Class ConversationModel (2.25.0)

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

Represents a conversation model.

This message has oneof_ fields (mutually exclusive fields). For each oneof, at most one member field can be set at the same time. Setting any member of the oneof automatically clears all other members.

.. _oneof:


name str
ConversationModel resource name. Format: projects/
display_name str
Required. The display name of the model. At most 64 bytes long.
create_time google.protobuf.timestamp_pb2.Timestamp
Output only. Creation time of this model.
datasets MutableSequence[]
Required. Datasets used to create model.
Output only. State of the model. A model can only serve prediction requests after it gets deployed.
language_code str
Language code for the conversation model. If not specified, the language is en-US. Language at ConversationModel should be set for all non en-us languages. This should be a BCP-47 __ language tag. Example: "en-US".
Metadata for article suggestion models. This field is a member of oneof_ model_metadata.
Metadata for smart reply models. This field is a member of oneof_ model_metadata.




Model type.

Values: MODEL_TYPE_UNSPECIFIED (0): ModelType unspecified. SMART_REPLY_DUAL_ENCODER_MODEL (2): ModelType smart reply dual encoder model. SMART_REPLY_BERT_MODEL (6): ModelType smart reply bert model.



State of the model.

Values: STATE_UNSPECIFIED (0): Should not be used, an un-set enum has this value by default. CREATING (1): Model being created. UNDEPLOYED (2): Model is not deployed but ready to deploy. DEPLOYING (3): Model is deploying. DEPLOYED (4): Model is deployed and ready to use. UNDEPLOYING (5): Model is undeploying. DELETING (6): Model is deleting. FAILED (7): Model is in error state. Not ready to deploy and use. PENDING (8): Model is being created but the training has not started, The model may remain in this state until there is enough capacity to start training.