Skip to main content
Ctrl+K
PyFlink 1.20+vvr.11.7.dev0 documentation - Home PyFlink 1.20+vvr.11.7.dev0 documentation - Home
  • API Reference
  • Examples
  • API Reference
  • Examples

Section Navigation

  • PyFlink Table
  • PyFlink DataStream
  • PyFlink DataFrame
    • DataFrame
    • DataFrame Creation
    • Input/Output
    • SQL
    • DataType
    • User Defined Functions
    • Configuration
    • GPU Support
    • AI / LLM
  • PyFlink Common
  • API Reference
  • PyFlink DataFrame
  • AI / LLM
  • pyflink.dataframe.ai.llm.LLMAccessor.ai_sentiment

pyflink.dataframe.ai.llm.LLMAccessor.ai_sentiment#

LLMAccessor.ai_sentiment(input_col: str | Expression, *, provider: str = None, model: str = None, config: Dict[str, str] = None) → DataFrame[source]#

Analyze the sentiment of input text.

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

  • provider – Provider name.

  • model – Model name.

  • config – Optional runtime config.

Returns:

  • score (DOUBLE): sentiment score from -1.0 to 1.0.

  • label (STRING): one of “positive”, “negative”, “neutral”.

  • confidence (DOUBLE): confidence score.

Return type:

A new DataFrame with columns appended

Example:

>>> df.llm.ai_sentiment("review", model="qwen-plus")

previous

pyflink.dataframe.ai.llm.LLMAccessor.ai_classify

next

pyflink.dataframe.ai.llm.LLMAccessor.ai_extract

On this page
  • LLMAccessor.ai_sentiment()

This Page

  • Show Source

Created using Sphinx 7.4.7.

Built with the PyData Sphinx Theme 0.16.1.