Tracker Stores

All conversations are stored within a tracker store. Rasa Open Source provides implementations for different store types out of the box. If you want to use another store, you can also build a custom tracker store by extending the TrackerStore class.

Contents

• InMemoryTrackerStore (default)
• SQLTrackerStore
• RedisTrackerStore
• MongoTrackerStore
• DynamoTrackerStore
• Custom Tracker Store

InMemoryTrackerStore (default)

Description

InMemoryTrackerStore is the default tracker store. It is used if no other tracker store is configured. It stores the conversation history in memory.

Note

As this store keeps all history in memory, the entire history is lost if you restart the Rasa server.

Configuration

To use the InMemoryTrackerStore no configuration is needed.

SQLTrackerStore

Description

SQLTrackerStore can be used to store the conversation history in an SQL database. Storing your trackers this way allows you to query the event database by sender_id, timestamp, action name, intent name and typename.

Configuration

To set up Rasa Open Source with SQL the following steps are required:

1. Add required configuration to your endpoints.yml:

tracker_store:
    type: SQL
    dialect: "postgresql"
    url: ""
    db: "rasa"
    username:  
    password:  
    query: 
      driver: my-driver

2. To start the Rasa server using your SQL backend, add the --endpoints flag:

rasa run -m models --endpoints endpoints.yml

Parameters

• domain: Domain object associated with this tracker store
• dialect: The dialect used to communicate with your SQL backend.
• url: URL of your SQL server
• port: Port of your SQL server
• db: The path to the database to be used
• username: The username which is used for authentication
• password: The password which is used for authentication
• event_broker: Event broker to publish events to
• query: Dictionary of options to be passed to the dialect and/or the DBAPI upon connect

RedisTrackerStore

Description

RedisTrackerStore can be used to store the conversation history in Redis. Redis is a fast in-memory key-value store which can optionally also persist data.

Configuration

1. Start your Redis instance
2. Add required configuration to your endpoints.yml:

tracker_store:
    type: redis
    url: <url>
    port: <port>
    db: <number>
    password: <password>
    use_ssl: <whether or not>

3. To start the Rasa server using your configured Redis instance, add the --endpoints flag:

rasa run -m models --endpoints endpoints.yml

Parameters

• url: The url of your redis instance
• port: The port which redis is running on
• db: The number of your redis database
• password: Password used for authentication
• record_exp: Record expiry in seconds
• use_ssl: whether or not to use SSL for transit encryption

MongoTrackerStore

Description

MongoTrackerStore can be used to store the conversation history in Mongo. MongoDB is a free and open-source cross-platform document-oriented NoSQL database.

Configuration

1. Start your MongoDB instance.
2. Add required configuration to your endpoints.yml

tracker_store:
    type: mongod
    url: <url>
    db: <name>
    username: <username>
    password: <password>
    auth_source: <dbname>

3. To start the Rasa server using your configured MongoDB instance, add the --endpoints flag:

rasa run -m models --endpoints endpoints.yml

Parameters

• url: URL of your MongoDB
• db: The database name which should be used
• username: The username which is used for authentication
• password: The password which is used for authentication
• auth_source: database name associated with the user’s credentials.
• collection: The collection name which is used to store the conversations

DynamoTrackerStore

Description

DynamoTrackerStore can be used to store the conversation history in DynamoDB. DynamoDB is a hosted NoSQL database offered by Amazon Web Services (AWS).

Configuration

1. Start your DynamoDB instance.
2. Add required configuration to your endpoints.yml:

tracker_store:
    type: dynamo
    tablename: <name>
    region: <name>

3. To start the Rasa server using your configured DynamoDB instance, add the --endpoints flag:

rasa run -m models --endpoints endpoints.yml

Parameters

• tablename: name of the DynamoDB table
• region: name of the region associated with the client

Custom Tracker Store

Description

If you require a tracker store which is not available out of the box, you can implement your own. This is done by extending the base class TrackerStore.

Steps

1. Extend the TrackerStore base class.
2. In your endpoints.yml put in the module path to your custom tracker store and the parameters you require:

tracker_store:
  type: path.to.your.module.Class
  url: localhost
  a_parameter: a value
  another_parameter: another value

3. If you are deploying in Docker Compose, you have options to add this store to Rasa Open Source:

• extending the Rasa image to include the module
• mounting the module as volume

Example Configuration

docker-compose.yml:

rasa:
  <existing service configuration>
  volumes:
    - ./path/to/your/module.py:/app/path/to/your/module.py
custom-tracker-store:
  image: custom-image:tag

endpoints.yml:

tracker_store:
  type: path.to.your.module.Class
  url: custom-tracker-store
  a_parameter: a value
  another_parameter: another value

👋 I can help you get started with Rasa and answer your technical questions.