dev.langchain4j.data.document

Interface DocumentSplitter

public interface DocumentSplitter

Defines the interface for splitting a document into text segments. This is necessary as LLMs have a limited context window, making it impossible to send the entire document at once. Therefore, the document should first be split into segments, and only the relevant segments should be sent to LLM.

Method Summary

Modifier and Type	Method and Description
List<TextSegment>	split(Document document) Splits a single Document into a list of TextSegment objects.
default List<TextSegment>	splitAll(List<Document> documents) Splits a list of Documents into a list of TextSegment objects.

Method Detail

split

List<TextSegment> split(Document document)

Splits a single Document into a list of TextSegment objects. The metadata is typically copied from the document and enriched with segment-specific information, such as position in the document, page number, etc.

Parameters:

document - The Document to be split.

Returns:

A list of TextSegment objects derived from the input Document.

splitAll

default List<TextSegment> splitAll(List<Document> documents)

Splits a list of Documents into a list of TextSegment objects. This is a convenience method that calls the split method for each Document in the list.

Parameters:

documents - The list of Documents to be split.

Returns:

A list of TextSegment objects derived from the input Documents.