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.
461 462 463 464 |
# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 461 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}
.
461 462 463 464 |
# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 461 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.
461 462 463 464 |
# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 461 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.
461 462 463 464 |
# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 461 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/*
.
461 462 463 464 |
# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 461 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.
461 462 463 464 |
# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 461 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.
461 462 463 464 |
# File 'proto_docs/google/cloud/aiplatform/v1/prediction_service.rb', line 461 class CountTokensRequest include ::Google::Protobuf::MessageExts extend ::Google::Protobuf::MessageExts::ClassMethods end |