split_list_of_docs#

langchain.chains.combine_documents.reduce.split_list_of_docs(

docs: list[Document],

length_func: Callable,

token_max: int,

**kwargs: Any,

) → list[list[Document]][source]#

Split Documents into subsets that each meet a cumulative length constraint.

Parameters:

• docs (list[Document]) – The full list of Documents.

• length_func (Callable) – Function for computing the cumulative length of a set of Documents.

• token_max (int) – The maximum cumulative length of any subset of Documents.

• **kwargs (Any) – Arbitrary additional keyword params to pass to each call of the length_func.

Returns:

A List[List[Document]].

Return type:

list[list[Document]]

Examples using split_list_of_docs

• # Basic example (short documents)

• How to summarize text through parallelization

• Summarize Text