Class: Google::Cloud::AIPlatform::V1::CountTokensRequest
- Inherits:
-
Object
- Object
- Google::Cloud::AIPlatform::V1::CountTokensRequest
- Extended by:
- Protobuf::MessageExts::ClassMethods
- Includes:
- Protobuf::MessageExts
- Defined in:
- proto_docs/google/cloud/aiplatform/v1/prediction_service.rb
Overview
Request message for [PredictionService.CountTokens][].
Instance Attribute Summary collapse
-
#contents ⇒ ::Array<::Google::Cloud::AIPlatform::V1::Content>
Optional.
-
#endpoint ⇒ ::String
Required.
-
#generation_config ⇒ ::Google::Cloud::AIPlatform::V1::GenerationConfig
Optional.
-
#instances ⇒ ::Array<::Google::Protobuf::Value>
Optional.
-
#model ⇒ ::String
Optional.
-
#system_instruction ⇒ ::Google::Cloud::AIPlatform::V1::Content
Optional.
-
#tools ⇒ ::Array<::Google::Cloud::AIPlatform::V1::Tool>
Optional.
Instance Attribute Details
#contents ⇒ ::Array<::Google::Cloud::AIPlatform::V1::Content>
Returns Optional. Input content.
474 475 476 477 |
# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 474 class CountTokensRequest include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#endpoint ⇒ ::String
Returns Required. The name of the Endpoint requested to perform token counting.
Format:
projects/{project}/locations/{location}/endpoints/{endpoint}.
474 475 476 477 |
# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 474 class CountTokensRequest include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#generation_config ⇒ ::Google::Cloud::AIPlatform::V1::GenerationConfig
Returns Optional. Generation config that the model will use to generate the response.
474 475 476 477 |
# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 474 class CountTokensRequest include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#instances ⇒ ::Array<::Google::Protobuf::Value>
Returns Optional. The instances that are the input to token counting call. Schema is identical to the prediction schema of the underlying model.
474 475 476 477 |
# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 474 class CountTokensRequest include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#model ⇒ ::String
Returns Optional. The name of the publisher model requested to serve the
prediction. Format:
projects/{project}/locations/{location}/publishers/*/models/*.
474 475 476 477 |
# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 474 class CountTokensRequest include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#system_instruction ⇒ ::Google::Cloud::AIPlatform::V1::Content
Returns Optional. The user provided system instructions for the model. Note: only text should be used in parts and content in each part will be in a separate paragraph.
474 475 476 477 |
# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 474 class CountTokensRequest include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |
#tools ⇒ ::Array<::Google::Cloud::AIPlatform::V1::Tool>
Returns Optional. A list of Tools the model may use to generate the next
response.
A Tool is a piece of code that enables the system to interact with
external systems to perform an action, or set of actions, outside of
knowledge and scope of the model.
474 475 476 477 |
# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 474 class CountTokensRequest include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |