agents-core/ai.koog.agents.core.agent/GraphAgentServiceBuilder

GraphAgentServiceBuilder

class GraphAgentServiceBuilder<Input, Output>(source)

A builder class for constructing a GraphAIAgentService with configurable properties such as prompt executor, model, tool registry, prompts, and various other configurations.

Parameters

Input

The input type for the AI agent graph service.

Output

The output type for the AI agent graph service.

Functions

agentConfig

fun agentConfig(config: AIAgentConfig): GraphAgentServiceBuilder<Input, Output>

Configures the agent with the specified parameters from the provided AIAgentConfig instance.

build

fun build(): GraphAIAgentService<Input, Output>

Builds and returns an instance of GraphAIAgentService configured with the specified parameters.

install

fun <TConfig : FeatureConfig> install(feature: AIAgentGraphFeature<TConfig, *>, configure: ConfigureAction<TConfig>): GraphAgentServiceBuilder<Input, Output>

Installs a specified feature into the GraphServiceBuilder and applies the given configuration to it.

llmModel

fun llmModel(model: LLModel): GraphAgentServiceBuilder<Input, Output>

Sets the Large Language Model (LLM) for the current GraphServiceBuilder instance.

maxIterations

fun maxIterations(maxIterations: Int): GraphAgentServiceBuilder<Input, Output>

Sets the maximum number of iterations to be used in the graph processing service. This parameter controls how many processing cycles will be executed.

numberOfChoices

fun numberOfChoices(numberOfChoices: Int): GraphAgentServiceBuilder<Input, Output>

Sets the number of choices that the service will consider during processing.

prompt

fun prompt(prompt: Prompt): GraphAgentServiceBuilder<Input, Output>

Sets the prompt to be used by the GraphServiceBuilder.

promptExecutor

fun promptExecutor(promptExecutor: PromptExecutor): GraphAgentServiceBuilder<Input, Output>

Sets the prompt executor for the GraphServiceBuilder. The prompt executor is responsible for handling the interaction with the language model based on the provided prompts and configurations.

systemPrompt

fun systemPrompt(systemPrompt: String): GraphAgentServiceBuilder<Input, Output>

Sets the system prompt for the GraphServiceBuilder, defining the initial context or instructions to be used by the language model.

temperature

fun temperature(temperature: Double): GraphAgentServiceBuilder<Input, Output>

Sets the temperature parameter for the GraphServiceBuilder. The temperature controls the randomness of the model's output, where a lower value results in more deterministic results, and a higher value increases variability.

toolRegistry

fun toolRegistry(toolRegistry: ToolRegistry): GraphAgentServiceBuilder<Input, Output>

Sets the ToolRegistry to be used by the GraphServiceBuilder.