notice

This is unreleased documentation for Rasa Documentation Main/Unreleased version.
For the latest released documentation, see the latest version (3.x).

Version: Main/Unreleased

Tracker Stores

Your assistant's conversations are stored within a tracker store. Rasa provides implementations for different store types out of the box, or you can create your own custom one.

InMemoryTrackerStore (default)

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

No configuration is needed to use the InMemoryTrackerStore.

SQLTrackerStore

You can use an SQLTrackerStore to store your assistant's conversation history in an SQL database.

Configuration

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

  1. Add required configuration to your endpoints.yml:

    endpoints.yml
    tracker_store:
    type: SQL
    dialect: "postgresql" # the dialect used to interact with the db
    url: "" # (optional) host of the sql db, e.g. "localhost"
    db: "rasa" # path to your db
    username: # username used for authentication
    password: # password used for authentication
    query: # optional dictionary to be added as a query string to the connection URL
    driver: my-driver
  2. To start the Rasa server using your SQL backend, add the --endpoints flag, e.g.:

    rasa run -m models --endpoints endpoints.yml
  3. If deploying your model in Docker Compose, add the service to your docker-compose.yml:

    docker-compose.yml
    postgres:
    image: postgres:latest

    To route requests to the new service, make sure that the url in your endpoints.yml references the service name:

    endpoints.yml
    tracker_store:
    type: SQL
    dialect: "postgresql" # the dialect used to interact with the db
    url: "postgres"
    db: "rasa" # path to your db
    username: # username used for authentication
    password: # password used for authentication
    query: # optional dictionary to be added as a query string to the connection URL
    driver: my-driver

Configuration Parameters

  • domain (default: None): Domain object associated with this tracker store

  • dialect (default: sqlite): The dialect used to communicate with your SQL backend. Consult the SQLAlchemy docs for available dialects.

  • 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

Compatible Databases

The following databases are officially compatible with the SQLTrackerStore:

  • PostgreSQL
  • Oracle > 11.0
  • SQLite

Configuring Oracle

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. Create a sequence in the database with the following command, where username is the user you created (read more about creating sequences in the Oracle Documentation):

CREATE SEQUENCE username.events_seq;

Next you have to extend the Rasa image to include the necessary drivers and clients. First download the Oracle Instant Client, rename it to oracle.rpm and store it in the directory from where you'll be building the docker image. Copy the following into a file called Dockerfile:

FROM rasa/rasa:3.7.0a1-full
# Switch to root user to install packages
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

Then build the docker image:

docker build . -t rasa-oracle:3.7.0a1-oracle-full

Now you can configure the tracker store in the endpoints.yml as described above, and start the container. The dialect parameter with this setup will be oracle+cx_oracle. Read more about Deploying a Rasa Assistant.

RedisTrackerStore

You can store your assistant's conversation history in Redis by using the RedisTrackerStore. Redis is a fast in-memory key-value store which can optionally also persist data.

Configuration

To set up Rasa with Redis the following steps are required:

  1. Start your Redis instance

  2. Add required configuration to your endpoints.yml:

    endpoints.yml
    tracker_store:
    type: redis
    url: <url of the redis instance, e.g. localhost>
    port: <port of your redis instance, usually 6379>
    key_prefix: <alphanumeric value to prepend to tracker store keys>
    db: <number of your database within redis, e.g. 0>
    password: <password used for authentication>
    use_ssl: <whether or not the communication is encrypted, default `false`>
    rasa run -m models --endpoints endpoints.yml
  3. If deploying your model in Docker Compose, add the service to your docker-compose.yml:

    docker-compose.yml
    redis:
    image: redis:latest

    To route requests to the new service, make sure that the url in your endpoints.yml references the service name:

    endpoints.yml
    tracker_store:
    type: redis
    url: <url of the redis instance, e.g. localhost>
    port: <port of your redis instance, usually 6379>
    db: <number of your database within redis, e.g. 0>
    key_prefix: <alphanumeric value to prepend to tracker store keys>
    password: <password used for authentication>
    use_ssl: <whether or not the communication is encrypted, default `false`>
  • 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

  • key_prefix (default: None): The prefix to prepend to tracker store keys. Must be alphanumeric

  • username (default: None): Username used for authentication

  • password (default: None): Password used for authentication (None equals no authentication)

  • record_exp (default: None): Record expiry in seconds

  • use_ssl (default: False): whether or not to use SSL for transit encryption

MongoTrackerStore

You can store your assistant's conversation history in MongoDB using the MongoTrackerStore. 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:

    endpoints.yml
    tracker_store:
    type: mongod
    url: <url to your mongo instance, e.g. mongodb://localhost:27017>
    db: <name of the db within your mongo instance, e.g. rasa>
    username: <username used for authentication>
    password: <password used for authentication>
    auth_source: <database name associated with the user's credentials>

    You can also add more advanced configurations (like enabling ssl) by appending a parameter to the url field, e.g. mongodb://localhost:27017/?ssl=true.

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

    rasa run -m models --endpoints endpoints.yml
  4. If deploying your model in Docker Compose, add the service to your docker-compose.yml:

    docker-compose.yml
    mongo:
    image: mongo
    environment:
    MONGO_INITDB_ROOT_USERNAME: rasa
    MONGO_INITDB_ROOT_PASSWORD: example
    mongo-express: # this service is a MongoDB UI, and is optional
    image: mongo-express
    ports:
    - 8081:8081
    environment:
    ME_CONFIG_MONGODB_ADMINUSERNAME: rasa
    ME_CONFIG_MONGODB_ADMINPASSWORD: example

    To route requests to this database, make sure to set the url in your endpoints.yml as the service name, and specify the user and password:

    endpoints.yml
    tracker_store:
    type: mongod
    url: mongodb://mongo:27017
    db: <name of the db within your mongo instance, e.g. rasa>
    username: <username used for authentication>
    password: <password used for authentication>
    auth_source: <database name associated with the user's credentials>

Configuration Parameters

  • url (default: mongodb://localhost:27017): URL of your MongoDB

  • db (default: rasa): The database name which should be used

  • username (default: 0): The username which is used for authentication

  • password (default: None): The password which is used for authentication

  • auth_source (default: admin): database name associated with the user's credentials.

  • collection (default: conversations): The collection name which is used to store the conversations

DynamoTrackerStore

You can store your assistant's conversation history in DynamoDB by using a DynamoTrackerStore. 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:

    endpoints.yml
    tracker_store:
    type: dynamo
    table_name: <name of the table to create, e.g. rasa>
    region: <name of the region associated with the client>
  3. To start the Rasa server using your configured DynamoDB instance, add the --endpoints flag, e.g.:

    rasa run -m models --endpoints endpoints.yml

Configuration Parameters

  • table_name (default: states): name of the DynamoDB table

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

Custom Tracker Store

If you need 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 and one of the provided mixin classes that implement the serialise_tracker method: SerializedTrackerAsText or SerializedTrackerAsDict.

To write a custom tracker store, extend the TrackerStore base class. Your constructor has to provide a parameter host. The constructor also needs to make a super call to the base class TrackerStore using domain and event_broker arguments:

super().__init__(domain, event_broker, **kwargs)

Your custom tracker store class must also implement the following three methods:

Configuration

Put the module path to your custom tracker store and the parameters you require in your endpoints.yml:

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

If you are deploying in Docker Compose, you have two options to add this store to Rasa: extending the Rasa image to include the module, or mounting the module as volume.

Make sure to add the corresponding service as well. For example, mounting it as a volume would look like so:

docker-compose.yml
rasa:
<existing rasa service configuration>
volumes:
- <existing volume mappings, if there are any>
- ./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

Fallback Tracker Store

In case the primary tracker store configured in endpoints.yml becomes unavailable, the rasa agent will issue an error message and fall back on the InMemoryTrackerStore implementation. A new dialogue session will be started for each turn, which will be saved separately in the InMemoryTrackerStore fallback.

As soon as the primary tracker store comes back up, it will replace the fallback tracker store and save the conversation from this point going forward. However, note that any previous states saved in the InMemoryTrackerStore fallback will be lost.

Using the same redis instance as lock-store and tracker store

You must not use the same Redis instance as both lock store and tracker store. If the Redis instance becomes unavailable, the conversation will hang because there is no fall back mechanism implemented for the lock store (as it is for the tracker store interfaces).