Rasa Starter Pack: Telecom - Instructions

Looking to install and use the Rasa CALM Starter Pack for Telecom? 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 Telecom Assistant or as inspiration for features you can implement. The Telecom Demo Assistant focuses on two key customer support areas:

  • Helps users check their monthly expenses/billing details.
  • Guides users through basic troubleshooting steps to resolve slow internet issues. making sure the user is engaged through all the necessary steps.

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 Telecom 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 Telecom 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-telco-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-telco-en files.

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

Starting the Demo Assistant

To start up the Telecom Demo Assistant, ensure you're in the starterpack-telco-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-telco-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 Telco 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-telco-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
    • For instance the internet speed result is a random number between 50 and 150 Mbps, in the example below it is 53 Mbps and you run the bot it will definitely be different.

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

Example 1: happy path with solving "internet slow" issue

- Bot: Hey Serena 👋 I am your virtual AI assistant that can check your bills or resolve issues with Internet speed. How may I help you?
- User: My internet is slow
- Bot:
      I see.
      Let me try identify the root cause of the issue you are facing.
      I will run a network diagnostics for you 🛜
      Wait a moment please...
      Thank you for waiting... ✅
      Your network download speed is 53 Mbps.
      That's definitely not good.
      Let's reboot your router. It helps resolving most issues with speed. Please turn the router off, wait 10 seconds and turn it back on. Let me know when you are done!
- User: Done
- Bot:
      I will run a network diagnostics for you 🛜
      Wait a moment please...
      Thank you for waiting... ✅
      111 Mbps, Awesome! 🚀
      If the Internet gets slow again, you can always reset the router.
      If that doesn't help, let me know, and we can try something else. 😊

Example 2: Providing human agent help when needed in the "billing" use case

- User: Can you explain my bill in detail?
- Bot:
      Alright. Could you please specify the month? 📅
- User: Feb
- Bot:
      Your bill for February 2025 is $55.00.
      The average of your past bills is $88.50.
      This bill is lower than your average by $33.50.
      Would you like to see the breakdown of the costs?
- User: Nope
- Bot: Did I manage to provide all the information you need?
- User: No
- Bot:
      Let me connect you to our human support managers. They will help you further!
      Please hold on while I connect you to our expert 📲

Advanced configurations

By default, the Telecom Starter Pack always starts the chat session with "Hey Serena .." as the end user. You can easily adjust this to showcase multiple user profiles by filling in the “customer_first_name” slot with an adequate user name through an API call to the right Database.

The Telecom Assistant includes three user profiles:

  • Serena Williams with 123 as a customer id
  • Lionel Messi with 124 as a customer id
  • Tom Cruise with 125 as a customer id
  • Beyoncé Knowles with 456 as a customer id

You can check in the csvs folder to find the information above plus the information about their expenses.

Each profile has its own expenses on Internet, Mobile and TV.

What’s next?

Congratulations on installing the Rasa CALM Starter Pack for Telecom! Stay tuned for more Starter Packs coming soon.

2016-2025 © Rasa.