Skip to main content

ReAct

Reasoning Engine with Actions using Agents / Tools and Forms including RAG as an Agent.

Introduction​

The ReAct reasoning engine is designed to assist users with a variety of queries by utilizing different agents and tools. This documentation provides guidance on configuring the ReAct reasoning engine and integrating it with agents/tools, including a RAG (Retrieval-Augmented Generation) engine. The RAG Q&A Criteria textbox specifies when to use the RAG agent, enhancing the AI's capability to provide accurate and comprehensive answers.

Suggested Content for System Prompt​

  • Tone:

    • Friendly and helpful
    • Professional and concise
    • Clear and informative

  • Key Components:

    • Greeting and introduction
    • General guidelines for responses
    • Specific handling instructions for common tasks
    • Examples for clarity
    • Encouragement for user interaction

ReAct & LLM Agent Settings Configure your AI assistant to call out Agents / Tools

This documentation ensures a comprehensive understanding of setting up and configuring the ReAct reasoning engine with Actions and agents, including a RAG engine. It also outlines the necessary components for any successful web project.