ai-mocks-ollama/dev.mokksy.aimocks.ollama.chat/ChatRequest

ChatRequest

data class ChatRequest(val model: String, val messages: List<Message>, val tools: List<Tool>? = null, val think: Boolean? = null, val format: Format? = null, val options: ModelOptions? = null, val stream: Boolean = true, val keepAlive: String? = null)(source)

Represents a request to generate the next message in a chat with a provided model.

See Ollama API for details.

Constructors

constructor(model: String, messages: List<Message>, tools: List<Tool>? = null, think: Boolean? = null, format: Format? = null, options: ModelOptions? = null, stream: Boolean = true, keepAlive: String? = null)

Properties

val format: Format?

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

@SerialName(value = "keep_alive")

val keepAlive: String?

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

val messages: List<Message>

The messages of the chat, used to keep chat memory

val model: String

The model name to use for generation (required)

val options: ModelOptions?

Additional model parameters such as temperature. See Valid Parameters and Values

val stream: Boolean

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

val think: Boolean?

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

val tools: List<Tool>?

List of tools in JSON for the model to use if supported