RNet AI
  • INTRODUCTION
    • About Rnet
    • Quickstart
    • Core Concepts
      • List of Model Providers
  • GETTING STARTED
    • Model
      • Add New Provider
      • Predefined Model Integration
      • Custom Model Integration
      • Interfaces
      • Schema
    • Application Orchestration
      • Overview
      • Interactive Chat Application
      • Agent
      • App Kits
    • Workflow
      • Core Concepts
      • Node Overview
        • Start
        • Question Classifier
        • Knowledge Retrieval
        • Variable Aggregator
        • LLM
        • Direct Reply
        • IF/ELSE
        • HTTP Request
        • End
    • Knowledge Base
Powered by GitBook
On this page
  1. GETTING STARTED
  2. Workflow

Node Overview

PreviousCore ConceptsNextStart

Last updated 8 months ago

Nodes are essential components in a workflow, enabling a sequence of operations by connecting nodes with various functionalities.

Core Nodes

  1. : Sets the initial parameters to begin a workflow process.

  2. End: Defines the final output to conclude a workflow process.

  3. Answer: Specifies response content in a Chatflow process.

  4. Large Language Model (LLM): Utilizes a large language model for answering questions or processing natural language.

  5. Knowledge Retrieval: Fetches relevant text content from a knowledge base for context in downstream LLM nodes.

  6. Question Classifier: Uses defined classification descriptions to allow the LLM to categorise user input.

  7. IF/ELSE: Splits the workflow into two branches based on conditional statements.

  8. Code Execution: Executes custom logic, such as data transformation, using Python/NodeJS code.

  9. Template Transformation: Uses Jinja2, a Python templating language, for flexible data transformation and text processing.

  10. Variable Aggregator: Combines variables from multiple branches into one for unified configuration in downstream nodes.

  11. Parameter Extractor: Uses LLM to infer and extract structured parameters from natural language for subsequent tool usage or HTTP requests.

  12. Iteration: Repeats steps on list objects until all results are processed.

  13. HTTP Request: Sends server requests using the HTTP protocol for external data retrieval, webhooks, image generation, and more.

  14. Tools: Allows the integration of built-in Dify tools, custom tools, sub-workflows, and more within the workflow.

Start