Categorizer Node

This node allows you to categorize text into custom defined categories using AI. For example, if you input “Golden Retriever” and you were to classify it into “Dog” or “Cat”, the category will be “Dog.

​

Node Inputs

1. Text for categorization: The text you want to categorize
   • Type: Text
2. Additional Context: The additional information or instructions for the AI
   • Type: Text
3. Category Names and Descriptions: The categories to classify the input into. Each category has two fields to define the category:
   • Name: The name of the category
     • Type: Text
   • Description: Explanation of the items that fall into this category
     • Type: Text

​

Node Parameters

On the face of the node:

1. Include Justification: When this parameter is turned on, the justification output field for why the specific category was chosen will be available.

In the gear:

1. Provider: Provider of the AI model you want to use. The default provider is OpenAI.
2. Model: Model name of the AI model you want to use. The default model is gpt-4o.

​

Node Outputs

1. Category: The category chosen by AI
   • Type: Text
   • Example usage: {{categorizer_0.category}}
2. Justification: The justification given by the AI for selecting the category (if include justification is switched on)
   • Type: Text
   • Example usage: {{categorizer_0.justification}}

​

Considerations

• Write clear category descriptions for accurate outputs.
• Use additional context for complex rules.

​

Example

The below example is a pipeline which categorizes a review into positive, negative or neutral.