Classifying Images

from typing import Literal
from pydantic import BaseModel, Field

class ImageClassification(BaseModel):
    rationale: str = Field(..., description="A rationale for the classification, based on the visual content and features of the image. Keep it short and concise, yet detailed enough to justify the classification.")
    image_type: Literal["news", "entertainment", "advertising", "other"] = Field(..., description="The type of image being processed")
    confidence: Literal["hi", "med", "lo"] = Field(..., description="Confidence score for the classification, based on the rationale provided and the visual features of the image. For ambiguous images, the confidence score should be `lo`.")

{
  "rationale": "The image contains financial market data and a news presenter from Bloomberg News, indicating a broadcast of financial news. The financial indices are highlighted, and stock performance is shown, which is typical for a news segment on economic updates.",
  "image_type": "news",
  "confidence": "hi"
}