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_embed

pyflink.dataframe.ai.llm.LLMAccessor.ai_embed#

LLMAccessor.ai_embed(input_col: str | Expression, dimension: int = 1024, *, provider: str = None, model: str = None, config: Dict[str, str] = None) → DataFrame[source]#

Generate embedding vectors for text.

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

  • dimension – Dimension of the embedding vector (default 1024).

  • provider – Provider name.

  • model – Model name.

  • config – Optional runtime config.

Returns:

  • embedding (ARRAY<FLOAT>): the embedding vector.

Return type:

A new DataFrame with a column appended

Example:

>>> df.llm.ai_embed("text", 512, model="qwen-plus")

previous

pyflink.dataframe.ai.llm.LLMAccessor.ai_mask

next

PyFlink Common

On this page
  • LLMAccessor.ai_embed()

This Page

  • Show Source

Created using Sphinx 7.4.7.

Built with the PyData Sphinx Theme 0.16.1.