For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
BlogLog InRequest Demo
HomeProductDevelopersSelf-HostingChangelog
HomeProductDevelopersSelf-HostingChangelog
  • Getting Started
    • Overview
  • Workflows SDK
    • Introduction
    • Installation
    • Core Concepts
    • Defining Control Flow
    • Configuration
    • Custom Docker Images
      • Displayable Nodes
        • Agent Node
        • Inline Prompt Node
        • Inline Subworkflow Node
        • Prompt Deployment Node
        • Search Node
        • Subworkflow Deployment Node
        • API Node
        • Code Execution Node
        • Templating Node
        • Guardrail Node
        • Map Node
        • Conditional Node
        • Merge Node
        • Error Node
        • Final Output Node
      • Datasets
      • CLI
  • Client SDK
    • Introduction
    • Authentication
    • API Versioning
LogoLogo
BlogLog InRequest Demo
On this page
  • Supported Displayable Nodes
  • Push and Pull Operations
  • Node Configuration
Workflows SDKAPI Reference

Displayable Nodes Overview

Was this page helpful?
Previous

Agent Node

Next
Built with

Supported Displayable Nodes

Displayable nodes are nodes that can be displayed and edited in the Vellum UI. They support complete push and pull operations allowing you to edit the node’s configuration in either the Vellum UI or as code and have those changes reflected in the other.

Below is an overview of each Displayable Node type with links to their detailed API reference pages.

NodeDescription
Agent NodeSimplify tool calling with automatic schema handling and iterative loop logic
Inline Prompt NodeExecute prompts directly within workflows without requiring prompt deployments
Inline Subworkflow NodeExecute subworkflows defined inline within your workflow code
Prompt Deployment NodeExecute deployed prompts from your Prompt Deployment system
Search NodePerform hybrid search against a Document Index for RAG applications
Subworkflow Deployment NodeExecute deployed workflows as subworkflows within parent workflows
API NodeMake HTTP requests to external API endpoints
Code Execution NodeRun custom Python or TypeScript code within your workflows
Templating NodeApply Jinja2 templating for lightweight data transformations
Guardrail NodeRun inline evaluations using pre-defined Metrics for quality checks
Map NodeIterate over arrays, executing subworkflows for each item with parallel processing
Conditional NodeBranch workflow execution based on conditions and upstream node results
Merge NodeConsolidate divergent execution paths using configurable merge strategies
Error NodeTerminate workflow execution and raise custom error messages
Final Output NodeStream workflow responses to production endpoints with Expression inputs

Push and Pull Operations

All Displayable Nodes support bidirectional synchronization between the Vellum UI and your SDK code:

  • Push: Upload locally defined node configurations to the Vellum application using vellum workflows push
  • Pull: Download node configurations from the Vellum UI to your local SDK using vellum workflows pull

This enables seamless collaboration between technical and non-technical team members, allowing nodes to be configured in either environment while maintaining consistency.

Node Configuration

Each Displayable Node can be configured with:

  • Attributes: Required and optional parameters that define the node’s behavior
  • Outputs: The data types and values returned by the node after execution
  • Input Mapping: References to Workflow inputs or outputs from upstream nodes
  • Ports: Conditional routing logic that controls workflow execution flow based on node outputs

For detailed configuration options and code examples, see the individual node reference pages linked above.

For comprehensive examples of port syntax and conditional logic patterns, see the Ports and Branches tutorial.