Using the Dockerized Platform

PandasAI provides a dockerized client-server architecture for easy deployment and local usage that adds a simple UI for conversational data analysis. This guide will walk you through the steps to set up and run the PandasAI platform on your local machine.


Before you begin, ensure you have the following installed on your system:

  • Docker
  • Docker Compose

Note: By default the platform will interact with the csv files located in the server/data directory. You can add your own csv files to this directory before running the platform and the platform will automatically detect them and make them available for querying. Make sure you replace the existing files with your own files if you want to use your own data.

Step-by-Step Installation Instructions

  1. Clone the PandasAI repository:

    git clone
    cd pandas-ai
  2. Copy thee .env.example file to .env in the client and server directories:

    cp client/.env.example client/.env
    cp server/.env.example server/.env
  3. Edit the .env files and update the PANDASAI_API_KEY with your API key:

    # Declare the API key
    # Update the server/.env file
    sed -i "" "s/^PANDASAI_API_KEY=.*/PANDASAI_API_KEY=${API_KEY}/" server/.env

    Replace YOUR_PANDASAI_API_KEY with your PandasAI API key. You can get your free API key by signing up at PandasAI.

  4. Build the Docker images:

    docker-compose build

Running the Platform

Once you have built the platform, you can run it with:

docker-compose up

Accessing the Client and Server

After deployment, the client can be accessed at http://localhost:3000, and the server will be available at http://localhost:8000.

Troubleshooting Tips

  • If you encounter any issues during the deployment process, ensure Docker and Docker Compose are correctly installed and up to date.
  • Check the Docker container logs for any error messages:
    docker-compose logs

Understanding the docker-compose.yml File

The docker-compose.yml file outlines the services required for the dockerized platform, including the client and server. Here’s a brief overview of the service configurations:

  • postgresql: Configures the PostgreSQL database used by the server.
  • server: Builds and runs the PandasAI server.
  • client: Builds and runs the PandasAI client interface.

For detailed information on each service configuration, refer to the comments within the docker-compose.yml file.