Financial Services Example Bot
This is an example chatbot demonstrating how to build AI assistants for financial services and banking with Rasa. It includes pre-built intents, actions, and stories for handling conversation flows like checking spending history and transferring money to another account.
pip install -r requirements.txt
To install development dependencies:
pip install -r requirements-dev.txt pre-commit install python -m spacy download en_core_web_md en python -m spacy link en_core_web_md en
With pre-commit installed, the
doctochooks will run on every
git commit. If any changes are made by the hooks, you will need to re-add changed files and re-commit your changes.
Run the bot
rasa train to train a model.
Then, to run, first set up your action server in one terminal window, listening on port 5056:
rasa run actions --port 5056
Note that port 5056 is used for the action server, to avoid a conflict when you also run the helpdesk bot as described below in the
In another window, run the duckling server (for entity extraction):
docker run -p 8000:8000 rasa/duckling
Then to talk to the bot, run:
rasa shell --debug
You can also try out your bot locally using Rasa X by running
Overview of the files
data/nlu/nlu.yml – contains NLU training data
data/nlu/rules.yml – contains rules training data
data/stories/stories*.yml – contains stories training data
actions.py – contains custom action/api code
domain.yml – the domain file, including bot response templates
config.yml – training configurations for the NLU pipeline and policy ensemble
Things you can ask the bot
The bot currently has five skills. You can ask it to:
- Transfer money to another person
- Check your earning or spending history (with a specific vendor or overall)
- Answer a question about transfer charges
- Pay a credit card bill
- Tell you your account balance
It also has a limited ability to switch skills mid-transaction and then return to the transaction at hand.
It recognises the following payment amounts (besides actual currency amounts):
It recognises the following vendors (for spending history):
You can change any of these by modifying
actions.py and the corresponding NLU data.
This bot includes a simple skill for handing off the conversation to another bot or a human. This demo relies on this fork of chatroom to work, however you could implement similar behaviour in another channel and then use that instead. See the chatroom README for more details on channel-side configuration.
Using the default set up, the handoff skill enables this kind of conversation with two bots:
Action Server Image
You will need to have docker installed in order to build the action server image. If you haven’t made any changes to the action code, you can also use the public image on Dockerhub instead of building it yourself.
See the Dockerfile for what is included in the action server image,
To build the image:
<div class="highlight highlight-source-shell position-relative overflow-auto" data-snippet-clipboard-copy-content="docker build . -t :”>
docker build . -t <name of your custom image>:<tag of your custom image>