Node

Nodes are the key components of a workflow, enabling the execution of a series of operations by connecting nodes with different functionalities.

Core Nodes

Start

Defines the initial parameters for starting a workflow process.

End

Defines the final output content for ending a workflow process.

Answer

Defines the response content in a Chatflow process.

Large Language Model (LLM)

Calls a large language model to answer questions or process natural language.

Knowledge Retrieval

Retrieves text content related to user questions from a knowledge base, which can serve as context for downstream LLM nodes.

Question Classifier

By defining classification descriptions, the LLM can select the matching classification based on user input.

IF/ELSE

Allows you to split the workflow into two branches based on if/else conditions.

Code Execution

Runs Python/NodeJS code to execute custom logic such as data transformation within the workflow.

Template

Enables flexible data transformation and text processing using Jinja2, a Python templating language.

Variable Aggregator

Aggregates variables from multiple branches into one variable for unified configuration of downstream nodes.

Variable Assigner

The variable assigner node is used to assign values to writable variables.

Parameter Extractor

Uses LLM to infer and extract structured parameters from natural language for subsequent tool calls or HTTP requests.

Iteration

Executes multiple steps on list objects until all results are output.

HTTP Request

Allows sending server requests via the HTTP protocol, suitable for retrieving external results, webhooks, generating images, and other scenarios.

Tools

Enables calling built-in Dify tools, custom tools, sub-workflows, and more within the workflow.