to use is the CrewAI. By employing agents and initiating the tasks, we can perform complex analyses to solve our problems automatically. This is an interesting prospect, especially for a data scientist who requires complex analysis to develop their model.

I want to experiment with whether CrewAI could perform data science tasks or not. So, let’s get into it.

The first thing we need to do is to install the CrewAI. You can do that by executing the following code in your CLI.

pip install crewai

Then, let’s try out the CrewAI agents for our work. I would also explain the components with the example along the way. Additionally, I would use the following Telecom Churn Kaggle dataset as an example.

First, we would set up the environment to accept the OpenAI API keys. The CrewAI agents could work with various LLMs, but… 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