Rasa Open Source

https://legacy-docs-oss.rasa.com/docs/rasa
Admin
Rasa Open Source is an open-source framework for building, deploying, and managing AI assistants and...
Tokens:613,328
Snippets:7,146
Trust Score:10
Update:3 months ago
Show doc for...
Tokens:
Raw
### Run Rasa Action Server with Rasa Installed

Source: https://legacy-docs-oss.rasa.com/docs/rasa/action-server/running-action-server

Use this command when Rasa is installed in your environment to start the action server.

```bash
rasa run actions
```

--------------------------------

### RabbitMQ Connection and Consumption Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/event-brokers

Demonstrates how to establish a RabbitMQ connection using credentials and start consuming messages from a specified queue. This is useful for processing incoming events.

```python
print("Received event {}".format(json.loads(body)))
if __name__ == "__main__":
# RabbitMQ credentials with username and password
credentials = pika.PlainCredentials("username", "password")
# Pika connection to the RabbitMQ host - typically 'rabbit' in a
# docker environment, or 'localhost' in a local environment
connection = pika.BlockingConnection(
    pika.ConnectionParameters("rabbit", credentials=credentials)
)
# start consumption of channel
channel = connection.channel()
channel.basic_consume(queue="rasa_events", on_message_callback=_callback, auto_ack=True)
channel.start_consuming()
```

--------------------------------

### Basic Intent Training Examples

Source: https://legacy-docs-oss.rasa.com/docs/rasa/training-data-format

List basic training examples for an intent, with one example per line.

```yaml
nlu:
- intent: greet
examples: |
- hey
- hi
- whats up
```

--------------------------------

### Install All Dependencies

Source: https://legacy-docs-oss.rasa.com/docs/rasa/installation/installing-rasa-open-source

Install Rasa Open Source with all optional dependencies included.

```bash
pip3 install 'rasa[full]'
```

--------------------------------

### Install Rasa from Source

Source: https://legacy-docs-oss.rasa.com/docs/rasa/installation/installing-rasa-open-source

Clone the Rasa repository and install it using Poetry for development versions.

```bash
curl -sSL https://install.python-poetry.org | python3 -
```

```bash
git clone https://github.com/RasaHQ/rasa.git
```

```bash
cd rasa
```

```bash
poetry install
```

--------------------------------

### Form Activation Intent Examples

Source: https://legacy-docs-oss.rasa.com/docs/rasa/business-logic

Add training examples for the intent that should activate the form. This snippet shows examples for the 'request_restaurant' intent.

```yaml
nlu:
- intent: request_restaurant
examples: |
- im looking for a restaurant
- can i get [swedish](cuisine) food in any area
- a restaurant that serves [caribbean](cuisine) food
- id like a restaurant
- im looking for a restaurant that serves [mediterranean](cuisine) food
- can i find a restaurant that serves [chinese](cuisine)
```

--------------------------------

### Example JSON Credentials File

Source: https://legacy-docs-oss.rasa.com/docs/rasa/deploy/deploy-rasa-plus

This is an example of the JSON credentials file you might receive for accessing a private registry.

```json
{
"type": "service_account",
"project_id": "rasa-platform",
"private_key_id": "somerandomcharacters",
"private_key": "-----BEGIN PRIVATE KEY-----\n\nPBTu1lAJDLo136ZGTdMKi+/TuRqrIMg/..................................................................................................................................\nsjAsuAH4Iz1XdfdenzGnyBZH\n-----END PRIVATE KEY-----",
"client_email": "company@rasa-platform.iam.gserviceaccount.com",
"client_id": "12345678910123",
"auth_uri": "https://accounts.google.com/o/oauth2/auth",
"token_uri": "https://accounts.google.com/o/oauth2/token",
"auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
"client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/company%40rasa-platform.iam.gserviceaccount.com"
}
```

--------------------------------

### Check Docker and Docker Compose Installation

Source: https://legacy-docs-oss.rasa.com/docs/rasa/docker/deploying-in-docker-compose

Verify if Docker and Docker Compose are installed on your system by checking their versions. If the command fails, Docker needs to be installed.

```bash
docker -v && docker-compose -v
# Docker version 18.09.2, build 6247962
# docker-compose version 1.23.2, build 1110ad01
```

--------------------------------

### Check Docker Installation

Source: https://legacy-docs-oss.rasa.com/docs/rasa/docker/building-in-docker

Run this command to verify if Docker is installed on your system. The output will display the installed Docker version.

```bash
docker -v
```

--------------------------------

### Session Started Event Handling

Source: https://legacy-docs-oss.rasa.com/docs/rasa/default-actions

This snippet shows how to construct a list of events for the start of a session, including fetching slots and appending an action_listen event.

```python
events = [SessionStarted()]
events.extend(self.fetch_slots(tracker))
events.append(ActionExecuted("action_listen"))
return events
```

--------------------------------

### Install MITIE Dependencies

Source: https://legacy-docs-oss.rasa.com/docs/rasa/installation/installing-rasa-open-source

Install the MITIE library and its dependencies for use with Rasa.

```bash
pip3 install git+https://github.com/mit-nlp/MITIE.git
```

```bash
pip3 install 'rasa[mitie]'
```

--------------------------------

### Install Rasa with Kafka support

Source: https://legacy-docs-oss.rasa.com/docs/rasa/changelog

To use the KafkaEventConsumer, install Rasa with the [kafka] extra dependency.

```bash
$ pip install rasa[kafka]
```

--------------------------------

### Install Pip Keyring Dependencies

Source: https://legacy-docs-oss.rasa.com/docs/rasa/installation/rasa-pro/installation

Installs necessary Python packages for Pip to authenticate with GCP Artifact Registry. Ensure keyring and its GCP backend are installed.

```bash
pip install keyring
pip install keyrings.google-artifactregistry-auth
```

--------------------------------

### Sort Intent Examples

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/nlu/training_data/training_data

Sort the intent examples first by intent name and then by response.

```python
| sorted_intent_examples() -> List[Message]
Sorts the intent examples by the name of the intent and then response
```

--------------------------------

### Form Filling Intent Examples

Source: https://legacy-docs-oss.rasa.com/docs/rasa/business-logic

Add training examples for intents used when filling slots within a form. This snippet includes examples for 'affirm', 'deny', and 'inform' intents, with entity annotation for 'cuisine'.

```yaml
nlu:
- intent: affirm
examples: |
- Yes
- yes, please
- yup
```

```yaml
nlu:
- intent: deny
examples: |
- no don't
- no
- no I don't want that
```

```yaml
nlu:
- intent: inform
examples: |
- [afghan](cuisine) food
- how bout [asian oriental](cuisine)
- what about [indian](cuisine) food
- uh how about [turkish](cuisine) type of food
- um [english](cuisine)
- im looking for [tuscan](cuisine) food
- id like [moroccan](cuisine) food
- for ten people
- 2 people
- for three people
- just one person
- book for seven people
- 2 please
- nine people
```

--------------------------------

### Check Rust Installation (Linux)

Source: https://legacy-docs-oss.rasa.com/docs/rasa/installation/installing-rasa-open-source

Verify the Rust compiler installation on Linux.

```bash
rustc --version
```

--------------------------------

### Example GET Request with If-None-Match Header

Source: https://legacy-docs-oss.rasa.com/docs/rasa/model-storage

This is an example of a GET request that Rasa Open Source sends to your model server. It includes the `If-None-Match` header with the model hash for caching purposes.

```bash
curl --header "If-None-Match: d41d8cd98f00b204e9800998ecf8427e" http://my-server.com/models/default
```

--------------------------------

### Install Rasa with spaCy

Source: https://legacy-docs-oss.rasa.com/docs/rasa/installation/installing-rasa-open-source

Install Rasa Open Source along with spaCy and its English language model.

```bash
pip3 install 'rasa[spacy]'
```

```bash
python3 -m spacy download en_core_web_md
```

--------------------------------

### Example of Handling Text Input

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/agent

Demonstrates how to load an agent and handle text input, showing the expected output format.

```python
>>> from rasa.core.agent import Agent
>>> agent = Agent.load("examples/moodbot/models")
>>> await agent.handle_text("hello")
[u'how can I help you?']
```

--------------------------------

### Duckling Entity Extractor Output Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/components

Example of entities extracted by the DucklingEntityExtractor, including start and end positions, entity type, value, confidence, and the extractor name.

```json
{
"entities": [{
"end": 53,
"entity": "time",
"start": 48,
"value": "2017-04-10T00:00:00.000+02:00",
"confidence": 1.0,
"extractor": "DucklingEntityExtractor"
}]
}
```

--------------------------------

### __init__

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/tracker_store

Initializes the AwaitableTrackerStore by wrapping an existing TrackerStore.

```APIDOC
## __init__

### Description
Create a `AwaitableTrackerStore`.

### Arguments
* `tracker_store` - the wrapped tracker store.
```

--------------------------------

### __init__

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/graph_components/providers/domain_provider

Creates a DomainProvider instance.

```APIDOC
def __init__(model_storage: ModelStorage,
resource: Resource,
domain: Optional[Domain] = None) -> None
```

--------------------------------

### MitieEntityExtractor Output Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/components

This is an example of the output format produced by the MitieEntityExtractor, showing extracted entities with their values, start and end positions, and the extractor name. Confidence scores are not provided.

```json
{
"entities": [{
"value": "New York City",
"start": 20,
"end": 33,
"confidence": null,
"entity": "city",
"extractor": "MitieEntityExtractor"
}]
}
```

--------------------------------

### Create a New Rasa Project

Source: https://legacy-docs-oss.rasa.com/docs/rasa/installation/installing-rasa-open-source

Initialize a new Rasa project after installation.

```bash
rasa init
```

--------------------------------

### SpacyEntityExtractor Output Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/components

This is an example of the output format from the SpacyEntityExtractor, detailing extracted entities with their values, start and end indices, and the source extractor. Confidence scores are always null for this extractor.

```json
{
"entities": [{
"value": "New York City",
"start": 20,
"end": 33,
"confidence": null,
"entity": "city",
"extractor": "SpacyEntityExtractor"
}]
}
```

--------------------------------

### ProjectProvider Initialization

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/graph_components/providers/project_provider

Initializes the ProjectProvider with a given configuration.

```python
__init__(config: Dict[Text, Any]) -> None:
    Initializes the ProjectProvider.
```

--------------------------------

### Story with a Conditional Checkpoint

Source: https://legacy-docs-oss.rasa.com/docs/rasa/training-data-format

This example demonstrates a story that starts with a checkpoint, which can be conditional on specific slots being set.

```yaml
stories:
- story: story_with_a_conditional_checkpoint
steps:
- checkpoint: greet_checkpoint
```

--------------------------------

### JWT Authentication with Models

Source: https://legacy-docs-oss.rasa.com/docs/rasa/http-api

Example of starting the Rasa server with JWT authentication and specifying a models directory.

```bash
rasa run \
-m models \
--enable-api \
--jwt-secret thisismysecret
```

--------------------------------

### start_visualization

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/training/interactive

Add routes to serve the conversation visualization files.

```APIDOC
## start_visualization

### Description
Add routes to serve the conversation visualization files.

### Method
def start_visualization(image_path: Text, port: int) -> None
```

--------------------------------

### JWT Based Authentication Setup

Source: https://legacy-docs-oss.rasa.com/docs/rasa/http-api

Configure JWT-based authentication by specifying a JWT secret when starting the Rasa server.

```bash
rasa run \
--enable-api \
--jwt-secret thisismysecret
```

--------------------------------

### Customizing action_session_start

Source: https://legacy-docs-oss.rasa.com/docs/rasa/default-actions

Override the default session start action to control which slots are carried over to a new session. This example carries over only 'name' and 'phone_number'.

```python
from typing import Any, Text, Dict, List
from rasa_sdk import Action, Tracker
from rasa_sdk.events import SlotSet, SessionStarted, ActionExecuted, EventType

class ActionSessionStart(Action):
    def name(self) -> Text:
        return "action_session_start"

    @staticmethod
    def fetch_slots(tracker: Tracker) -> List[EventType]:
        """Collect slots that contain the user's name and phone number."""
        slots = []
        for key in ("name", "phone_number"):
            value = tracker.get_slot(key)
            if value is not None:
                slots.append(SlotSet(key=key, value=value))
        return slots

    async def run(
        self,
        dispatcher,
        tracker: Tracker,
        domain: Dict[Text, Any],
    ) -> List[Dict[Text, Any]]:
        
```

--------------------------------

### Simple Pipeline for Training Order Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/tuning-your-model

A basic pipeline configuration used to illustrate the order of component calls during training.

```yaml
pipeline:
- name: "Component A"
- name: "Component B"
- name: "Last Component"
```

--------------------------------

### Extract and Sort Entities

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/shared/nlu/training_data/training_data

Extracts all entities from training examples and sorts them by entity type. Use this to get a structured overview of entities present in your data.

```python
def sorted_entities() -> List[Any]
```

--------------------------------

### Get Max Depth of OperatorMarker Tree

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/evaluation/marker_base

Retrieves the maximum depth of the marker tree starting from this OperatorMarker. This can be useful for understanding the complexity of nested markers.

```python
def max_depth() -> int
```

--------------------------------

### TrainingTrackerProvider.__init__

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/graph_components/providers/training_tracker_provider

Initializes the TrainingTrackerProvider with a configuration dictionary.

```APIDOC
## __init__

### Description
Creates provider from config.

### Method Signature
def __init__(config: Dict[Text, Any]) -> None
```

--------------------------------

### Marker Configuration Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/markers

A comprehensive example of a marker configuration file for a mood bot. It demonstrates various operators and event conditions, including slot setting and negation.

```yaml
marker_name_provided:
  description: "slot `name` was provided"
  slot_was_set: name
marker_mood_expressed:
  or:
  - intent: mood_unhappy
  - intent: mood_great
marker_cheer_up_failed:
  seq:
  - intent: mood_unhappy
  - action: utter_cheer_up
  - action: utter_did_that_help
  - intent: deny
marker_bot_not_challenged:
  description: "Example of a negated marker, it can be used to surface conversations without bot_challenge intent"
  never:
  - intent: bot_challenge
marker_cheer_up_attempted:
  at_least_once:
  - action: utter_cheer_up
marker_mood_expressed_and_name_not_provided:
  and:
  - or:
  - intent: mood_unhappy
  - intent: mood_great
  - not:
  - slot_was_set: name
```

--------------------------------

### Stories Connected by Checkpoints

Source: https://legacy-docs-oss.rasa.com/docs/rasa/training-data-format

This example shows two stories connected using a checkpoint. The first story ends with a checkpoint, and the second story starts with the same checkpoint.

```yaml
stories:
- story: story_with_a_checkpoint_1
steps:
- intent: greet
- action: utter_greet
- checkpoint: greet_checkpoint
- story: story_with_a_checkpoint_2
steps:
- checkpoint: greet_checkpoint
- intent: book_flight
- action: action_book_flight
```

--------------------------------

### Get Telemetry ID

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/telemetry

Retrieves the unique telemetry identifier for the Rasa Open Source installation. The identifier should ideally be a UUID. Returns the ID if configured correctly.

```python
def get_telemetry_id() -> Optional[Text]
Return the unique telemetry identifier for this Rasa Open Source install.
The identifier can be any string, but it should be a UUID.
**Returns** :
The identifier, if it is configured correctly.
```

--------------------------------

### Get Tracker for Conversation

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/processor

Retrieves the tracker for a specific conversation ID without adding session start events. Creates an empty tracker if the conversation is new.

```python
async def get_tracker(conversation_id: Text) -> DialogueStateTracker
```

--------------------------------

### Install Oracle Client and cx-Oracle

Source: https://legacy-docs-oss.rasa.com/docs/rasa/tracker-stores

This Dockerfile snippet shows how to install the Oracle Instant Client and the cx-Oracle Python library. It's used when you need to store conversation history in an Oracle database.

```dockerfile
USER root
RUN apt-get update -qq && apt-get install -y --no-install-recommends alien libaio1 && apt-get clean && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
# Copy in oracle instaclient
# https://www.oracle.com/database/technologies/instant-client/linux-x86-64-downloads.html
COPY oracle.rpm oracle.rpm
# Install the Python wrapper library for the Oracle drivers
RUN pip install cx-Oracle
# Install Oracle client libraries
RUN alien -i oracle.rpm
USER 1001
```

--------------------------------

### Get Entity Tag IDs

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/utils/tensorflow/model_data_utils

Generates a feature array containing the entity tag IDs for a given training example. This is crucial for sequence labeling tasks where entities need to be identified and tagged.

```python
def get_tag_ids(example: Message, tag_spec: "EntityTagSpec",
bilou_tagging: bool) -> "Features"
Creates a feature array containing the entity tag ids of the given example.
**Arguments** :
  * `example` - the message
  * `tag_spec` - entity tag spec
  * `bilou_tagging` - indicates whether BILOU tagging should be used or not


**Returns** :
A list of features.
```

--------------------------------

### __init__

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/nlu/featurizers/dense_featurizer/mitie_featurizer

Initializes a new instance of the MitieFeaturizer class.

```APIDOC
## __init__(config: Dict[Text, Any], execution_context: ExecutionContext)

### Parameters
* `config` (Dict[Text, Any]) - The configuration dictionary for the component.
* `execution_context` (ExecutionContext) - The execution context.
```

--------------------------------

### Add Events to Conversation Tracker

Source: https://legacy-docs-oss.rasa.com/docs/rasa/changelog

The endpoint PUT /conversations/<conversation_id>/tracker/events no longer adds session start events automatically. To replicate previous behavior, send a GET /conversations/<conversation_id>/tracker request before appending events.

```http
PUT /conversations/<conversation_id>/tracker/events
```

--------------------------------

### Combine NLU, Stories, and Rules in One YAML File

Source: https://legacy-docs-oss.rasa.com/docs/rasa/training-data-format

This example shows how to include NLU examples, stories, and rules within a single YAML file for training data. Ensure the 'version' key is specified.

```yaml
version: "3.1"
nlu:
- intent: greet
examples: |
- Hey
- Hi
- hey there [Sara](name)
- intent: faq/language
examples: |
- What language do you speak?
- Do you only handle english?
stories:
- story: greet and faq
steps:
- intent: greet
- action: utter_greet
- intent: faq
- action: utter_faq
rules:
- rule: Greet user
steps:
- intent: greet
- action: utter_greet
```

--------------------------------

### Install Rust Compiler (macOS)

Source: https://legacy-docs-oss.rasa.com/docs/rasa/installation/installing-rasa-open-source

Install Rustup and the Rust compiler on macOS to resolve potential installation issues.

```bash
brew install rustup
```

```bash
rustup-init
```

--------------------------------

### Install Rust Compiler (Linux)

Source: https://legacy-docs-oss.rasa.com/docs/rasa/installation/installing-rasa-open-source

Install Rust compiler and Cargo on Linux if you encounter issues with 'rasa[full]' installation.

```bash
apt install rustc && apt install cargo
```

--------------------------------

### Initialize AwaitableTrackerStore

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/tracker_store

Instantiate `AwaitableTrackerStore` by wrapping an existing `TrackerStore` object.

```python
def __init__(tracker_store: TrackerStore) -> None
```

--------------------------------

### Initialize MitieNLP Component

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/nlu/utils/_mitie_utils

Constructs a new language model from the MITIE framework. Use this to create an instance of the MitieNLP component.

```python
class MitieNLP(Component)
#### __init__#
Copy
| __init__(component_config: Optional[Dict[Text, Any]] = None, extractor: Optional["mitie.total_word_feature_extractor"] = None) -> None
Construct a new language model from the MITIE framework.
```

--------------------------------

### Intent Training Examples with Intent-Level Metadata

Source: https://legacy-docs-oss.rasa.com/docs/rasa/training-data-format

Apply metadata to all examples of an intent. This simplifies the data structure when the same metadata applies to all examples.

```yaml
nlu:
- intent: greet
metadata:
sentiment: neutral
examples:
- text: |
hi
- text: |
hey there!
```

--------------------------------

### Create KafkaProducer with Security Protocols

Source: https://legacy-docs-oss.rasa.com/docs/rasa/changelog

Example of creating a KafkaProducer, ensuring correct instantiation for PLAINTEXT and SASL_SSL security protocols.

```python
from rasa.shared.core.kafka_utils import KafkaProducer

KafkaProducer(security_protocol='PLAINTEXT')
KafkaProducer(security_protocol='SASL_SSL')
```

--------------------------------

### Example Marker Configuration

Source: https://legacy-docs-oss.rasa.com/docs/rasa/changelog

Demonstrates how to add descriptions to markers in Rasa configuration. This helps document the usage of each marker.

```yaml
marker_name_provided:
  description: “Name slot has been set”
  slot_was_set: name
marker_mood_expressed:
  description: “Unhappy or Great Mood was expressed”
  or:
  - intent: mood_unhappy
  - intent: mood_great
```

--------------------------------

### MarkerTrackerLoader.__init__

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/evaluation/marker_tracker_loader

Creates a MarkerTrackerLoader instance.

```APIDOC
def __init__(tracker_store: TrackerStore,
             strategy: str,
             count: int = None,
             seed: Any = None) -> None

    Creates a MarkerTrackerLoader.

    Arguments:
      tracker_store - The underlying tracker store to access.
      strategy - The strategy to use for selecting trackers, can be 'all', 'sample_n', or 'first_n'.
      count - Number of trackers to return, can only be None if strategy is 'all'.
      seed - Optional seed to set up random number generator, only useful if strategy is 'sample_n'.
```

--------------------------------

### Remove examples without a response

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/nlu/test

Filters out examples that do not have a response assigned from a list of response selection evaluation results. This is useful for focusing on examples where a response was actually selected.

```python
def remove_empty_response_examples(
 response_results: List[ResponseSelectionEvaluationResult]
) -> List[ResponseSelectionEvaluationResult]
```

--------------------------------

### Load Marker Configurations from Directory

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/evaluation/markers

Loads and appends multiple marker configurations from a directory tree. This allows for modular configuration management.

```python
| @classmethod
| from_directory(cls, path: Text) -> Dict
Loads and appends multiple configs from a directory tree.
```

--------------------------------

### Rasa JSON Training Data Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/shared/nlu/training_data/formats/rasa

Example structure of Rasa NLU training data in JSON format, including regex features, entity synonyms, and common examples with intents.

```json
{
  "rasa_nlu_data": {
    "regex_features": [
      {
        "name": "zipcode",
        "pattern": "[0-9]{5}"
      }
    ],
    "entity_synonyms": [
      {
        "value": "chinese",
        "synonyms": [
          "Chinese",
          "Chines",
          "chines"
        ]
      }
    ],
    "common_examples": [
      {
        "text": "hey",
        "intent": "greet",
        "regex_features": []
      },
      {
        "text": "howdy",
        "intent": "greet",
        "regex_features": []
      }
    ]
  }
}
```

--------------------------------

### create

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/graph_components/providers/domain_for_core_training_provider

Creates an instance of DomainForCoreTrainingProvider.

```APIDOC
## create

@classmethod
def create(
cls, config: Dict[Text, Any], model_storage: ModelStorage,
resource: Resource,
execution_context: ExecutionContext) -> DomainForCoreTrainingProvider

Creates component (see parent class for full docstring).
```

--------------------------------

### serve_application

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/run

Runs the Rasa API entrypoint.

```APIDOC
## serve_application

### Description
Run the API entrypoint for the Rasa server.

### Parameters
- **model_path** (Optional[Text]) - Path to the Rasa model.
- **channel** (Optional[Text]) - The input channel to use.
- **interface** (Optional[Text]) - The server interface to use. Defaults to constants.DEFAULT_SERVER_INTERFACE.
- **port** (int) - The port to run the server on. Defaults to constants.DEFAULT_SERVER_PORT.
- **credentials** (Optional[Text]) - Path to the credentials file.
- **cors** (Optional[Union[Text, List[Text]]]) - CORS configuration.
- **auth_token** (Optional[Text]) - Authentication token.
- **enable_api** (bool) - Whether to enable the Rasa API. Defaults to True.
- **response_timeout** (int) - Timeout for responses. Defaults to constants.DEFAULT_RESPONSE_TIMEOUT.
- **jwt_secret** (Optional[Text]) - JWT secret key.
- **jwt_private_key** (Optional[Text]) - JWT private key.
- **jwt_method** (Optional[Text]) - JWT authentication method.
- **endpoints** (Optional[AvailableEndpoints]) - Available endpoints configuration.
- **remote_storage** (Optional[Text]) - URL for remote model storage.
- **log_file** (Optional[Text]) - Path to the log file.
- **ssl_certificate** (Optional[Text]) - Path to the SSL certificate file.
- **ssl_keyfile** (Optional[Text]) - Path to the SSL key file.
- **ssl_ca_file** (Optional[Text]) - Path to the SSL CA certificate file.
- **ssl_password** (Optional[Text]) - Password for the SSL key file.
- **conversation_id** (Optional[Text]) - Default conversation ID. Defaults to a new UUID hex.
- **use_syslog** (Optional[bool]) - Whether to use syslog. Defaults to False.
- **syslog_address** (Optional[Text]) - Syslog server address.
- **syslog_port** (Optional[int]) - Syslog server port.
- **syslog_protocol** (Optional[Text]) - Syslog protocol.
- **request_timeout** (Optional[int]) - Request timeout in seconds.
- **server_listeners** (Optional[List[Tuple[Callable, Text]]]) - List of server listeners.
```

--------------------------------

### CRFEntityExtractor Output Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/components

This is an example of the output format for entities extracted by the CRFEntityExtractor.

```json
{
"entities": [{
"value": "New York City",
"start": 20,
"end": 33,
"entity": "city",
"confidence": 0.874,
"extractor": "CRFEntityExtractor"
}]
}
```

--------------------------------

### Run Actions and End-to-End Tests

Source: https://legacy-docs-oss.rasa.com/docs/rasa/testing-your-assistant

Start the action server and then run end-to-end tests, necessary when test cases involve custom actions.

```bash
rasa run actions && rasa test e2e
```

--------------------------------

### config.yml with Suggested Config applied

Source: https://legacy-docs-oss.rasa.com/docs/rasa/model-configuration

This example shows a `config.yml` file after the 'Suggested Config' feature has been applied. Uncomment and modify the suggested pipeline components or policies as needed. If a key remains commented out and unspecified, Rasa will suggest a default configuration during training.

```yaml
recipe: default.v1
assistant_id: example_bot
language: en
pipeline:
# # No configuration for the NLU pipeline was provided. The following default pipeline was used to train your model.
# # If you'd like to customize it, uncomment and adjust the pipeline.
# # See https://rasa.com/docs/rasa/tuning-your-model for more information.
# - name: WhitespaceTokenizer
# - name: RegexFeaturizer
# - name: LexicalSyntacticFeaturizer
# - name: CountVectorsFeaturizer
# - name: CountVectorsFeaturizer
# analyzer: char_wb
# min_ngram: 1
# max_ngram: 4
# - name: DIETClassifier
# epochs: 100
# - name: EntitySynonymMapper
# - name: ResponseSelector
# epochs: 100
# - name: FallbackClassifier
# threshold: 0.3
# ambiguity_threshold: 0.1
policies:
- name: MemoizationPolicy
- name: TEDPolicy
max_history: 5
epochs: 10
```

--------------------------------

### Dependency Incompatibility Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/changelog

Illustrates a common dependency conflict related to the 'multidict' package, highlighting version mismatches that can occur.

```text
sanic 20.9.1 has requirement multidict==5.0.0, but you'll have multidict 4.6.0 which is incompatible.
```

--------------------------------

### Install Python Development Packages on Ubuntu

Source: https://legacy-docs-oss.rasa.com/docs/rasa/installation/environment-set-up

Fetch and install the necessary Python development and pip packages using apt on Ubuntu systems. This is a prerequisite for setting up the Python environment.

```bash
sudo apt update
sudo apt install python3-dev python3-pip
```

--------------------------------

### __init__

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/policies/ted_policy

Initializes the TEDPolicy with the given configuration and resources.

```APIDOC
## __init__

def __init__(config: Dict[Text, Any],
model_storage: ModelStorage,
resource: Resource,
execution_context: ExecutionContext,
model: Optional[RasaModel] = None,
featurizer: Optional[TrackerFeaturizer] = None,
fake_features: Optional[Dict[Text, List[Features]]] = None,
entity_tag_specs: Optional[List[EntityTagSpec]]) -> None
Declares instance variables with default values.
```

--------------------------------

### KeywordIntentClassifier Output Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/components

Example output from the KeywordIntentClassifier, showing the predicted intent and its confidence.

```json
{
"intent": {"name": "greet", "confidence": 1.0}
}
```

--------------------------------

### Provide Component Configuration

Source: https://legacy-docs-oss.rasa.com/docs/rasa/graph-recipe

Pass configuration parameters to the component. This example sets the language to 'en' and disables persistence.

```yaml
config:
  language: en
  persist: false
```

--------------------------------

### Parse Training Example for Entities and Synonyms

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/nlu/training_data/entities_parser

Parses a training example to extract entities and synonyms, and converts the example into a plain text format. This function is a core part of processing NLU training data.

```python
parse_training_example(example: Text, intent: Optional[Text] = None) -> "Message"
```

--------------------------------

### Example Stories for `requested_slot`

Source: https://legacy-docs-oss.rasa.com/docs/rasa/forms

These stories demonstrate how to handle the `explain` intent differently based on the `requested_slot` when using forms.

```yaml
stories:
- story: explain cuisine slot
  steps:
  - intent: request_restaurant
  - action: restaurant_form
  - active_loop: restaurant
  - slot_was_set:
    - requested_slot: cuisine
  - intent: explain
  - action: utter_explain_cuisine
  - action: restaurant_form
  - active_loop: null
- story: explain num_people slot
  steps:
  - intent: request_restaurant
  - action: restaurant_form
  - active_loop: restaurant
  - slot_was_set:
    - requested_slot: cuisine
  - slot_was_set:
    - requested_slot: num_people
  - intent: explain
  - action: utter_explain_num_people
  - action: restaurant_form
  - active_loop: null
```

--------------------------------

### Incomplete Rule Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/policies

An example of an incomplete rule where a slot is expected to be set but is missing in the steps.

```yaml
rules:
- rule: complete rule
steps:
- intent: search_venues
- action: action_search_venues
- slot_was_set:
- venues: ["name": "Big Arena", "reviews": 4.5]
- rule: incomplete rule
steps:
- intent: search_venues
- action: action_search_venues
```

--------------------------------

### SlackInput __init__

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/channels/slack

Initializes the Slack input channel with necessary authentication and configuration settings.

```APIDOC
## __init__

### Description
Create a Slack input channel.
Needs a couple of settings to properly authenticate and validate messages.

### Arguments
* `slack_token` (Text) - Your Slack Authentication token.
* `slack_channel` (Optional[Text]) - The string identifier for a channel to which the bot posts, or channel name.
* `proxy` (Optional[Text]) - A Proxy Server to route your traffic through.
* `slack_retry_reason_header` (Optional[Text]) - Slack HTTP header name indicating reason that slack send retry request.
* `slack_retry_number_header` (Optional[Text]) - Slack HTTP header name indicating the attempt number.
* `errors_ignore_retry` (Optional[List[Text]]) - Any error codes given by Slack included in this list will be ignored.
* `use_threads` (Optional[bool]) - If set to `False`, your bot will send responses in Slack as a threaded message. Responses will appear as a normal Slack message if set to `True`.
* `slack_signing_secret` (Text) - Slack creates a unique string for your app and shares it with you. This allows us to verify requests from Slack with confidence by verifying signatures using your signing secret.
* `conversation_granularity` (Optional[Text]) - Conversation granularity for slack conversations. sender allows 1 conversation per user (across channels), channel allows 1 conversation per user per channel, thread allows 1 conversation per user per thread.

### Method
def __init__(slack_token: Text, slack_channel: Optional[Text] = None, proxy: Optional[Text] = None, slack_retry_reason_header: Optional[Text] = None, slack_retry_number_header: Optional[Text] = None, errors_ignore_retry: Optional[List[Text]] = None, use_threads: Optional[bool] = False, slack_signing_secret: Text = "", conversation_granularity: Optional[Text] = "sender") -> None
```

--------------------------------

### Start Conversation Visualization

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/training/interactive

Serves conversation visualization files from a specified image path and port. This is used to view conversation flows graphically.

```python
def start_visualization(image_path: Text, port: int) -> None
```

--------------------------------

### Load Marker Configuration from Path

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/evaluation/markers

Loads the marker configuration from a specified file or directory path. Ensures the configuration is correctly loaded for use.

```python
| @classmethod
| load_config_from_path(cls, path: Union[Text, Path]) -> Dict
Loads the config from a file or directory.
```

--------------------------------

### do_events_begin_with_session_start

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/shared/core/events

Determines if a list of events starts with a session start sequence (action_session_start followed by session_started).

```APIDOC
## do_events_begin_with_session_start

### Description
Determines whether `events` begins with a session start sequence.
A session start sequence is a sequence of two events: an executed `action_session_start` as well as a logged `session_started`.

### Arguments
* `events` - The events to inspect.

### Returns
Whether `events` begins with a session start sequence.

### Signature
```python
def do_events_begin_with_session_start(events: List["Event"]) -> bool
```
```

--------------------------------

### Count Examples Per Response

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/nlu/training_data/training_data

Calculate and return a dictionary mapping each response to the number of training examples it has.

```python
| @lazy_property
| number_of_examples_per_response() -> Dict[Text, int]
Calculates the number of examples per response.
```

--------------------------------

### Initialize PrecomputedValueProvider

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/engine/training/components

Initializes a `PrecomputedValueProvider` with a specified output.

```python
def __init__(output: Cacheable)
```

--------------------------------

### Initialize MitieNLP

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/nlu/utils/mitie_utils

Constructs a new language model from the MITIE framework. Requires the path to the model file and an optional feature extractor.

```python
def __init__(
path_to_model_file: Path,
extractor: Optional["mitie.total_word_feature_extractor"] = None
) -> None
```

--------------------------------

### Count Examples Per Intent

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/nlu/training_data/training_data

Calculate and return a dictionary mapping each intent to the number of training examples it has.

```python
| @lazy_property
| number_of_examples_per_intent() -> Dict[Text, int]
Calculates the number of examples per intent.
```

--------------------------------

### FallbackClassifier Output Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/components

An example of the output structure from the FallbackClassifier, including intent, intent ranking, and entities.

```json
{
"intent": {"name": "nlu_fallback", "confidence": 0.7183846840434321},
"intent_ranking": [
{
"confidence": 0.7183846840434321,
"name": "nlu_fallback"
},
{
"confidence": 0.28161531595656784,
"name": "restaurant_search"
}
],
"entities": [{
"end": 53,
"entity": "time",
"start": 48,
"value": "2017-04-10T00:00:00.000+02:00",
"confidence": 1.0,
"extractor": "DIETClassifier"
}]
}
```

--------------------------------

### DIETClassifier Output Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/components

Example output from the DIETClassifier, including intent, intent ranking, and extracted entities.

```json
{
"intent": {"name": "greet", "confidence": 0.7800},
"intent_ranking": [
{
"confidence": 0.7800,
"name": "greet"
},
{
"confidence": 0.1400,
"name": "goodbye"
},
{
"confidence": 0.0800,
"name": "restaurant_search"
}
],
"entities": [{
"end": 53,
"entity": "time",
"start": 48,
"value": "2017-04-10T00:00:00.000+02:00",
"confidence": 1.0,
"extractor": "DIETClassifier"
}]
}
```

--------------------------------

### Fetch Tracker with Token Auth

Source: https://legacy-docs-oss.rasa.com/docs/rasa/http-api

Example of how to fetch a conversation tracker from the server using token-based authentication.

```bash
curl -XGET localhost:5005/conversations/default/tracker?token=thisismysecret
```

--------------------------------

### MitieIntentClassifier Output Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/components

Example of the output format for the MitieIntentClassifier, showing the predicted intent and its confidence score.

```json
{
"intent": {"name": "greet", "confidence": 0.98343}
}
```

--------------------------------

### GCSPersistor.__init__

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/nlu/persistor

Initializes the GCSPersistor with a bucket name.

```APIDOC
## GCSPersistor.__init__

### Description
Initialise class with client and bucket.

### Signature
```python
def __init__(bucket_name: Text) -> None
```
```

--------------------------------

### Contradicting Rules Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/policies

An example illustrating two contradicting rules where the same intent leads to different actions.

```yaml
rules:
- rule: Chitchat
steps:
- intent: chitchat
- action: utter_chitchat
- rule: Greet instead of chitchat
steps:
- intent: chitchat
- action: utter_greet # `utter_greet` contradicts `utter_chitchat` from the rule above
```

--------------------------------

### RedisLockStore Initialization

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/lock_store

Initializes a Redis lock store. Configure connection details like host, port, database, and authentication. SSL and key prefix options are also available.

```python
def __init__(
host: Text = "localhost",
port: int = 6379,
db: int = 1,
username: Optional[Text] = None,
password: Optional[Text] = None,
use_ssl: bool = False,
ssl_certfile: Optional[Text] = None,
ssl_keyfile: Optional[Text] = None,
ssl_ca_certs: Optional[Text] = None,
key_prefix: Optional[Text] = None,
socket_timeout: float = DEFAULT_SOCKET_TIMEOUT_IN_SECONDS) -> None
```

--------------------------------

### Initialize BotFrameworkInput

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/channels/botframework

Create a Bot Framework input channel. Requires your Bot Framework's API ID and application secret.

```python
def __init__(app_id: Text, app_password: Text) -> None:
    """Create a Bot Framework input channel.

    **Arguments** :
      * `app_id` - Bot Framework's API id
      * `app_password` - Bot Framework application secret
    """
```

--------------------------------

### Redshift Example DB URL

Source: https://legacy-docs-oss.rasa.com/docs/rasa/monitoring/analytics/getting-started-with-analytics

An example of a Redshift DB URL format for the RASA_ANALYTICS_DB_URL environment variable.

```bash
redshift://awsuser:4324312adfaGQ@analytics.cp1yucixmagz.us-east-1.redshift.amazonaws.com:5439/analytics
```

--------------------------------

### MessageProcessor.__init__

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/processor

Initializes a MessageProcessor.

```APIDOC
def __init__(
model_path: Union[Text, Path],
tracker_store: rasa.core.tracker_store.TrackerStore,
lock_store: LockStore,
generator: NaturalLanguageGenerator,
action_endpoint: Optional[EndpointConfig] = None,
max_number_of_predictions: int = MAX_NUMBER_OF_PREDICTIONS,
on_circuit_break: Optional[LambdaType] = None,
http_interpreter: Optional[RasaNLUHttpInterpreter] = None) -> None

Initializes a `MessageProcessor`.
```

--------------------------------

### List Slot Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/domain

Example of a list slot mapping from an entity. Used for storing lists of values.

```yaml
slots:
  shopping_items:
    type: list
    mappings:
    - type: from_entity
      entity: shopping_item
```

--------------------------------

### ProjectProvider get_default_config Method

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/graph_components/providers/project_provider

Provides the default configuration for the ProjectProvider.

```python
@staticmethod
def get_default_config() -> Dict[Text, Any]:
    Default config for ProjectProvider.
```

--------------------------------

### Text Slot Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/domain

Example of a text slot mapping from an entity. Used for storing text values.

```yaml
slots:
  cuisine:
    type: text
    mappings:
    - type: from_entity
      entity: cuisine
```

--------------------------------

### Response Selector Output Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/components

This example shows the structure of the output when a response selector is configured with a specific retrieval intent ('faq'). It includes the predicted response details and a ranking of other potential responses.

```json
{
"response_selector": {
"faq": {
"response": {
"id": 1388783286124361986,
"confidence": 0.7,
"intent_response_key": "chitchat/ask_weather",
"responses": [
{
"text": "It's sunny in Berlin today",
"image": "https://i.imgur.com/nGF1K8f.jpg"
},
{
"text": "I think it's about to rain."
}
],
"utter_action": "utter_chitchat/ask_weather"
},
"ranking": [
{
"id": 1388783286124361986,
"confidence": 0.7,
"intent_response_key": "chitchat/ask_weather"
},
{
"id": 1388783286124361986,
"confidence": 0.3,
"intent_response_key": "chitchat/ask_name"
}
]
}
}
}
```

--------------------------------

### Start Rasa Shell

Source: https://legacy-docs-oss.rasa.com/docs/rasa/command-line-interface

Run this command to start a chat session with the latest trained Rasa model.

```bash
rasa shell
```

--------------------------------

### Initialize RasaNLUModelConfig

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/nlu/config

Create a new instance of RasaNLUModelConfig. Optionally, provide a dictionary to override default configuration values.

```python
__init__(configuration_values: Optional[Dict[Text, Any]] = None) -> None
```

--------------------------------

### Rasa Story Format Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/changelog

An example of a dialogue in the Rasa story format, demonstrating intents, entities, and actions.

```yaml
stories:
- story: collect restaurant booking info # name of the story - just for debugging
steps:
- intent: greet # user message with no entities
- action: utter_ask_howcanhelp # action that the bot should execute
- intent: inform # user message with entities
entities:
- location: "rome"
- price: "cheap"
- bot: On it # actual text that bot can output
- action: utter_ask_cuisine
- user: I would like [spanish](cuisine). # actual text that user input
- action: utter_ask_num_people
```

--------------------------------

### Run Rasa Server

Source: https://legacy-docs-oss.rasa.com/docs/rasa/migrate-from/microsoft-luis-to-rasa

Starts a server that listens on port 5005, making the trained NLU model available for requests.

```bash
rasa run
```

--------------------------------

### Verify Example Repetition in Intents

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/validator

Checks for duplicated examples across different intents in the NLU training data.

```python
def verify_example_repetition_in_intents(ignore_warnings: bool = True) -> bool
Checks if there is no duplicated example in different intents.
```

--------------------------------

### create

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/graph_components/providers/domain_provider

Creates a DomainProvider component using a configuration dictionary and other necessary resources.

```APIDOC
@classmethod
def create(cls, config: Dict[Text, Any], model_storage: ModelStorage,
resource: Resource,
execution_context: ExecutionContext) -> DomainProvider
```

--------------------------------

### RulePolicy Configuration Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/policies

Example configuration for the RulePolicy in config.yml, including fallback settings and rule contradiction checks.

```yaml
policies:
- name: "RulePolicy"
core_fallback_threshold: 0.3
core_fallback_action_name: action_default_fallback
enable_fallback_prediction: true
restrict_rules: true
check_for_contradictions: true
```

--------------------------------

### create

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/core/tracker_store

A static method to create a tracker store, potentially wrapping it with AwaitableTrackerStore.

```APIDOC
## create

### Description
Wrapper to call `create` method of primary tracker store.

### Arguments
* `obj` - The tracker store object, endpoint configuration, or None.
* `domain` - Optional domain object.
* `event_broker` - Optional event broker object.

### Returns
* `TrackerStore` - The created tracker store.
```

--------------------------------

### Basic Story for UnexpecTEDIntentPolicy Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/policies

A simple training story used to illustrate how negative examples are generated for the UnexpecTEDIntentPolicy.

```yaml
version: 2.0
stories:
- story: happy path 1
steps:
- intent: greet
- action: utter_greet
- intent: mood_great
- action: utter_goodbye
```

--------------------------------

### Any Slot Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/domain

Example of an 'any' slot type. Used for storing arbitrary values like dictionaries or lists.

```yaml
slots:
  shopping_items:
    type: any
    mappings:
    - type: custom
```

--------------------------------

### load

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/nlu/config

Creates an NLU configuration object from a file path or a dictionary. If no configuration is provided, it loads from the default file path.

```APIDOC
## load

### Description
Create configuration from file or dict.

### Arguments
* `config` - a file path, a dictionary with configuration keys. If set to `None` the configuration will be loaded from the default file path.

### Returns
Configuration object.
```

--------------------------------

### DotProductLoss.__init__

Source: https://legacy-docs-oss.rasa.com/docs/rasa/reference/rasa/utils/tensorflow/layers

Initializes the DotProductLoss layer with configuration parameters for similarity calculation and loss scaling.

```APIDOC
## __init__(num_candidates: int, scale_loss: bool = False, constrain_similarities: bool = True, model_confidence: Text = SOFTMAX, similarity_type: Text = INNER, name: Optional[Text] = None, **kwargs: Any)

Declares instance variables with default values.
**Arguments** :
  * `num_candidates` - Number of labels besides the positive one. Depending on whether single- or multi-label loss is implemented (done in sub-classes), these can be all negative example labels, or a mixture of negative and further positive labels, respectively.
  * `scale_loss` - Boolean, if `True` scale loss inverse proportionally to the confidence of the correct prediction.
  * `constrain_similarities` - Boolean, if `True` applies sigmoid on all similarity terms and adds to the loss function to ensure that similarity values are approximately bounded. Used inside _loss_cross_entropy() only.
  * `model_confidence` - Normalization of confidence values during inference. Currently, the only possible value is `SOFTMAX`.
  * `similarity_type` - Similarity measure to use, either `cosine` or `inner`.
  * `scale_loss`0 - Optional name of the layer.

**Raises** :
  * `scale_loss`1 - When `similarity_type` is not one of `scale_loss`3 or `scale_loss`4.
```

--------------------------------

### Boolean Slot Example

Source: https://legacy-docs-oss.rasa.com/docs/rasa/domain

Example of a boolean slot with a custom mapping. Used for storing true or false values.

```yaml
slots:
  is_authenticated:
    type: bool
    mappings:
    - type: custom
```
Tokens:
Raw