Command Line Interface

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.

Cheat Sheet

Command Effect
rasa init Creates a new project with example training data, actions, and config files.
rasa train Trains a model using your NLU data and stories, saves trained model in ./models.
rasa interactive Starts an interactive learning session to create new training data by chatting to your assistant.
rasa shell Loads your trained model and lets you talk to your assistant on the command line.
rasa run Starts a server with your trained model.
rasa run actions Starts an action server using the Rasa SDK.
rasa visualize Generates a visual representation of your stories.
rasa test Tests a trained Rasa model on any files starting with test_.
rasa test e2e Runs end-to-end testing fully integrated with the action server that serves as acceptance testing.
rasa data split nlu Performs a 80/20 split of your NLU training data.
rasa data split stories Do the same as rasa data split nlu, but for your stories data.
rasa data convert Converts training data between different formats.
rasa data migrate Migrates 2.0 domain to 3.0 format.
rasa data validate Checks the domain, NLU and conversation data for inconsistencies.
rasa export Exports conversations from a tracker store to an event broker.
rasa evaluate markers Extracts markers from an existing tracker store.
rasa marker upload Upload marker configurations to Analytics Data Pipeline
rasa license Display licensing information.
rasa -h Shows all available commands.
note

If you run into character encoding issues on Windows like: UnicodeEncodeError: 'charmap' codec can't encode character ... or the terminal is not displaying colored messages properly, prepend winpty to the command you would like to run. For example winpty rasa init instead of rasa init

Log Level

Rasa produces log messages at several different levels (eg. warning, info, error and so on). You can control which level of logs you would like to see with --verbose (same as -v) or --debug (same as -vv) as optional command line arguments. See each command below for more explanation on what these arguments mean.

In addition to CLI arguments, several environment variables allow you to control log output in a more granular way. With these environment variables, you can configure log levels for messages created by external libraries such as Matplotlib, Pika, and Kafka. These variables follow standard logging level in Python. Currently, following environment variables are supported:

  1. LOG_LEVEL_LIBRARIES: This is the general environment variable to configure log level for the main libraries Rasa uses. It covers Tensorflow, asyncio, APScheduler, SocketIO, Matplotlib, RabbitMQ, Kafka.
  2. LOG_LEVEL_MATPLOTLIB: This is the specialized environment variable to configure log level only for Matplotlib.
  3. LOG_LEVEL_RABBITMQ: This is the specialized environment variable to configure log level only for AMQP libraries, at the moment it handles log levels from aio_pika and aiormq.
  4. LOG_LEVEL_KAFKA: This is the specialized environment variable to configure log level only for kafka.
  5. LOG_LEVEL_PRESIDIO: This is the specialized environment variable to configure log level only for Presidio, at the moment it handles log levels from presidio_analyzer and presidio_anonymizer.
  6. LOG_LEVEL_FAKER: This is the specialized environment variable to configure log level only for Faker.

General configuration (LOG_LEVEL_LIBRARIES) has less priority than library level specific configuration (LOG_LEVEL_MATPLOTLIB, LOG_LEVEL_RABBITMQ etc); and CLI parameter sets the lowest level log messages which will be handled. This means variables can be used together with a predictable result. As an example:

LOG_LEVEL_LIBRARIES=ERROR LOG_LEVEL_MATPLOTLIB=WARNING LOG_LEVEL_KAFKA=DEBUG rasa shell --debug

The above command run will result in showing:

Note that CLI config sets the lowest level log messages to be handled, hence the following command will set the log level to INFO (due to --verbose) and no debug messages will be seen (library level configuration will not have any effect):

LOG_LEVEL_LIBRARIES=DEBUG LOG_LEVEL_MATPLOTLIB=DEBUG rasa shell --verbose

As an aside, CLI log level sets the level at the root logger (which has the important handler - coloredlogs handler); this means even if an environment variable sets a library logger to a lower level, the root logger will reject messages from that library. If not specified, the CLI log level is set to INFO.

Custom logging configuration

New in 3.4

The Rasa CLI now includes a new argument --logging-config-file which accepts a YAML file as value.

You can now configure any logging formatters or handlers in a separate YAML file. The logging config YAML file must follow the Python built-in dictionary schema, otherwise it will fail validation. You can pass this file as argument to the --logging-config-file CLI option and use it with any of the rasa commands.

rasa init

This command sets up a complete assistant for you with some example training data:

rasa init

It creates the following files:

.
├── actions
│   ├── __init__.py
│   └── actions.py
├── config.yml
├── credentials.yml
├── data
│   ├── nlu.yml
│   └── stories.yml
├── domain.yml
├── endpoints.yml
├── models
│   └── <timestamp>.tar.gz
└── tests
    └── test_stories.yml

It will ask you if you want to train an initial model using this data. If you answer no, the models directory will be empty.

Any of the default CLI commands will expect this project setup, so this is the best way to get started. You can run rasa train, rasa shell and rasa test without any additional configuration.

rasa train

The following command trains a Rasa model:

rasa train

If you have existing models in your directory (under models/ by default), only the parts of your model that have changed will be re-trained. For example, if you edit your NLU training data and nothing else, only the NLU part will be trained.

If you want to train an NLU or dialogue model individually, you can run rasa train nlu or rasa train core. If you provide training data only for one of these, rasa train will fall back to one of these commands by default.

rasa train will store the trained model in the directory defined by --out, models/ by default. The name of the model by default is <timestamp>.tar.gz. If you want to name your model differently, you can specify the name using the --fixed-model-name flag.

By default validation is run before training the model. If you want to skip validation, you can use the --skip-validation flag. If you want to fail on validation warnings, you can use the --fail-on-validation-warnings flag. The --validation-max-history is analogous to the --max-history argument of rasa data validate.

The following arguments can be used to configure the training process:

usage: rasa train [-h] [-v] [-vv] [--quiet]   
                  [--logging-config-file LOGGING_CONFIG_FILE]   
                  [--data DATA [DATA ...]] [-c CONFIG] [-d DOMAIN] [--out OUT]   
                  [--dry-run] [--skip-validation]   
                  [--fail-on-validation-warnings]   
                  [--validation-max-history VALIDATION_MAX_HISTORY]   
                  [--augmentation AUGMENTATION] [--debug-plots]   
                  [--num-threads NUM_THREADS]   
                  [--fixed-model-name FIXED_MODEL_NAME] [--persist-nlu-data]   
                  [--force] [--finetune [FINETUNE]]   
                  [--epoch-fraction EPOCH_FRACTION] [--endpoints ENDPOINTS]   
                  {core,nlu} ...

Positional arguments:

Optional arguments:

See the section on data augmentation for info on how data augmentation works and how to choose a value for the flag. Note that TEDPolicy is the only policy affected by data augmentation.

Incremental training

New in 2.2

This feature is experimental. We introduce experimental features to get feedback from our community, so we encourage you to try it out! However, the functionality might be changed or removed in the future. If you have feedback (positive or negative) please share it with us on the Rasa Forum.

In order to improve the performance of an assistant, it's helpful to practice CDD and add new training examples based on how your users have talked to your assistant. You can use rasa train --finetune to initialize the pipeline with an already trained model and further finetune it on the new training dataset that includes the additional training examples. This will help reduce the training time of the new model.

By default, the command picks up the latest model in the models/ directory. If you have a specific model which you want to improve, you may specify the path to this by running rasa train --finetune <path to model to finetune>. Finetuning a model usually requires fewer epochs to train machine learning components like DIETClassifier, ResponseSelector and TEDPolicy compared to training from scratch. Either use a model configuration for finetuning which defines fewer epochs than before or use the flag --epoch-fraction. --epoch-fraction will use a fraction of the epochs specified for each machine learning component in the model configuration file. For example, if DIETClassifier is configured to use 100 epochs, specifying --epoch-fraction 0.5 will only use 50 epochs for finetuning.

You can also finetune an NLU-only or dialogue management-only model by using rasa train nlu --finetune and rasa train core --finetune respectively.

To be able to fine tune a model, the following conditions must be met:

  1. The configuration supplied should be exactly the same as the configuration used to train the model which is being finetuned. The only parameter that you can change is epochs for the individual machine learning components and policies.
  2. The set of labels(intents, actions, entities and slots) for which the base model is trained should be exactly the same as the ones present in the training data used for finetuning. This means that you cannot add new intent, action, entity or slot labels to your training data during incremental training. You can still add new training examples for each of the existing labels. If you have added/removed labels in the training data, the pipeline needs to be trained from scratch.
  3. The model to be finetuned is trained with MINIMUM_COMPATIBLE_VERSION of the currently installed rasa version.

rasa interactive

You can start an interactive learning session by running:

rasa interactive

This will first train a model and then start an interactive shell session. You can then correct your assistants predictions as you talk to it. If UnexpecTEDIntentPolicy is included in the pipeline, action_unlikely_intent can be triggered at any conversation turn. Subsequently, the following message will be displayed:

The bot wants to run 'action_unlikely_intent' to indicate that the last user message was unexpected

At this point in the conversation. Check out UnexpecTEDIntentPolicy docs to learn more.

As the message states, this is an indication that you have explored a conversation path which is unexpected according to the current set of training stories and hence adding this path to training stories is recommended. Like other bot actions, you can choose to confirm or deny running this action.

If you provide a trained model using the --model argument, training is skipped and that model will be loaded instead.

During interactive learning, Rasa will plot the current conversation and a few similar conversations from the training data to help you keep track of where you are. You can view the visualization at http://localhost:5005/visualization.html as soon as the session has started. This diagram can take some time to generate. To skip the visualization, run rasa interactive --skip-visualization.

Add the assistant_id key introduced in 3.5

Running interactive learning with a pre-trained model whose metadata does not include the assistant_id will exit with an error. If this happens, add the required key with a unique identifier value in config.yml and re-run training.

The following arguments can be used to configure the interactive learning session:

usage: rasa interactive [-h] [-v] [-vv] [--quiet]   
                       [--logging-config-file LOGGING_CONFIG_FILE] [--e2e]   
                       [-p PORT] [-m MODEL] [--data DATA [DATA ...]]   
                       [--skip-visualization]       
                       [--conversation-id CONVERSATION_ID]   
                       [--endpoints ENDPOINTS] [-c CONFIG] [-d DOMAIN]   
                       [--out OUT] [--augmentation AUGMENTATION]   
                       [--debug-plots] [--finetune [FINETUNE]]   
                       [--epoch-fraction EPOCH_FRACTION] [--force]   
                       [--persist-nlu-data]   
                       {core} ... [model-as-positional-argument]

Positional arguments:

Options:

Train Arguments:

rasa shell

You can start a chat session by running:

rasa shell

By default, this will load up the latest trained model. You can specify a different model to be loaded by using the --model flag.

If you start the shell with an NLU-only model, rasa shell will output the intents and entities predicted for any message you enter.

If you have trained a combined Rasa model but only want to see what your model extracts as intents and entities from text, you can use the command rasa shell nlu.

To increase the logging level for debugging, run:

rasa shell --debug
note

In order to see the typical greetings and/or session start behavior you might see in an external channel, you will need to explicitly send /session_start as the first message. Otherwise, the session start behavior will begin as described in Session configuration.

The following arguments can be used to configure the command. Most arguments overlap with rasa run; see the following section for more info on those arguments.

Note that the --connector argument will always be set to cmdline when running rasa shell. This means all credentials in your credentials file will be ignored, and if you provide your own value for the --connector argument it will also be ignored.

usage: rasa shell [-h] [-v] [-vv] [--quiet]   
                   [--logging-config-file LOGGING_CONFIG_FILE]   
                   [--conversation-id CONVERSATION_ID] [-m MODEL]   
                   [--log-file LOG_FILE] [--use-syslog]   
                   [--syslog-address SYSLOG_ADDRESS]   
                   [--syslog-port SYSLOG_PORT]   
                   [--syslog-protocol SYSLOG_PROTOCOL] [--endpoints ENDPOINTS]
                   [-i INTERFACE] [-p PORT] [-t AUTH_TOKEN]   
                   [--cors [CORS ...]] [--enable-api]   
                   [--response-timeout RESPONSE_TIMEOUT]   
                   [--request-timeout REQUEST_TIMEOUT]
                   [--remote-storage REMOTE_STORAGE]   
                   [--ssl-certificate SSL_CERTIFICATE]   
                   [--ssl-keyfile SSL_KEYFILE]   
                   [--ssl-ca-file SSL_CA_FILE]   
                   [--ssl-password SSL_PASSWORD]   
                   [--credentials CREDENTIALS]   
                   [--connector CONNECTOR]   
                   [--jwt-secret JWT_SECRET]   
                   [--jwt-method JWT_METHOD]
                   [--jwt-private-key JWT_PRIVATE_KEY]
                   {nlu} ... [model-as-positional-argument]

Positional arguments:

Options:

Server Settings:

rasa run

To start a server running your trained model, run:

rasa run

By default the Rasa server uses HTTP for its communication. To secure the communication with SSL and run the server on HTTPS, you need to provide a valid certificate and the corresponding private key file. You can specify these files as part of the rasa run command. If you encrypted your keyfile with a password during creation, you need to add the --ssl-password as well.

rasa run --ssl-certificate myssl.crt --ssl-keyfile myssl.key --ssl-password mypassword

Rasa by default listens on each available network interface. You can limit this to a specific network interface using the -i command line option.

rasa run -i 192.168.69.150

Rasa will by default connect to all channels specified in your credentials file. To connect to a single channel and ignore all other channels in your credentials file, specify the name of the channel in the --connector argument.

rasa run --connector rest

The name of the channel should match the name you specify in your credentials file. For supported channels see the page about messaging and voice channels.

The following arguments can be used to configure your Rasa server:

usage: rasa run [-h] [-v] [-vv] [--quiet]   
                [--logging-config-file LOGGING_CONFIG_FILE]   
                [-m MODEL] [--log-file LOG_FILE]   
                [--use-syslog]   
                [--syslog-address SYSLOG_ADDRESS]   
                [--syslog-port SYSLOG_PORT]   
                [--syslog-protocol SYSLOG_PROTOCOL] [--endpoints ENDPOINTS]
                [-i INTERFACE] [-p PORT] [-t AUTH_TOKEN]   
                [--cors [CORS ...]]   
                [--enable-api]   
                [--response-timeout RESPONSE_TIMEOUT]   
                [--request-timeout REQUEST_TIMEOUT]
                [--remote-storage REMOTE_STORAGE]   
                [--ssl-certificate SSL_CERTIFICATE]   
                [--ssl-keyfile SSL_KEYFILE]   
                [--ssl-ca-file SSL_CA_FILE]   
                [--ssl-password SSL_PASSWORD]   
                [--credentials CREDENTIALS]   
                [--connector CONNECTOR]   
                [--jwt-secret JWT_SECRET]   
                [--jwt-method JWT_METHOD]   
                [--jwt-private-key JWT_PRIVATE_KEY]
                {actions} ... [model-as-positional-argument]

Positional arguments:

Options:

rasa visualize

To generate a graph of your stories in the browser, run:

rasa visualize

If your stories are located somewhere other than the default location data/, you can specify their location with the --stories flag.

The following arguments can be used to configure this command:

usage: rasa visualize [-h] [-v] [-vv] [--quiet]   
                     [--logging-config-file LOGGING_CONFIG_FILE]   
                     [-d DOMAIN] [-s STORIES]   
                     [--out OUT] [--max-history MAX_HISTORY]   
                     [-u NLU]

Options:

rasa test

To evaluate a model on your test data, run:

rasa test

This will test your latest trained model on any end-to-end stories you have defined in files with the test_ prefix. If you want to use a different model, you can specify it using the --model flag.

To evaluate the dialogue and NLU models separately, use the commands below:

rasa test core

and

rasa test nlu

You can find more details on specific arguments for each testing type in Evaluating an NLU Model and Evaluating a Dialogue Management Model.

The following arguments are available for rasa test:

usage: rasa test [-h] [-v] [-vv] [--quiet]   
                 [--logging-config-file LOGGING_CONFIG_FILE]   
                 [-m MODEL] [-s STORIES]   
                 [--max-stories MAX_STORIES]   
                 [--endpoints ENDPOINTS]   
                 [--fail-on-prediction-errors]   
                 [--url URL] [--evaluate-model-directory]   
                 [-u NLU] [-c CONFIG [CONFIG ...]]   
                 [-d DOMAIN] [--cross-validation]   
                 [-f FOLDS] [-r RUNS]   
                 [-p PERCENTAGES [PERCENTAGES ...]]   
                 [--no-plot] [--successes]   
                 [--no-errors] [--no-warnings]   
                 [--out OUT]

Positional arguments:

Options:

rasa test e2e

Rasa Pro Only

Rasa Pro License

You'll need a license to get started with Rasa Pro. Get it here

New in 3.5

You can now use end-to-end testing to test your assistant as a whole, including dialogue management and custom actions.

To run end-to-end testing on your trained model, run:

rasa test e2e

This will test your latest trained model on any end-to-end test cases you have. If you want to use a different model, you can specify it using the --model flag.

The following arguments are available for rasa test e2e:

usage: rasa test e2e [-h] [-v] [-vv] [--quiet]   
                      [--logging-config-file LOGGING_CONFIG_FILE]   
                      [--fail-fast] [-o]   
                      [--remote-storage REMOTE_STORAGE]   
                      [-m MODEL] [--endpoints ENDPOINTS]   
                      [path-to-test-cases]

Optional arguments:

rasa data split

To create a train-test split of your NLU training data, run:

rasa data split nlu

This will create a 80/20 split of train/test data by default. You can specify the training data, the fraction, and the output directory using the following arguments:

usage: rasa data split nlu [-h] [-v] [-vv] [--quiet]   
                           [--logging-config-file LOGGING_CONFIG_FILE]   
                           [-u NLU] [--training-fraction TRAINING_FRACTION]  
                           [--random-seed RANDOM_SEED] [--out OUT]

Options:

Python Logging Options: You can control level of log messages printed. In addition to these arguments, a more fine grained configuration can be achieved with environment variables. See online documentation for more info.

Please report your findings on any discrepancies or missing information that may seem relevant to your Rasa setup.