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

Package-level declarations

Types

abstract class DynamicPromptExecutor : PromptExecutor

A PromptExecutor that introduces an explicit resolveModel step before every LLM operation.

class ModelResolutionException(requestedModel: LLModel, detailedMsg: String? = null, cause: Throwable? = null) : Exception

Exception thrown when model resolution (PromptExecutorAPI.resolveModel) fails for a requested model.

PromptExecutor

actual abstract class PromptExecutor : PromptExecutorAPI

An interface representing an executor for processing LLM prompts. This defines methods for executing prompts against models with or without tool assistance, as well as for streaming responses.

actual abstract class PromptExecutor : PromptExecutorAPI

An interface representing an executor for processing LLM prompts. This defines methods for executing prompts against models with or without tool assistance, as well as for streaming responses.

expect abstract class PromptExecutor : PromptExecutorAPI

An interface representing an executor for processing LLM prompts. This defines methods for executing prompts against models with or without tool assistance, as well as for streaming responses.

actual abstract class PromptExecutor : PromptExecutorAPI

An interface representing an executor for processing LLM prompts. This defines methods for executing prompts against models with or without tool assistance, as well as for streaming responses.

actual abstract class PromptExecutor : PromptExecutorAPI

An interface representing an executor for processing LLM prompts. This defines methods for executing prompts against models with or without tool assistance, as well as for streaming responses.

actual abstract class PromptExecutor : PromptExecutorAPI

An interface representing an executor for processing LLM prompts. This defines methods for executing prompts against models with or without tool assistance, as well as for streaming responses.

PromptExecutorAPI

interface PromptExecutorAPI : AutoCloseable

API for PromptExecutor

PromptExecutorBuilder

class PromptExecutorBuilder

Builder for constructing a PromptExecutor that automatically selects the appropriate executor implementation based on the registered clients.

PromptExecutorOperation

enum PromptExecutorOperation : Enum<PromptExecutorOperation>

Enum representing different operations that can be performed by the prompt executor.

ResolvedModel

data class ResolvedModel(val effectiveModel: LLModel)

Represents a resolved model for use by PromptExecutorAPI. Outcome of PromptExecutorAPI.resolveModel

StructureFixingParser

class StructureFixingParser(val model: LLModel, val retries: Int, prompt: (builder: PromptBuilder, content: String, structure: Structure<*, *>, exception: SerializationException) -> PromptBuilder = ::defaultFixingPrompt)

Helper fixing parser for handling malformed structured data that uses LLMs to attempt to correct any errors in the provided content to produce valid structured outputs.

Functions

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.

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.