GenerativeModel

class GenerativeModel

A controller for communicating with the API of a given multimodal model (for example, Gemini).

Summary

Public functions
`suspend CountTokensResponse`	`countTokens(prompt: Bitmap)` Counts the amount of tokens in the image prompt.
`suspend CountTokensResponse`	`countTokens(vararg prompt: Content)` Counts the amount of tokens in a prompt.
`suspend CountTokensResponse`	`countTokens(prompt: String)` Counts the amount of tokens in the text prompt.
`suspend GenerateContentResponse`	`generateContent(prompt: Bitmap)` Generates a `GenerateContentResponse` from the backend with the provided image prompt.
`suspend GenerateContentResponse`	`generateContent(vararg prompt: Content)` Generates a `GenerateContentResponse` from the backend with the provided `Content`.
`suspend GenerateContentResponse`	`generateContent(prompt: String)` Generates a `GenerateContentResponse` from the backend with the provided text prompt.
`Flow<GenerateContentResponse>`	`generateContentStream(prompt: Bitmap)` Generates a streaming response from the backend with the provided image prompt.
`Flow<GenerateContentResponse>`	`generateContentStream(vararg prompt: Content)` Generates a streaming response from the backend with the provided `Content`.
`Flow<GenerateContentResponse>`	`generateContentStream(prompt: String)` Generates a streaming response from the backend with the provided text prompt.
`Chat`	`startChat(history: List<Content>)` Creates a `Chat` instance which internally tracks the ongoing conversation with the model

Public properties
`GenerationConfig?`	`generationConfig`
`String`	`modelName`
`List<SafetySetting>?`	`safetySettings`
`Content?`	`systemInstruction`
`ToolConfig?`	`toolConfig`
`List<Tool>?`	`tools`

Public functions

countTokens

suspend fun countTokens(prompt: Bitmap): CountTokensResponse

Counts the amount of tokens in the image prompt.

Parameters
`prompt: Bitmap`	The image to be converted to a single piece of `Content` to count the tokens of.

Returns
`CountTokensResponse`	A `CountTokensResponse` containing the amount of tokens in the prompt.

countTokens

suspend fun countTokens(vararg prompt: Content): CountTokensResponse

Counts the amount of tokens in a prompt.

Parameters
`vararg prompt: Content`	A group of `Content` to count tokens of.

Returns
`CountTokensResponse`	A `CountTokensResponse` containing the amount of tokens in the prompt.

countTokens

suspend fun countTokens(prompt: String): CountTokensResponse

Counts the amount of tokens in the text prompt.

Parameters
`prompt: String`	The text to be converted to a single piece of `Content` to count the tokens of.

Returns
`CountTokensResponse`	A `CountTokensResponse` containing the amount of tokens in the prompt.

generateContent

suspend fun generateContent(prompt: Bitmap): GenerateContentResponse

Generates a GenerateContentResponse from the backend with the provided image prompt.

Parameters
`prompt: Bitmap`	The image to be converted into a single piece of `Content` to send to the model.

Returns
`GenerateContentResponse`	A `GenerateContentResponse` after some delay. Function should be called within a suspend context to properly manage concurrency.

generateContent

suspend fun generateContent(vararg prompt: Content): GenerateContentResponse

Generates a GenerateContentResponse from the backend with the provided Content.

Parameters
`vararg prompt: Content`	`Content` to send to the model.

Returns
`GenerateContentResponse`	A `GenerateContentResponse`. Function should be called within a suspend context to properly manage concurrency.

generateContent

suspend fun generateContent(prompt: String): GenerateContentResponse

Generates a GenerateContentResponse from the backend with the provided text prompt.

Parameters
`prompt: String`	The text to be converted into a single piece of `Content` to send to the model.

Returns
`GenerateContentResponse`	A `GenerateContentResponse` after some delay. Function should be called within a suspend context to properly manage concurrency.

generateContentStream

fun generateContentStream(prompt: Bitmap): Flow<GenerateContentResponse>

Generates a streaming response from the backend with the provided image prompt.

Parameters
`prompt: Bitmap`	The image to be converted into a single piece of `Content` to send to the model.

Returns
`Flow<GenerateContentResponse>`	A `Flow` which will emit responses as they are returned from the model.

generateContentStream

fun generateContentStream(vararg prompt: Content): Flow<GenerateContentResponse>

Generates a streaming response from the backend with the provided Content.

Parameters
`vararg prompt: Content`	`Content` to send to the model.

Returns
`Flow<GenerateContentResponse>`	A `Flow` which will emit responses as they are returned from the model.

generateContentStream

fun generateContentStream(prompt: String): Flow<GenerateContentResponse>

Generates a streaming response from the backend with the provided text prompt.

Parameters
`prompt: String`	The text to be converted into a single piece of `Content` to send to the model.

Returns
`Flow<GenerateContentResponse>`	A `Flow` which will emit responses as they are returned from the model.

startChat

fun startChat(history: List<Content> = emptyList()): Chat

Creates a Chat instance which internally tracks the ongoing conversation with the model

Public properties

generationConfig

val generationConfig: GenerationConfig?

modelName

val modelName: String

safetySettings

val safetySettings: List<SafetySetting>?

systemInstruction

val systemInstruction: Content?

toolConfig

val toolConfig: ToolConfig?

tools

val tools: List<Tool>?