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

3. If deploying your model in Docker Compose, add the service to your docker-compose.yml:

   postgres:
     image: postgres:latest

Parameters

• domain (default: None): Domain object associated with this tracker store
• dialect (default: sqlite): The dialect used to communicate with your SQL backend.
• url (default: None): URL of your SQL server
• port (default: None): Port of your SQL server
• db (default: rasa.db): The path to the database to be used
• username (default: None): The username which is used for authentication
• password (default: None): The password which is used for authentication
• event_broker (default: None): Event broker to publish events to
• login_db (default: None): Alternative database name to which initially connect, and create the database specified by db (PostgreSQL only)
• query (default: None): Dictionary of options to be passed to the dialect and/or the DBAPI upon connect

Officially Compatible Databases

• PostgreSQL
• Oracle > 11.0
• SQLite

Oracle Configuration
To use the SQLTrackerStore with Oracle, there are a few additional steps. First, create a database tracker in your Oracle database and create a user with access to it.

Parameters

• tablename (default: states): name of the DynamoDB table
• region (default: us-east-1): name of the region associated with the client

RedisTrackerStore

Description
RedisTrackerStore can be used to store the conversation history in Redis.

Configuration

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

   tracker_store:
       type: redis
       url: <url of the redis instance, e.g. localhost>
       port: 6379
       db: 0
       password: <password used for authentication>
       use_ssl: false
   

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

   rasa run -m models --endpoints endpoints.yml
   

Parameters

• url (default: localhost): The url of your redis instance
• port (default: 6379): The port which redis is running on
• db (default: 0): The number of your redis database
• password (default: None): Password used for authentication

MongoTrackerStore

Description
MongoTrackerStore can be used to store the conversation history in Mongo.

Configuration

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

   tracker_store:
       type: mongod
       url: mongodb://localhost:27017
       db: rasa
       username:
       password:
       auth_source: admin
   

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

   rasa run -m models --endpoints endpoints.yml
   

Parameters

• url (default: mongodb://localhost:27017): URL of your MongoDB
• db (default: rasa): Database name to use
• username (default: None): Username used for authentication

DynamoTrackerStore

Description
DynamoTrackerStore can be used to store the conversation history in DynamoDB.

Configuration

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

   tracker_store:
       type: dynamo
       tablename: <name of the table to create, e.g. rasa>
       region: <name of the region associated with the client>
   

Parameters

• tablename (default: states): Name of the DynamoDB table
• region (default: us-east-1): 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.

class CustomTrackerStore(TrackerStore):
    """Your custom tracker store implementation."""

Steps

1. Extend the TrackerStore base class. Ensure that your constructor provides a parameter url.
2. In your endpoints.yml, put 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 deploying in Docker Compose, you can either extend the Rasa image to include the module or mount the module as a volume.