ai-mocks-ollama/dev.mokksy.aimocks.ollama.generate/GenerateRequest

GenerateRequest

data class GenerateRequest(val model: String, val prompt: String? = null, val suffix: String? = null, val images: List<String>? = null, val think: Boolean? = null, val format: Format? = null, val options: ModelOptions? = null, val system: String? = null, val template: String? = null, val stream: Boolean = true, val raw: Boolean? = null, val keepAlive: String? = null, val context: List<Int>? = null)(source)

Represents a request to generate a completion for a given prompt with a provided model.

Constructors

GenerateRequest

constructor(model: String, prompt: String? = null, suffix: String? = null, images: List<String>? = null, think: Boolean? = null, format: Format? = null, options: ModelOptions? = null, system: String? = null, template: String? = null, stream: Boolean = true, raw: Boolean? = null, keepAlive: String? = null, context: List<Int>? = null)

Properties

val context: List<Int>?

The context parameter returned from a previous request, used to keep a short conversational memory

val format: Format?

The format to return a response in. Format can be "json" or a JSON schema

val images: List<String>?

A list of base64-encoded images (for multimodal models such as llava)

@SerialName(value = "keep_alive")

val keepAlive: String?

Controls how long the model will stay loaded into memory following the request (default: "5m")

val model: String

The model name to use for generation (required)

val options: ModelOptions?

Additional model parameters such as temperature

val prompt: String?

The prompt to generate a response for

val raw: Boolean?

If true no formatting will be applied to the prompt

val stream: Boolean

If false the response will be returned as a single response object, rather than a stream of objects

val suffix: String?

The text after the model response

val system: String?

System message (overrides what is defined in the Modelfile)

val template: String?

The prompt template to use (overrides what is defined in the Modelfile)

val think: Boolean?

Should the model think before responding? (for thinking models)