This is documentation for Rasa Documentation v2.x, which is no longer actively maintained.
For up-to-date documentation, see the latest version (3.x).

Version: 2.x

Jupyter Notebooks

This page contains the most important methods for using Rasa in a Jupyter notebook.

Running asynchronous Rasa code in Jupyter Notebooks requires an extra requirement, since Jupyter Notebooks already run on event loops. Install this requirement in the command line before launching jupyter:

pip3 install nest_asyncio

Then in the first cell of your notebook, include:

import nest_asyncio
print("Event loop ready.")

First, you need to create a project if you don't already have one. To do this, run this cell, which will create the test-project directory and make it your working directory:

from rasa.cli.scaffold import create_initial_project
import os
project = "test-project"
# move into project directory and show files

To train a model, you will have to tell the train function where to find the relevant files. To define variables that contain these paths, run:

config = "config.yml"
training_files = "data/"
domain = "domain.yml"
output = "models/"
print(config, training_files, domain, output)

Train a Model

Now we can train a model by passing in the paths to the rasa.train function. Note that the training files are passed as a list. When training has finished, rasa.train returns the path where the trained model has been saved.

import rasa
model_path = rasa.train(domain, config, [training_files], output)

Chat with your assistant

To start chatting to an assistant, call the chat function, passing in the path to your saved model. If you do not have custom actions you can set endpoints = None or omit it:

from rasa.jupyter import chat
endpoints = "endpoints.yml"
chat(model_path, endpoints)

Evaluate your model against test data

Rasa has a convenience function for getting your training data. Rasa's get_core_nlu_directories is a function which recursively finds all the stories and NLU data files in a directory and copies them into two temporary directories. The return values are the paths to these newly created directories.

import as data
nlu_data_directory = data.get_data_directories(training_files, data.is_nlu_file)
stories_directory = data.get_data_directories(training_files, data.is_story_file)
print(stories_directory, nlu_data_directory)

To test your model, call the test function, passing in the path to your saved model and directories containing the stories and nlu data to evaluate on.

rasa.test(model_path, stories_directory, nlu_data_directory)
print("Done testing.")

The results of the core evaluation will be written to a file called results. NLU errors will be reported to errors.json. Together, they contain information about the accuracy of your model's predictions and other metrics.

if os.path.isfile("errors.json"):
print("NLU Errors:")
print("No NLU errors.")
if os.path.isdir("results"):
print("Core Errors:")