pyflink.dataframe.ai.llm.LLMAccessor.ai_embed

LLMAccessor.ai_embed(input_col: Union[str, Expression], dimension: int = 1024, *, provider: str = None, model: str = None, config: Dict[str, str] = None, cache_table: Optional[str] = None, cache_key: Optional[str] = None) → DataFrame

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.

• cache_table – Pre-registered catalog table identifier for the embedding cache.

• cache_key – Column name used as cache key.

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")
>>> df.llm.ai_embed(
...     "text", 512, model="qwen-plus",
...     cache_table="default_catalog.default_database.embed_cache",
...     cache_key="text")