AI_CLASSIFY

Applies to: ✅ Data 360 SQL ❌ Tableau Hyper API

Analyzes text and classifies it into the best matching category from a list of categories you define. This function uses the classification model to categorize support cases, customer inquiries, product feedback, and other unstructured text.

1AI_CLASSIFY(<input_text>, <input_categories>)

• <input_text>: The text to classify.
• <input_categories>: A text array of categories with at least one unique value. An empty category list results in the Input categories cannot be empty validation error message.

After analyzing the input_text, returns the category with the highest confidence score from the input_categories.

• Input text length: The function supports input text up to 512 tokens (approximately 400-500 words). For longer text such as full emails or lengthy documents, split the content into shorter passages before classifying.
• Best for short text: This function works best on short, intent-rich text such as support case descriptions, product inquiries, and customer feedback.
• Category consistency: The input_categories parameter must be constant across all rows in the query.
• Performance: Requests to the function time out after 30 seconds.
• First execution: When executing this function on a large number of rows for the first time, you can encounter timeout or capacity errors. Start with smaller row counts and gradually increase volume to avoid these issues.
• Non-NULL values: input_text must be a non-NULL value. Add IS NOT NULL to the WHERE clause in your SQL statement to avoid NULL value errors.
• Multilingual support: The underlying model supports multiple languages.

Classify issues in an automobile repair center based on the type of issue.

1SELECT
2  "issuesIdentified__c",
3  ai_classify(input_text=>"issuesIdentified__c",
4  input_categories=>'["Engine", "Chassis", "Electrical"]') AS category
5  FROM "AutomobileServiceFeedback__dll"

Returns:

Returns only the rows matching the defined classification.

1WITH ClassifiedIssues AS (
2  SELECT
3    "serviceCenterName__c",
4    "costOfService__c",
5    "issuesIdentified__c",
6    ai_classify(
7      input_text => "issuesIdentified__c",
8      input_categories => '["Engine", "Chassis", "Electrical"]'
9    ) AS category
10  FROM "AutomobileServiceFeedback__dll"
11)
12SELECT * FROM ClassifiedIssues
13WHERE category = 'Engine';

Returns all reported vehicle issues related to the engine.

• Topic Classification: Learn about topic classification models, use cases, and integration options.
• AI Models in Data Cloud: Read an overview of AI model capabilities.