OllamaClient.generate

Generates text based on a prompt using the specified model.

class OllamaClient

@safe

JSONValue

generate

(

string model

,

string prompt

,

JSONValue options = JSONValue.init

,

bool stream = false

,

string system = null

,

string[] images = null

,

JSONValue format = JSONValue.init

,

string suffix = null

,

string keepAlive = null

,

OllamaOptions opts = OllamaOptions.init

)

Parameters

model string: Model name (e.g. "llama3.1:8b").
prompt string: Input text.
options JSONValue: Raw JSONValue generation options (backward-compatible).
stream bool: Whether to stream the response (not fully supported).
system string: Optional system prompt.
images string[]: Optional base64-encoded images for multimodal input.
format JSONValue: Structured output: JSONValue("json") or a JSON Schema.
suffix string: Text appended after the generated response.
keepAlive string: How long to keep the model loaded (e.g. "5m", "0").
opts OllamaOptions: Typed OllamaOptions; takes precedence over options.

Return Value

Type: JSONValue

A JSONValue containing "response", "done", and metadata.

Meta

Source

See Implementation