Class Agent (2.22.0)

Agent(mapping=None, *, ignore_unknown_fields=False, **kwargs)

A Dialogflow agent is a virtual agent that handles conversations with your end-users. It is a natural language understanding module that understands the nuances of human language. Dialogflow translates end-user text or audio during a conversation to structured data that your apps and services can understand. You design and build a Dialogflow agent to handle the types of conversations required for your system.

For more information about agents, see the Agent guide <>__.


parent str
Required. The project of this agent. Format: projects/ or projects/
display_name str
Required. The name of this agent.
default_language_code str
Required. The default language of the agent as a language tag. See `Language Support
supported_language_codes MutableSequence[str]
Optional. The list of all languages supported by this agent (except for the default_language_code).
time_zone str
Required. The time zone of this agent from the `time zone database
description str
Optional. The description of this agent. The maximum length is 500 characters. If exceeded, the request is rejected.
avatar_uri str
Optional. The URI of the agent's avatar. Avatars are used throughout the Dialogflow console and in the self-hosted `Web Demo
enable_logging bool
Optional. Determines whether this agent should log conversation queries.
Optional. Determines how intents are detected from user queries.
classification_threshold float
Optional. To filter out false positive results and still get variety in matched natural language inputs for your agent, you can tune the machine learning classification threshold. If the returned score value is less than the threshold value, then a fallback intent will be triggered or, if there are no fallback intents defined, no intent will be triggered. The score values range from 0.0 (completely uncertain) to 1.0 (completely certain). If set to 0.0, the default of 0.3 is used.
Optional. API version displayed in Dialogflow console. If not specified, V2 API is assumed. Clients are free to query different service endpoints for different API versions. However, bots connectors and webhook calls will follow the specified API version.
Optional. The agent tier. If not specified, TIER_STANDARD is assumed.




API version for the agent.

Values: API_VERSION_UNSPECIFIED (0): Not specified. API_VERSION_V1 (1): Legacy V1 API. API_VERSION_V2 (2): V2 API. API_VERSION_V2_BETA_1 (3): V2beta1 API.



Match mode determines how intents are detected from user queries.

Values: MATCH_MODE_UNSPECIFIED (0): Not specified. MATCH_MODE_HYBRID (1): Best for agents with a small number of examples in intents and/or wide use of templates syntax and composite entities. MATCH_MODE_ML_ONLY (2): Can be used for agents with a large number of examples in intents, especially the ones using @sys.any or very large custom entities.



Represents the agent tier.

Values: TIER_UNSPECIFIED (0): Not specified. This value should never be used. TIER_STANDARD (1): Trial Edition, previously known as Standard Edition. TIER_ENTERPRISE (2): Essentials Edition, previously known as Enterprise Essential Edition. TIER_ENTERPRISE_PLUS (3): Essentials Edition (same as TIER_ENTERPRISE), previously known as Enterprise Plus Edition.