Classification Automatique

Automatically classifies data into predefined categories using a language model. Returns the category and a confidence score.

Parameters

Parameter	Type	Required	Variable	Description
input	dynamic value	No	Yes	Entities or texts to automatically classify.
classificationScheme.type	choice (predefined, ontology_types, custom)	No	No	Classification scheme type: predefined list, ontology types, or custom. (Default: "predefined")
classificationScheme.categories	array	Yes	No	List of available categories for classification (e.g. Tech, Finance, Health).
classificationScheme.allowMultiple	boolean	No	No	Allow assigning multiple categories per item. (Default: false)
classificationScheme.maxCategories	number	No	No	Maximum number of categories to assign per item (if multi-label enabled). (min 1)
classificationScheme.customPrompt	text	No	Yes	Custom instructions to guide the classification.
includeConfidence	boolean	No	No	Include confidence score in classification results. (Default: true)
confidenceThreshold	number	No	No	Minimum confidence threshold (0 to 1) to assign a category. (Default: 0.7, min 0, max 1)
entityTypeFilter	array	No	No	Filter entities by type before classification.
targetAttribute	text	No	No	Target attribute name to store the classification result on the entity.
model.provider	text	No	No	Language model provider (e.g. openai, anthropic).
model.model	text	No	No	Model identifier to use (e.g. gpt-4o).
parameters.temperature	number	No	No	Model creativity. Low value recommended for classification. (Default: 0.3, min 0, max 2)
parameters.maxTokens	number	No	No	Maximum number of tokens in the response. (Default: 2048, min 1, max 128000)
outputVariable	text	No	No	Output variable name containing the classification results.

Parameters marked Variable = Yes accept the {{blockName.field}} syntax.

Output

Output variable : classificationResult

{
  "category": "...",
  "confidence": 0
}

Example

Classify a support ticket.

Input :

{"text": "Je ne peux pas me connecter a mon compte"}

Output :

{"category": "authentification", "confidence": 0.91}

Tip

Define categories in the block configuration. {{classificationResult.category}} contains the selected category, {{classificationResult.confidence}} the score.