All Objects
UnstructuredChunkingStrategy
Configuration for chunking unstructured data, including partitioning and chunking strategies, character limits, and similarity thresholds.
The partitioning strategy used for unstructured data.
Available options:
auto, fast, hi_res, ocr_only The chunking strategy used for unstructured data.
Available options:
basic, by_title, by_page, by_similarity The maximum number of characters allowed per chunk.
The number of characters after which a new chunk is created.
The number of characters to overlap between chunks.
Threshold for similarity when chunking by similarity, with a value between 0.0 and 1.0.
Required range:
0 < x < 1Indicates whether to apply overlap to all chunks or only between adjacent chunks.