Overview of FastGPT Workflow Nodes
FastGPT workflow automation uses modular, reusable nodes as its fundamental building blocks. Each node executes a specific data processing or response generation function, and all standard workflow nodes share a uniform structural design. The following details the core shared components and connection mechanics for all FastGPT workflow nodes, as defined in the official workflow setup guide. 
Core Node Component Specifications
Every FastGPT workflow node includes three mandatory core structural components, with clear rules for their use:
| Component Type | Valid Examples | Usage Guidelines |
|---|---|---|
| Inputs | AI model, Prompt, chat history, user question, Dataset citation | Input values can be either manually entered static text or dynamic variable references. Accepted variable sources include global workflow variables and output data generated by any preceding workflow node. |
| Outputs | New context, AI reply content | All generated output data from a node can be referenced as input values for any subsequent workflow nodes within the same automation flow. |
| Connection Triggers | Structural interface points | Each node features four fixed connection points located at the top, bottom, left, and right edges of the node display. These points enable physical linking between adjacent workflow nodes. |
Node Execution and Linking
When nodes are connected via their trigger points, execution order is determined by the configured connection conditions. Linked nodes will run in a sequential sequence, with each node processing data only after the preceding connected node has completed its assigned task. The visual layout of connected nodes on the workflow canvas directly reflects the execution order, with directional arrows indicating the direction of data flow between nodes.
Source: FastGPT official source
Applicability and version scope
Use this page for the documented Workflow nodes scenario. Confirm the FastGPT, dependency, API, and deployment versions in the official source before applying a change.
Safety guardrails
Use [REDACTED_CREDENTIAL] for credentials and private data. Confirm the documented environment and version before review.
Rollback guidance
Restore the prior technical-content authority snapshot. Restore saved configuration and data snapshots, then repeat the smallest verification scenario.