Skip to content
Handling multiple intents using Rasa NLU Tensorflow pipeline
Branch: master
Clone or download
Latest commit 1393477 Aug 6, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data Updated stories Jun 21, 2018
models/current Updated stories Jun 21, 2018
README.md Updated README.md Aug 6, 2018
config.yml updated readme Jun 7, 2018
domain.yml
entrypoint.sh add train & run script Jun 24, 2018
load_nlu_model.py changed input Jun 9, 2018
requirements.txt

README.md

How to handle multiple intents per input using Rasa NLU TensorFlow pipeline

In release 0.12, Rasa introduced a new TensorFlow-based pipeline for NLU models. This repository contains the code for a tutorial on how to use this pipeline to handle multiple intents per input. You can find a step-by-step tutorial on how to use this code here. The result of this tutorial is a chatbot which can recommend the meetups to attend in Berlin. The example conversation is:

User: Hello
Bot: Hey, how can I help you?
User: I am new to Berlin and I would like to join some meetups. Any suggestions?
Bot: Rasa Bots Berlin meetup is definitely worth checking out! They are having an event today at Behrenstraße 42. Would you like to join?
User: Sure! Can you also tell me how can I get to the venue?
Bot: Great, just made an RSVP for you. 
Bot: The venue is close to the Berlin Friedrichstraße station, so the best option is to catch a U-Bahn U6.
User: Thanks a lot. Talk to you later.
Bot: Glad I could help!
Bot: Talk to you later! 

In order to keep the main focus on the usage of the new pipeline and to ensure that the tutorial is fully reproducible, we didn't use any custom actions or APIs here. Instead, we would like to encourage you to take this code, build things on top of it and keep us posted on how it goes!

Versions of the software used in this tutorial:

  • Python 3.6
  • Rasa NLU 0.12.3
  • Rasa Core 0.9.6

How to use this repository:

  1. Clone or download the repository and install Rasa NLU and Rasa Core:
pip install -r requirements.txt
  1. Follow a step-by-step tutorial here.
  2. At any time you can load the chatbot and test it on your local machine:
python -m rasa_core.run -d models/current/dialogue -u models/current/nlu_model

Useful resources:

You can’t perform that action at this time.