Class EmbeddingExecutor

java.lang.Object

ai.nervemind.app.executor.EmbeddingExecutor

All Implemented Interfaces:

NodeExecutor

@Component
public class EmbeddingExecutor
extends Object
implements NodeExecutor

Executor for the "embedding" node type - generates vector embeddings for text.

Creates dense vector representations of text using embedding models from various providers. Essential for semantic search, similarity matching, and building RAG (Retrieval-Augmented Generation) pipelines.

Node Parameters

Embedding node configuration parameters

Parameter	Type	Default	Description
provider	String	"openai"	"openai", "ollama", "azure", "cohere"
model	String	provider-specific	Embedding model name
apiKey	String	from settings	API key for the provider
baseUrl	String	provider default	Custom base URL
input	String/List	-	Text(s) to embed (supports ${interpolation})
dimensions	Integer	model default	Output dimensions (for dimension reduction)
timeout	Integer	60	Request timeout in seconds

Supported Models

• OpenAI: text-embedding-3-small, text-embedding-3-large, text-embedding-ada-002
• Ollama: nomic-embed-text, mxbai-embed-large, all-minilm
• Cohere: embed-english-v3.0, embed-multilingual-v3.0

Output Data

Output keys added by this executor

Key	Type	Description
embedding	List<Double>	Vector embedding (or list of vectors for batch)
dimensions	Integer	Number of dimensions in the vector
model	String	Model that was used
usage	Map	Token usage information

Batch Processing

When input is a list of strings, embeddings are generated for each item in a single API call (if supported by provider), improving efficiency.

See Also:

• For using embeddings in retrieval-augmented generation
• For chat completions using LLMs

Constructor Summary

Constructors

Constructor	Description
EmbeddingExecutor()	Default constructor for EmbeddingExecutor.

Method Summary

Modifier and Type	Method	Description
Map<String,Object>	execute(ai.nervemind.common.domain.Node node, Map<String,Object> input, ExecutionService.ExecutionContext context)	Executes the business logic for this node type.
String	getNodeType()	Unique identifier for the node type this executor handles.

Methods inherited from class Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

EmbeddingExecutor

public EmbeddingExecutor()

Default constructor for EmbeddingExecutor. Initializes the HttpClient with a 30-second connection timeout.

Method Details

execute

public Map<String,Object> execute(ai.nervemind.common.domain.Node node,
 Map<String,Object> input,
 ExecutionService.ExecutionContext context)

Description copied from interface: NodeExecutor

Executes the business logic for this node type.

Specified by:

execute in interface NodeExecutor

Parameters:

node - The node definition containing parameters and configuration. Use Node.parameters() to access user settings.

input - Combined output from all upstream nodes that connected to this node. For simple flows, this contains the direct predecessor's output. For merge nodes, it contains combined data.

context - Verification context providing access to workflow-scoped services, logger, and execution metadata.

Returns:

A Map containing the results of this node's execution. Keys in this map become available variables for downstream nodes.
Note: Returning null is treated as an empty map.

getNodeType

public String getNodeType()

Description copied from interface: NodeExecutor

Unique identifier for the node type this executor handles. This must match the 'type' field in the JSON definition of the node.

Specified by:

getNodeType in interface NodeExecutor

Returns:

the node type identifier ("embedding")