@agentica/core/lib/structures/IMicroAgenticaExecutor.d.ts

Agentic AI Library specialized in LLM Function Calling

import type { ILlmSchema } from "@samchon/openapi";
import type { MicroAgenticaContext } from "../context/MicroAgenticaContext";
import type { AgenticaExecuteHistory } from "../histories/AgenticaExecuteHistory";
/**
 * Executor of the Micro Agentic AI.
 *
 * `IMicroAgenticaExecutor` represents an executor of the
 * {@link MicroAgentica}, composing its internal agents to accomplish
 * the Agentic AI through the LLM (Large Language Model) function
 * calling.
 *
 * You can customize one of these intnernal agents by configuring
 * properties of the `IMicroAgenticaExecutor` type, and assigning
 * it to the {@link IMicroAgenticaConfig.executor} property.
 *
 * @author Samchon
 */
export interface IMicroAgenticaExecutor<Model extends ILlmSchema.Model> {
    /**
     * Function caller agent.
     *
     * `Call` agent performs the LLM (Large Language Model) function
     * calling from the candidate functions enrolled in the
     * {@link AgenticaContext.stack}. And the scope of function calling
     * is, not only just arguments filling, but also actual executing
     * the function and returning the result.
     *
     * By the way, conversation context with user can be not enough to
     * filling the arguments of the candidate functions. In that case,
     * the `call` agent will ask the user to fill the missing arguments.
     *
     * Otherwise the cpnversation context is enough, so that succeeded
     * to call some candidate functions, the `call` agent will step to
     * the {@link describe} agent to explain the result of the function
     * calling to the user as markdown content.
     *
     * @param ctx Context of the agent
     * @returns List of prompts generated by the caller
     * @warning Recommend not to customize, due to its validation
     *          feedback strategy is working very well, and the `call`
     *          agent is the most general topic which can be universally
     *          applied to all domain fields.
     */
    call: (ctx: MicroAgenticaContext<Model>) => Promise<AgenticaExecuteHistory<Model>[]>;
    /**
     * Describer agent of the function calling result.
     *
     * `Describe` agent explains the results of the function callings
     * to the user as markdown content.
     *
     * If you configure this property as `false` or `null`, the describer
     * agent never be used.
     *
     * @param ctx Context of the agent
     * @param executes List of function calling results
     * @returns List of prompts generated by the describer
     */
    describe: boolean | null | ((ctx: MicroAgenticaContext<Model>, executes: AgenticaExecuteHistory<Model>[]) => Promise<void>);
}