Rasa Starter Pack: Retail Banking - Instructions

Looking to install and use the Rasa CALM Starter Pack for Retail Banking? We've documented all the steps in these simple-to-use installation instructions.

Once installed, leverage the Starter Pack as the foundation for creating your own Retail Banking Assistant or as inspiration for features you can implement. With the Retail Banking Demo Assistant, you can offer features like transferring money, checking balances, managing payees, and blocking cards.

Installation (Docker)

Note: You can find alternative installation methods in the Rasa documentation.

Installation Steps

  • Before You Begin
  • Setting Environment Variables for Rasa
  • Install Docker
  • Download Rasa Retail Banking Starter Pack
  • Starting the Demo Assistant

Before You Begin

To use this starter pack, you will need:

  1. A free Rasa Developer Edition license. To get the free license use the link and complete the form. You’ll be emailed the license key. Store this somewhere safe as you’ll need it a bit later in the instructions below. The actual installation of the Rasa Pro platform will be performed during the installation steps described below.
  2. An API key from OpenAI (the default model provider for this starter pack, though CALM supports other LLMs, too).
    - If you haven't already, sign up for an account on the OpenAI platform.
    - Then, navigate to the OpenAI Key Management (Dashboard > API keys) page and click on the "Create New Secret Key" button to initiate obtaining <your-openai-api-key>.
  3. A computer. Instructions are available for MacOS, Linux & Windows.

Note for Windows users: If you don’t already have make, you’ll need to install it:

  • Option 1: Install Chocolatey. 👉 Open PowerShell as Administrator (Start → search "PowerShell" → right-click → Run as Administrator).
    Then run:

    choco install make -y

    Verify with:

    make --version

  • Option 2: Install Git for Windows, which includes Git Bash (and make).
    Open Git Bash instead of PowerShell to run your commands.

Setting Environment Variables for Rasa

You'll need to save your Rasa Pro license key and OpenAI API key as environment variables so they can be used by the application.

MacOS, Linux

  1. Open your terminal, and edit your shell config
    i. nano ~/.zshrc (or ~/.bashrc if you’re using Linux bash)
  2. At the bottom of the file, add lines like this (replace the values with your actual keys):
    - export RASA_PRO_LICENSE=<your-rasa-pro-license-key>
    - export OPENAI_API_KEY=sk-<your-openai-api-key>
    i. For example, it may look something like this:
    - RASA_PRO_LICENSE=etou948949theu
    - OPENAI_API_KEY=sk-proj-ntehoitnhtnoe
  3. Save the file (CTRL+O, Enter, CTRL+X in nano), then reload it
    i. source ~/.zshrc (or ~/.bashrc if you’re using Linux bash)
  4. Check that the variables are set:
    i. echo $RASA_PRO_LICENSE
    ii. echo $OPENAI_API_KEY

Windows

  1. Press Win + S and type Environment Variables, then select Edit the system environment variables.
  2. In the System Properties window, click Environment Variables.
  3. Under User variables (applies only to your user), click New.
    i. For Name, enter: RASA_PRO_LICENSE
    ii. For Value, enter: <your-rasa-pro-license-key>
  4. Repeat for OPENAI_API_KEY.
  5. Click OK → OK to save and close all windows.
  6. Restart your terminal (PowerShell) so the new values load.
  7. Verify the variables are set (PowerShell):
    i. echo $env:RASA_PRO_LICENSE
    ii. echo $env:OPENAI_API_KEY

Install Docker

  1. Download & install docker:
    - MacOS: https://docs.docker.com/desktop/setup/install/mac-install/
    - Linux: https://docs.docker.com/engine/install/
    - Windows: https://docs.docker.com/desktop/setup/install/windows-install/
    i. For Windows, use WSL 2 backend (not Hyper-V)
  2. Start Docker Desktop. Make sure Docker Desktop (the Docker daemon) is running before you run any commands.
    - Windows: Follow prompted instructions for WSL (e.g. wsl --update)
  3. Verify Installation. Open your terminal (Mac/Linux shell, or PowerShell on Windows) and run:
    i. docker --version
  4. Download the Rasa Pro Docker image. Open your terminal and run:
    i. docker pull rasa/rasa-pro:3.13.7

Download Rasa Retail Banking Starter Pack

  1. Download the Source Code Assets for the latest release from GitHub
  2. Uncompress the assets in a local directory of your choice.
    i. The starterpack-retail-banking-en directory (created when uncompressed) contains a README file with additional instructions on installing dependencies, training the model, and running the assistant locally.
  3. Open your terminal (or PowerShell on Windows) and navigate to the directory where you uncompressed the starterpack-retail-banking-en files.

Congratulations, you have successfully installed Rasa and are ready to use the Retail Banking Starter Pack as a demo or as a foundation for your custom flows.

Starting the Demo Assistant

To start up the Retail Banking Demo Assistant, ensure you're in the starterpack-retail-banking-en directory.

  1. Train the Rasa model
  2. Start the Rasa Inspector or
  3. Start the Rasa Chat Widget

1. Train the Rasa model

make model
  1. You will find your trained model inside the models/ directory.
  2. You can now test your assistant using the Rasa Inspector or Rasa Chat Widget.

2. Start the Rasa Inspector

make inspect
  1. Once you see the “Starting worker” message in your terminal, proceed to the next step.
  2. In your browser go to: http://localhost:5005/webhooks/socketio/inspect.html

3. Start the Rasa Chat Widget

make run
  1. Once you see the “Starting worker” message in your terminal, proceed to the next step.
  2. Open Finder (Mac) or File Explorer (Windows).
  3. Navigate to the chatwidget directory inside the starterpack-retail-banking-en folder you uncompressed earlier.
  4. Double-click chatwidget/index.html to open the demo in your browser.
  5. You can now interact with the Retail Banking Demo Assistant using Rasa’s chat widget.

Tip: You can also edit chatwidget/index.html to customize the look and behavior of the demo.

Note: For a full list of Rasa CLI commands refer to: https://rasa.com/docs/reference/api/command-line-interface/#cheat-sheet

Stopping the Demo Assistant

  1. To stop the Rasa server, return to the terminal window where it is running and press Ctrl+C.
  2. That's it, you’ve successfully run your first Rasa Assistant! You can now close the terminal window if you wish.

Restarting the Demo Assistant

  1. Open your terminal and navigate to the starterpack-retail-banking-en directory.
  2. Then, follow the same steps from Starting the Demo Assistant to run the assistant again.

Demo examples

For the following examples, please note:

  • Due to the dynamic nature of this conversational bot assistant, the assistant’s responses might differ slightly.
  • Clear your browser’s cookies or open a new incognito window to clear your chat widget conversation history.

You are now ready to start your demo. Feel free to follow the steps below:

Example 1

- bot: "Hello there! I'm Rasano, here to assist you with all your banking needs."
- bot: "Money Transfer"
- bot: "Account Balance Verification"
- bot: "Payee Management"
- bot: "Card Blocking"
- bot: "Banking Questions"
- user: "I want to transfer money"
- bot: "Which account would you like to transfer money from?"
- user: "Savings"
- bot: "Which payee would you like to send money to?"
- user: "Oops, I meant Checking"
- bot: "Certainly! I will update the account from which the funds will be transferred to your checking account accordingly."
- bot: "Which payee would you like to send money to?"
- user: "Who are my payees"
- bot: "You are authorised to transfer money to: Robert, James, Food Market."
- bot: "Which payee would you like to send money to?"

Example 2

- bot: "Hello there! I'm Rasano, here to assist you with all your banking needs."
- user: "I want to block a card"
- bot: "Certainly, I can help you with that. Let's go through the process step by step."
- bot: "Select the card you require assistance with:"
- user: Credit Card selected
- bot: "Please tell us the reason for blocking"
- user: lost selected
- bot: "As your card was potentially stolen, it's crucial to report this incident to the authorities. Please contact your local law enforcement agency immediately."
- bot: "Since you have reported lost, we will block your card"
- bot: "Would you like to be issued a new card?"
- user: Yes, send a new card, selected
- bot: "I have found your address: 1 Psychohistorical Way, Trantor Square, London, SW1A 1AA. Should the new card be delivered there?"
- user: Yes, selected
- bot: "Your card will be delivered to 1 Psychohistorical Way, Trantor Square, London, SW1A 1AA within 7 business days"

Advanced configurations

By default, the Retail Banking Starter Pack always starts the chat session with "John Smith" as the end user. You can easily adjust this to showcase multiple user profiles.

The Retail Banking Assistant includes three user profiles:

  • John Smith with payees: Robert, James, Food Market
  • Mary Brown with payees: Richard, Susan, Electric Company
  • Dan Young with payees: Amy, Gym, William

Each profile has its own account—Current (Checking), Savings, and Business—that influence interactions with the assistant.

To randomly assign a user profile at the start of each session, do the following:

  • In a Mac Finder window, navigate to the actions directory inside the ​​starterpack-retail-banking-en directory.
  • Open the action_session_start.py file.
  • Comment the following line:
    • username = "John Smith"
  • Uncomment the following line:
    • #username = random.choice(["John Smith", "Mary Brown", "Dan Young"])
  • In your terminal window, run:
    • make clean
    • make model
    • make run

Now at the start of each chat conversation session, a random user profile will be assigned.

What’s next?

Congratulations on installing the Rasa CALM Starter Pack for Retail Banking! Click next to access the telecom starter pack.

2016-2025 © Rasa.