executeStreaming

abstract fun executeStreaming(prompt: Prompt, model: LLModel, tools: List<ToolDescriptor> = emptyList()): Flow<StreamFrame>(source)

Executes a given prompt using the specified LLM and returns a stream of output as a flow of StreamFrame objects.

Return

A flow emitting StreamFrame objects that represent the streaming output of the LLM.

Parameters

prompt

The prompt containing input messages and parameters to guide the LLM execution.

model

The LLM to be used for processing the prompt.

tools

An optional list of ToolDescriptor objects that define the tools available for the execution.