Abstract
abstract class AbstractLlmOperations(toolDecorator: ToolDecorator, modelProvider: <Error class: unknown class>, validator: <Error class: unknown class>, validationPromptGenerator: ValidationPromptGenerator = DefaultValidationPromptGenerator(), autoLlmSelectionCriteriaResolver: AutoLlmSelectionCriteriaResolver, dataBindingProperties: LlmDataBindingProperties) : LlmOperations
Convenient superclass for LlmOperations implementations, which should normally extend this Find all tool callbacks and decorate them to be aware of the platform Also emits events.
Constructors
Link copied to clipboard
constructor(toolDecorator: ToolDecorator, modelProvider: <Error class: unknown class>, validator: <Error class: unknown class>, validationPromptGenerator: ValidationPromptGenerator = DefaultValidationPromptGenerator(), autoLlmSelectionCriteriaResolver: AutoLlmSelectionCriteriaResolver, dataBindingProperties: LlmDataBindingProperties)
Functions
Link copied to clipboard
override fun <O> createObject(messages: List<Message>, interaction: LlmInteraction, outputClass: Class<O>, agentProcess: AgentProcess, action: Action?): O
Create an output object, in the context of an AgentProcess.
Link copied to clipboard
override fun <O> createObjectIfPossible(messages: List<Message>, interaction: LlmInteraction, outputClass: Class<O>, agentProcess: AgentProcess, action: Action?): <Error class: unknown class><O>
Try to create an output object in the context of an AgentProcess. Return a failure result if the LLM does not have enough information to create the object.
Link copied to clipboard
open fun <O> doTransform(prompt: String, interaction: LlmInteraction, outputClass: Class<O>, llmRequestEvent: LlmRequestEvent<O>?): O
Low level transform, not necessarily aware of platform This is a convenience overload that creates a UserMessage from a String prompt
abstract fun <O> doTransform(messages: List<Message>, interaction: LlmInteraction, outputClass: Class<O>, llmRequestEvent: LlmRequestEvent<O>?): O
Low level transform, not necessarily aware of platform
Link copied to clipboard
open fun generate(prompt: String, interaction: LlmInteraction, agentProcess: AgentProcess, action: Action?): String
Generate text in the context of an AgentProcess.