Node Description

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

Core Nodes

Defines the initial parameters for starting a workflow process.

Defines the final output content for ending a workflow process.

Defines the response content in a Chatflow process.

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

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

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

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

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

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

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

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

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

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

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

Last updated