Class TextClassifierExecutor

java.lang.Object

ai.nervemind.app.executor.TextClassifierExecutor

All Implemented Interfaces:

NodeExecutor

@Component
public class TextClassifierExecutor
extends Object
implements NodeExecutor

Executor for the "textClassifier" node type - classifies text into categories using LLM.

Uses a Large Language Model to analyze text and categorize it into one or more predefined categories. Useful for sentiment analysis, intent detection, spam filtering, and content tagging.

Node Parameters

Text Classifier node configuration parameters

Parameter	Type	Default	Description
provider	String	"openai"	LLM provider ("openai", "anthropic", "ollama")
model	String	provider-specific	Model name (optimized for classification)
text	String	-	Text to classify (supports interpolation)
categories	List<String>	[]	List of valid categories
multiLabel	Boolean	false	Allow multiple categories per text
includeConfidence	Boolean	true	Include confidence scores
timeout	Integer	60	Request timeout in seconds

Output Data (Single Label)

Output keys when multiLabel=false

Key	Type	Description
category	String	The predicted category
confidence	Double	Confidence score (0.0-1.0)
allScores	Map	Scores for all candidate categories

Output Data (Multi Label)

Output keys when multiLabel=true

Key	Type	Description
categories	List<String>	List of predicted categories
confidences	List<Double>	Confidence scores for predicted categories

Prompt Engineering

This executor automatically constructs a specialized system prompt that forces the LLM to return valid JSON with constrained output corresponding to the provided categories.

See Also:

• For general purpose LLM interactions

Constructor Summary

Constructors

Constructor	Description
TextClassifierExecutor(ai.nervemind.common.service.SettingsServiceInterface settingsService)	Creates a new text classifier executor with configured HTTP client.

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

TextClassifierExecutor

public TextClassifierExecutor(ai.nervemind.common.service.SettingsServiceInterface settingsService)

Creates a new text classifier executor with configured HTTP client.

Parameters:

settingsService - the settings service for configuration access

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 unique type string (e.g., "httpRequest", "llmChat").