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.

Before You Begin

To use this starter pack, you will need:

  • A free Rasa Pro 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.
  • 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) https://platform.openai.com/api-keys page and click on the "Create New Secret Key" button to initiate obtaining <your-openai-api-key>.
  • A Mac computer (preferred). Instructions are also available for Linux with minimal modifications, with Windows support coming soon.

Installation steps

  1. Download the Source Code Assets for the latest release from GitHub:

  2. Uncompress the assets in a local directory. The zip file is preferred for Macs.

    • You can find instructions for installing dependencies, training the model, and running the assistant locally in the README file located inside the ​​starterpack-retail-banking-en directory where the zip file was uncompressed.

  3. Navigate to the ​​starterpack-retail-banking-en directory where the zip file was uncompressed, and run the following commands in your terminal to set up your environment:

    • make install-homebrew
      i. Note: You may need to run the following commands if prompted:
      1. echo >> $HOME/.zprofile
      2. echo 'eval "$(/opt/homebrew/bin/brew shellenv)"' >> $HOME/.zprofile
      3. eval "$(/opt/homebrew/bin/brew shellenv)"
    • make install-pyenv
    • make install-uv
    • make setup-pyenv-virtualenv
    • source ~/.zshrc
    • pyenv activate rasa3.11.3-py3.11.11
      i. Note: Use the command `pyenv versions` to view your version. The versions of Rasa and Python may differ based on updated versions of releases of the starter pack in Github.
    • make install-packages
    • source deactivate

  4. Once the installation is complete, update the placeholders in the Makefile file with your actual values: (Note: remove the # and <, > characters too), and save the file.

#RASA_PRO_LICENSE=<your-rasa-pro-license-key>
#OPENAI_API_KEY=sk-<your-openai-api-key>

For example, after updating, it would look similar to this:

RASA_PRO_LICENSE=etou948949theu
OPENAI_API_KEY=sk-proj-ntehoitnhtnoe

  1. Run the following commands in your terminal:
    • make set-env
    • source ~/.zshrc

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

To start up the Retail Banking Demo Assistant, follow these steps:

  • Ensure you're in the ​​starterpack-retail-banking-en directory.

  • Next, type the following commands in your terminal window:

1.pyenv versionsList your Rasa / python versions
2.pyenv local rasa3.11.3-py3.11.11Activate your Rasa python environment (use your version from previous step)
3.rasa --versionConfirm your Rasa / python version is actively set
4.make cleanThis will clean all Rasa files
5.make modelThis will train the Rasa model
6.make runThis will start the Rasa server
  • Once you see a 'Starting worker' message in the terminal window, proceed with the next step.
  • In a Mac Finder window, navigate to the chatwidget directory inside the starterpack-retail-banking-en directory where the zip file was uncompressed.
  • Double-click on the index.html to open the demo. You can now interact with the Retail Banking Demo Assistant using Rasa's chatbot widget.
    • Note: It is also possible to modify this index.html to your liking.

Stopping the demo

  1. To stop the Rasa server go to your terminal window and press: Ctrl-C
  2. Congratulations you have successfully run your first Rasa Assistant. Feel free to close your terminal window.

Restarting the demo

  1. Open your terminal window and navigate to your starterpack-retail-banking-en directory.
  2. Repeat Starting the Demo Instructions

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: "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! Stay tuned for more starter packs coming soon.

2016-2025 © Rasa.