com.google.mlkit.genai.prompt

Kotlin |Java

Interfaces

`Caches`	Provides an interface to explicitly manage caches for `GenerativeModel`.
`GenerativeModel`	Provides an interface for performing content generation.

Classes

`CachedContext`	Represents an identifier of a cached context that can be used in inference.
`Candidate`	A piece of a response from the model.
`CountTokensResponse`	Data class holding token count information.
`CreateCachedContextRequest`	A request to create a cached context.
`CreateCachedContextRequest.Builder`	Builder for `CreateCachedContextRequest`.
`GenerateContentRequest`	A request to generate content.
`GenerateContentRequest.Builder`	Builder for `GenerateContentRequest`.
`GenerateContentResponse`	Represents a response from the model.
`GenerationConfig`	Configuration parameters to use for content generation.
`GenerationConfig.Builder`	Builder for `GenerationConfig`.
`ImagePart`	A data class representing an image part of a prompt.
`ModelConfig`	Specifies the desired model for content generation.
`ModelConfig.Builder`	Builder for `ModelConfig`.
`Part`	A sealed class representing a part of a multimodal prompt.
`PromptPrefix`	A data class representing a prompt prefix.
`TextPart`	A data class representing a text part of a prompt.

Objects

Generation

Entry class to get a GenerativeModel client.

Annotations

`Candidate.FinishReason`	The reason why this `Candidate` is returned.
`ModelPreference`	Defines the developer's preference to guide model selection, balancing characteristics like speed and capability.
`ModelReleaseStage`	Defines the release stage preference for model selection.

Top-level functions summary

`CreateCachedContextRequest`	`createCachedContextRequest(name: String, promptPrefix: PromptPrefix)` Helper method to construct a `CreateCachedContextRequest`.
`GenerateContentRequest`	`generateContentRequest(text: TextPart, init: GenerateContentRequest.Builder.() -> Unit)` Helper method to construct a `GenerateContentRequest` in a DSL-like manner.
`GenerateContentRequest`	`generateContentRequest(image: ImagePart, text: TextPart, init: GenerateContentRequest.Builder.() -> Unit)` Helper method to construct a `GenerateContentRequest` in a DSL-like manner.
`GenerationConfig`	`generationConfig(init: GenerationConfig.Builder.() -> Unit)` Helper method to construct a `GenerationConfig` in a DSL-like manner.
`ModelConfig`	`modelConfig(init: ModelConfig.Builder.() -> Unit)` Helper function for Kotlin DSL to build ModelConfig.

Top-level functions

createCachedContextRequest

fun createCachedContextRequest(name: String, promptPrefix: PromptPrefix): CreateCachedContextRequest

Helper method to construct a CreateCachedContextRequest.

Example Usage:

createCachedContextRequest("my_cache", PromptPrefix("Repeat 3 times: "))

generateContentRequest

fun generateContentRequest(text: TextPart, init: GenerateContentRequest.Builder.() -> Unit): GenerateContentRequest

Helper method to construct a GenerateContentRequest in a DSL-like manner.

Example Usage:

// Generation Request with text only:
generateContentRequest(TextPart("Hello World")) {
  temperature = 0.5f
  seed = 123
  topK = 10
  candidateCount = 5
  maxOutputTokens = 200
}

generateContentRequest

fun generateContentRequest(image: ImagePart, text: TextPart, init: GenerateContentRequest.Builder.() -> Unit): GenerateContentRequest

Helper method to construct a GenerateContentRequest in a DSL-like manner.

Example Usage:

// Generation Request with image and text:
generateContentRequest(ImagePart(bitmap), TextPart("Hello World")) {
  temperature = 0.5f
  seed = 123
  topK = 10
  candidateCount = 5
  maxOutputTokens = 200
}

generationConfig

fun generationConfig(init: GenerationConfig.Builder.() -> Unit): GenerationConfig

Helper method to construct a GenerationConfig in a DSL-like manner.

Example usage:

// Default generation config - uses ModelConfig.DEFAULT and a default background thread pool.
val config1 = generationConfig {}

// Customized model spec
val config2 = generationConfig {
  workerExecutor = myExecutor
  modelConfig = modelConfig {
    releaseStage = ModelReleaseStage.PREVIEW
    preference = ModelPreference.FAST
  }
}

// Using prebuilt default ModelConfig with a custom executor
val config3 = generationConfig {
  workerExecutor = myExecutor
  modelConfig = ModelConfig.DEFAULT
}

modelConfig

fun modelConfig(init: ModelConfig.Builder.() -> Unit): ModelConfig

Helper function for Kotlin DSL to build ModelConfig.