Product description classification

Name and categorize shoes in JSON format.

You can query a model directly and test the results returned when using different parameter values with the Cloud console, or by calling the Vertex AI API directly. For an example of using the Vertex AI API, see Quickstart using the Vertex AI API. To view this sample in the Cloud console: Go to Google Cloud console

System instructions Analyze and categorize the input product description. Use JSON Format: - title: The name of the shoe model; if not provided, then provide a concise, descriptive title; title should be between 3 to 10 words. - classification: From the specified [shoe type list], select the category that best fits the product description. This must be in English. Selections outside of the [shoe type list] are not allowed. Do not add any information that is not included in the product description. Prompt Freeform CLASSIFICATION LIST : [Athletic Shoes, Casual Shoes, Dress Shoes, Boots, Sandals, Specialty Shoes] Lightweight Shawnson running shoe with breathable mesh upper, responsive foam cushioning, durable rubber outsole for traction on various surfaces. Ideal for daily runs and training sessions. { "title": "Shawnson", "classification": "Athletic Shoes" } Classic leather upper, lace-up closure, cushioned footbed for comfort, versatile design suitable for both casual and semi-formal wear. Response { "title": "Classic Leather Lace-Up Shoe", "classification": "Casual Shoes" }

Model: gemini-2.5-pro Temperature: 0.2 Max output tokens: 8192 TopK: 40.0 TopP: 0.95