Rasa as open source alternative to Facebook’s Wit.ai - Migration Guide

You are viewing documentation for our open source project which is maintained by the community. If you want to get started building assistants with Rasa please check out our latest documentation here.

To get started with migrating your application from Wit.ai to Rasa:

Step 1: Export your Training Data from Wit.ai

Navigate to your app's setting page by clicking the Settings item in the Management section of the left navigation bar.
Scroll down to Export your data and hit the button Download .zip with your data.

This will download a file with a .zip extension. Unzip this file to create a folder.
The files you want from your download are located in the utterances directory.

Step 2: Create a Rasa Project

To create a Rasa project, run:

rasa init

This will create a directory called data.
Remove the files in this directory, and move the content of the utterances directory to data.

rm -rf data/
mv /path/to/utterances data/

Step 3: Train your NLU model

To train a model using your Wit data, run:

rasa train nlu

Step 4: Test your NLU model

Let's see how your NLU model will interpret some test messages.
To start a testing session, run:

rasa shell nlu

This will prompt your for input.
Type a test message and press 'Enter'.
The output of your NLU model will be printed to the screen.
You can keep entering messages and test as many as you like.
Press 'control + C' to quit.

Step 5: Start a Server with your NLU Model

To start a server with your NLU model, run:

rasa run nlu

This will start a server listening on port 5005.

To send a request to the server, run:

curl 'localhost:5005/model/parse?emulation_mode=wit' -d '{"text": "hello"}'

The emulation_mode parameter tells Rasa that you want your json response to have the same format as you would get from wit.ai.

You can also leave it out to get the result in the usual Rasa format.

Join the Rasa Community Forum and let us know how your migration went!