Version: Latest
Adding Environment Variables
Rasa offers advanced configuration through environment variables. Find the full reference here.
To add extra environment variables to your containers, add the
environment variable to an extraEnvs array on the service in your values.yml. These
values can be provided directly or refer to secrets.
The extraEnvs parameter is available for all services.
For example:
# rasa: Settings common for all Rasa containers
rasa:
# other configured parameters
# ...
extraEnvs:
- name: "LOG_LEVEL"
value: "warning"
Rasa Pro
When running Rasa Pro, the RASA_PRO_LICENSE environment variable needs to contain
the Rasa Pro license key.
Backing services
| Environment Variable | Description | Default |
|---|---|---|
POSTGRESQL_SCHEMA | The postgres schema for the SQLTrackerStore. | "public" |
POSTGRESQL_POOL_SIZE | The limit of the number of open connections for the SQLTrackerStore. | 50 |
POSTGRESQL_MAX_OVERFLOW | The maximum overflow of pool size for the SQLTrackerStore. | 100 |
RABBITMQ_SSL_CLIENT_CERTIFICATE | The path to the SSL client certificate for the PikaEventBroker. | |
RABBITMQ_SSL_CLIENT_KEY | The path to the SSL client key for the PikaEventBroker. | |
RASA_ENVIRONMENT | The Rasa environment for the PikaEventBroker and the KafkaEventBroker. | |
SECRET_MANAGER | The type of secret manager. | "vault" |
TICKET_LOCK_LIFETIME | The lifetime of ticket locks, in seconds. It configures the lock store. | 60 |
VAULT_URL | The URl of the HashiCorp Vault. | |
VAULT_TOKEN | The token to authenticate to the HashiCorp Vault. | |
VAULT_NAMESPACE | The namespace of the HashiCorp Vault. | |
VAULT_RASA_SECRETS_PATH | The path to Rasa secrets in the HashiCorp Vault. | "rasa-secrets" |
VAULT_TRANSIT_MOUNT_POINT | The mount point of the HashiCorp Vault. |
Model Storage
Environment variables that configure model storage on cloud providers are described in the following sections:
Dialogue Management
| Environment Variable | Description | Default |
|---|---|---|
RASA_DUCKLING_HTTP_URL | The URL of the Duckling service powering the DucklingEntityExtractor. | |
MAX_NUMBER_OF_PREDICTIONS | The maximum of predictions after each user message for a NLU-based assistant. See Action Selection. | 10 |
MAX_NUMBER_OF_PREDICTIONS_CALM | The maximum of predictions after each user message for a CALM-based assistant. See Action Selection. | 1000 |
TF_GPU_MEMORY_ALLOC | GPU configuration for TensorFlow. See Configuring TensorFlow. | |
TF_INTER_OP_PARALLELISM_THREADS | The number of threads used for parallelism between independent operations in TensorFlow. See Configuring TensorFlow. | |
TF_INTRA_OP_PARALLELISM_THREADS | The number of threads used within an individual TensorFlow operation for parallelism. See Configuring TensorFlow. | |
TF_DETERMINISTIC_OPS | Configures TensorFlow ops to run deterministically. See Configuring TensorFlow. | false |
Observability
| Environment Variable | Description | Default |
|---|---|---|
LOG_LEVEL | The log level for Rasa and Rasa Pro. | "INFO" |
LOG_LEVEL_LIBRARIES | The log level for 3rd-party libraries. More info here. | "ERROR" |
LOG_LEVEL_KAFKA | The log level for kafka library. More info here. | "ERROR" |
LOG_LEVEL_RABBITMQ | The log level for rabbitmq library. More info here. | "ERROR" |
LOG_LEVEL_FAKER | The log level for faker library. More info here. | "ERROR" |
LOG_LEVEL_PRESIDIO | The log level for presidio library. More info here. | "ERROR" |
LOG_LEVEL_LLM | The log level for all LLM components. More info here. | "DEBUG" |
LOG_LEVEL_LLM_COMMAND_GENERATOR | The log level for LLMCommandGenerator prompt. More info here. | "DEBUG" |
LOG_LEVEL_LLM_ENTERPRISE_SEARCH | The log level for EnterpriseSearchPolicy prompt. More info here. | "DEBUG" |
LOG_LEVEL_LLM_INTENTLESS_POLICY | The log level for IntentlessPolicy prompt. More info here. | "DEBUG" |
LOG_LEVEL_LLM_REPHRASER | The log level for ContextualResponseRephraser prompt. More info here. | "DEBUG" |
RASA_TELEMETRY_ENABLED | Toggle telemetry reporting. More info here | true |
RASA_TELEMETRY_DEBUG | Toggle debug information for telemetry reporting. | false |
RASA_PRO_TELEMETRY_ENABLED | Toggle telemetry reporting. More info here | true |
RASA_PRO_TELEMETRY_DEBUG | Toggle debug information for telemetry reporting. | false |
TRACING_SERVICE_NAME | The top-level service name when sending traces. More info here | "rasa" |
Advanced configuration
| Environment Variable | Description | Default |
|---|---|---|
COMPRESS_ACTION_SERVER_REQUEST | Toggle compression of HTTP requests sent to the Action Server. | false |
RASA_MAX_CACHE_SIZE | The maximum size of the training cache, in MB. | 1000 |
RASA_CACHE_NAME | The filename of the training cache. | "cache.db" |
RASA_CACHE_DIRECTORY | The directory for the training cache. | ".rasa/cache/" |
RASA_SHELL_STREAM_READING_TIMEOUT_IN_SECONDS | The stream reading timeout for rasa shell, in seconds. | 10 |
SANIC_BACKLOG | The number of unaccepted connections that the HTTP server and NLG server will allow before refusing new connections. | 100 |
SANIC_WORKERS | The number of HTTP workers when enabling the HTTP server. | 1 |
READ_YAML_FILE_CACHE_MAXSIZE | The maximum size of the LRU (Least Recently Used) cache for reading and parsing YAML files. | 256 |
Rasa Pro Services
The Rasa Pro Services docker container supports configuration through several environment variables. The following table lists the available environment variables:
| Environment Variable | Description | Default |
|---|---|---|
RASA_PRO_LICENSE | Required. The license key for Rasa Pro Services. | |
KAFKA_BROKER_ADDRESS | Required. The address of the Kafka broker. | |
KAFKA_TOPIC | Required. The topic Rasa Pro publishes events to and Rasa Pro consumes from. | rasa_core_events |
LOGGING_LEVEL | Set the log level of the application. Valid levels are DEBUG, INFO, WARNING, ERROR, CRITICAL. (Available from 3.0.2) | INFO |
RASA_ANALYTICS_DB_URL | The URL of the data lake to store analytics data in. | |
KAFKA_SASL_MECHANISM | The SASL mechanism to use for authentication. Valid mechanisms are | PLAIN |
KAFKA_SASL_USERNAME | The username for SASL authentication. | |
KAFKA_SASL_PASSWORD | The password for SASL authentication. | |
KAFKA_SECURITY_PROTOCOL | The security protocol to use for communication with Kafka. Supported mechanisms are PLAINTEXT and SASL_PLAINTEXT. | PLAINTEXT |
KAFKA_SSL_CA_LOCATION | The filepath for SSL CA Certificate that will be used to connect with Kafka (Available from 3.1.0b1) |
Rasa Studio
These environment variables take precedence over the values in the global.yml file, that is created with rasa studio config.
| Environment Variable | Description | Default |
|---|---|---|
RASA_STUDIO_AUTH_SERVER_URL | URL of the Authentication Server. | |
RASA_STUDIO_CLI_STUDIO_URL | URL of the Studio Data Endpoint. | |
RASA_STUDIO_CLI_REALM_NAME_KEY | Name of the Keycloak realm which hold the data about client ID and client secret. | |
RASA_STUDIO_CLI_CLIENT_ID_KEY | Client ID used to authenticate rasa studio CLI tool with Keycloak |
Rasa SDK
The Rasa SDK docker container supports configuration through several environment variables. The following table lists the available environment variables:
| Environment Variable | Description | Default |
|---|---|---|
ACTION_SERVER_SANIC_WORKERS | The number of Sanic HTTP workers in the Action server. | 1 |
LOG_LEVEL_LIBRARIES | The log level of third-party libraries. See Log level configuration. | ERROR |