Some or all of the information on this page might not apply to Cloud de Confiance by S3NS. See Differences from Google Cloud for more details.

Google Cloud Ai Platform V1 Client - Class CountTokensRequest (1.22.0)

Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class CountTokensRequest.

Request message for PredictionService.CountTokens.

Generated from protobuf message google.cloud.aiplatform.v1.CountTokensRequest

Namespace

Google \ Cloud \ AIPlatform \ V1

Methods

__construct

Constructor.

Parameters
Name	Description
`data`	`array` Optional. Data for populating the Message object.
`↳ endpoint`	`string` Required. The name of the Endpoint requested to perform token counting. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`
`↳ model`	`string` Optional. The name of the publisher model requested to serve the prediction. Format: `projects/{project}/locations/{location}/publishers//models/`
`↳ instances`	`array<Google\Protobuf\Value>` Optional. The instances that are the input to token counting call. Schema is identical to the prediction schema of the underlying model.
`↳ contents`	`array<Content>` Optional. Input content.
`↳ system_instruction`	`Content` 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.
`↳ tools`	`array<Tool>` 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.
`↳ generation_config`	`GenerationConfig` Optional. Generation config that the model will use to generate the response.

getEndpoint

Required. The name of the Endpoint requested to perform token counting.

Format: projects/{project}/locations/{location}/endpoints/{endpoint}

Returns
Type	Description
`string`

setEndpoint

Required. The name of the Endpoint requested to perform token counting.

Format: projects/{project}/locations/{location}/endpoints/{endpoint}

Parameter
Name	Description
`var`	`string`

Returns
Type	Description
`$this`

getModel

Optional. The name of the publisher model requested to serve the prediction. Format: projects/{project}/locations/{location}/publishers/*/models/*

Returns
Type	Description
`string`

setModel

Optional. The name of the publisher model requested to serve the prediction. Format: projects/{project}/locations/{location}/publishers/*/models/*

Parameter
Name	Description
`var`	`string`

Returns
Type	Description
`$this`

getInstances

Optional. The instances that are the input to token counting call.

Schema is identical to the prediction schema of the underlying model.

Returns
Type	Description
`Google\Protobuf\Internal\RepeatedField`

setInstances

Optional. The instances that are the input to token counting call.

Schema is identical to the prediction schema of the underlying model.

Parameter
Name	Description
`var`	`array<Google\Protobuf\Value>`

Returns
Type	Description
`$this`

getContents

Optional. Input content.

Returns
Type	Description
`Google\Protobuf\Internal\RepeatedField`

setContents

Optional. Input content.

Parameter
Name	Description
`var`	`array<Content>`

Returns
Type	Description
`$this`

getSystemInstruction

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.

Returns
Type	Description
`Content\|null`

hasSystemInstruction

clearSystemInstruction

setSystemInstruction

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.

Parameter
Name	Description
`var`	`Content`

Returns
Type	Description
`$this`

getTools

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.

Returns
Type	Description
`Google\Protobuf\Internal\RepeatedField`

setTools

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.

Parameter
Name	Description
`var`	`array<Tool>`

Returns
Type	Description
`$this`

getGenerationConfig

Optional. Generation config that the model will use to generate the response.

Returns
Type	Description
`GenerationConfig\|null`

hasGenerationConfig

clearGenerationConfig

setGenerationConfig

Optional. Generation config that the model will use to generate the response.

Parameter
Name	Description
`var`	`GenerationConfig`

Returns
Type	Description
`$this`

static::build

Parameters
Name	Description
`endpoint`	`string` Required. The name of the Endpoint requested to perform token counting. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}` Please see LlmUtilityServiceClient::endpointName() for help formatting this field.
`instances`	`array<Google\Protobuf\Value>` Optional. The instances that are the input to token counting call. Schema is identical to the prediction schema of the underlying model.

Returns
Type	Description
`CountTokensRequest`