Frequently Asked Questions

The best place to get your questions answered is the forum <> which has thousands of members. In many cases, you can find an answer there!

Here we’ve collected answers to a couple of the most common questions.

What languages does Rasa NLU support?

Rasa NLU can be used to understand any language that can be tokenized (on whitespace or using a custom tokenizer), but some backends are restricted to specific languages.

The supervised_embeddings pipeline can be used for any language because it trains custom word embeddings for your domain using the data you provide in the NLU training examples.

Other backends use pre-trained word vectors and are therefore restricted to languages which have pre-trained vectors available.

You can read more about the Rasa NLU supported languages in section_languages.

How many training examples do I need for NLU?

Unfortunately, the answer is it depends.

A good starting point is to have 10 examples for each intent and build up from there.

If you have intents that are easily confusable, you will need more training data. Accordingly, as you add more intents, you also want to add more training examples for each intent. If you quickly write 20-30 unique expressions for each intent, you should be good for the beginning.

The same holds true for entities. the number of training examples you will need depends on how closely related your different entity types are and how clearly entities are distinguishable from non-entities in your use case.

To assess your model’s performance, use the rasa test command.

Which version of Rasa am I running?

To find out which Rasa version you are running, you can execute

python -c "import rasa; print(rasa.__version__);"

If you are using a virtual environment to run your python code, make sure you are using the correct python to execute the above code.

Why am I getting an UndefinedMetricWarning?

The complete warning is: UndefinedMetricWarning: F-score is ill-defined and being set to 0.0 in labels with no predicted samples. The warning is a result of a lack of training data. During the training the dataset will be splitted multiple times, if there are to few training samples for any of the intents, the splitting might result in splits that do not contain any examples for this intent.

Hence, the solution is to add more training samples. As this is only a warning, training will still succeed, but the resulting models predictions might be weak on the intents where you are lacking training data.

I have an issue, can you help me?

We’d love to help you. If you are unsure if your issue is related to your setup, you should state your problem in the Rasa Community Forum. If you found an issue with the framework, please file a report on github issues including all the information needed to reproduce the problem.

Which Python Versions are Supported?

Rasa supports Python 3.5, 3.6, and 3.7. Rasa NLU also supported python 2.7 until version 0.14, and Rasa Core until 0.12. If there are any issues with a specific python version, please create an issue on github <>.