Displayable Nodes Overview | Vellum

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.

Node	Description
Agent Node	Simplify tool calling with automatic schema handling and iterative loop logic
Inline Prompt Node	Execute prompts directly within workflows without requiring prompt deployments
Inline Subworkflow Node	Execute subworkflows defined inline within your workflow code
Prompt Deployment Node	Execute deployed prompts from your Prompt Deployment system
Search Node	Perform hybrid search against a Document Index for RAG applications
Subworkflow Deployment Node	Execute deployed workflows as subworkflows within parent workflows
API Node	Make HTTP requests to external API endpoints
Code Execution Node	Run custom Python or TypeScript code within your workflows
Templating Node	Apply Jinja2 templating for lightweight data transformations
Guardrail Node	Run inline evaluations using pre-defined Metrics for quality checks
Map Node	Iterate over arrays, executing subworkflows for each item with parallel processing
Conditional Node	Branch workflow execution based on conditions and upstream node results
Merge Node	Consolidate divergent execution paths using configurable merge strategies
Error Node	Terminate workflow execution and raise custom error messages
Final Output Node	Stream 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

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