pyflink.dataframe.ai.llm.LLMAccessor.ai_classify

LLMAccessor.ai_classify(input_col: str | Expression, labels: List[str], *, provider: str = None, model: str = None, config: Dict[str, str] = None) → DataFrame

Classify text into one of the provided labels.

Parameters:

• input_col – Column name (str) or Expression for the input text.

• labels – List of label strings.

• provider – Provider name.

• model – Model name.

• config – Optional runtime config.

Returns:

• category (STRING): the predicted label.

• confidence (DOUBLE): confidence score.

Return type:

A new DataFrame with columns appended

Example:

>>> df.llm.ai_classify("text", ["positive", "negative"],
...                    model="qwen-plus")