prompt-executor-model/ai.koog.prompt.executor.llms/SingleLLMPromptExecutor

SingleLLMPromptExecutor

open class ~~SingleLLMPromptExecutor~~(llmClient: LLMClient) : PromptExecutor(source)

Deprecated

Please use MultiLLMPromptExecutor instead

Replace with

import ai.koog.prompt.executor.llms.MultiLLMPromptExecutor

MultiLLMPromptExecutor

Executes prompts using a direct client for communication with large language model (LLM) providers.

This class provides functionality to execute prompts with optional tools and retrieve either a list of responses or a streaming flow of response chunks from the LLM provider. It delegates the actual LLM interaction to the provided implementation of LLMClient.

Parameters

llmClient

The client used for direct communication with the LLM provider.

Constructors

SingleLLMPromptExecutor

constructor(llmClient: LLMClient)

Creates an instance of LLMPromptExecutor.

Functions

open override fun close()

execute

open suspend override fun execute(prompt: Prompt, model: LLModel, tools: List<ToolDescriptor>): List<Message.Response>

Executes a given prompt using the specified LLM and tools, returning a list of responses from the model.

executeMultipleChoices

open suspend override fun executeMultipleChoices(prompt: Prompt, model: LLModel, tools: List<ToolDescriptor>): List<LLMChoice>

Receives multiple independent choices from the LLM. The method is implemented only for some specific providers which support multiple LLM choices.

executeStreaming

open override fun executeStreaming(prompt: Prompt, model: LLModel, tools: List<ToolDescriptor>): Flow<StreamFrame>

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

executeStructured

suspend fun <T> PromptExecutor.executeStructured(prompt: Prompt, model: LLModel, config: StructuredRequestConfig<T>, fixingParser: StructureFixingParser? = null): Result<StructuredResponse<T>>

inline suspend fun <T> PromptExecutor.executeStructured(prompt: Prompt, model: LLModel, examples: List<T> = emptyList(), fixingParser: StructureFixingParser? = null): Result<StructuredResponse<T>>

suspend fun <T> PromptExecutor.executeStructured(prompt: Prompt, model: LLModel, serializer: KSerializer<T>, examples: List<T> = emptyList(), fixingParser: StructureFixingParser? = null): Result<StructuredResponse<T>>

Executes a prompt with structured output, enhancing it with schema instructions or native structured output parameter, and parses the response into the defined structure.

getBasicJsonSchemaGenerator

open override fun getBasicJsonSchemaGenerator(model: LLModel): BasicJsonSchemaGenerator

Basic JSON schema generator required for the given model. Return BasicJsonSchemaGenerator by default.

getStandardJsonSchemaGenerator

open override fun getStandardJsonSchemaGenerator(model: LLModel): StandardJsonSchemaGenerator

Standard JSON schema generator required for the given model. Return StandardJsonSchemaGenerator by default.

models

open suspend override fun models(): List<LLModel>

Retrieves a list of available models from all LLM clients managed by this executor.

moderate

open suspend override fun moderate(prompt: Prompt, model: LLModel): ModerationResult

Moderates the content of a given message with attachments using a specified LLM.

parseResponseToStructuredResponse

suspend fun <T> PromptExecutor.parseResponseToStructuredResponse(response: Message.Assistant, config: StructuredRequestConfig<T>, model: LLModel, fixingParser: StructureFixingParser? = null): StructuredResponse<T>

Parses a structured response from the assistant message using the provided structured output configuration and language model. If a fixing parser is specified in the configuration, it will be used; otherwise, the structure will be parsed directly.