pyflink.dataframe.ai.llm.LLMAccessor.ai_summarize

LLMAccessor.ai_summarize(input_col: Union[str, Expression], max_length: int, *, provider: Optional[str] = None, model: Optional[str] = None, cache_table: Optional[str] = None, cache_key: Optional[Union[str, List[str]]] = None, config: Optional[Dict[str, str]] = None, **kwargs) → DataFrame

Summarize text to a maximum length.

Parameters

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

• max_length – Maximum length of the summary in characters. Must be greater than 0.

• provider – Registered model provider lookup name. Uses default if not specified. If no provider is configured, model is treated as a catalog model name.

• model – Model name.

• cache_table – Optional cache table identifier.

• cache_key – Optional cache key column name or list of column names.

• config – Optional dict of runtime prediction options.

• **kwargs –

  Per-call overrides for the selected DataFrame model provider’s constructor parameters. Overrides are applied only when the call uses a configured provider.

  Note: This function uses its own task-specific prompt. Provider configurations for the system prompt, such as system_prompt on OpenAICompatProvider and DashScopeProvider, do not take effect for this call.

Returns

A new DataFrame with a column appended –

• summary (STRING): the summarized text.

Examples

Simple invocation:

::

>>> import pyflink.dataframe as pf
>>> pf.set_model_provider(pf.OpenAICompatProvider(
...     task="chat/completions"))
>>> df = pf.from_dict({"article": ["Long article text..."]})
>>> df.llm.ai_summarize("article", 200, model="qwen3.6-plus")

With cache:

::

>>> df.llm.ai_summarize(
...     "article", 200, model="qwen3.6-plus",
...     cache_table="`fluss-catalog`.default_database.summarize_cache",
...     cache_key="article")

Using runtime config supported by pyflink.dataframe.OpenAICompatProvider:

::

>>> df.llm.ai_summarize(
...     "article", 200, model="qwen3.6-plus",
...     config={"max-concurrent-operations": "20"})