Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.agentcloud.dev/llms.txt

Use this file to discover all available pages before exploring further.

Configuration for chunking unstructured data, including partitioning and chunking strategies, character limits, and similarity thresholds.

​
partitioning
enum<string>
required

The partitioning strategy used for unstructured data.

Available options:
auto,
fast,
hi_res,
ocr_only
​
strategy
enum<string>
required

The chunking strategy used for unstructured data.

Available options:
basic,
by_title,
by_page,
by_similarity
​
max_characters
integer<int32>
required

The maximum number of characters allowed per chunk.

​
new_after_n_chars
integer<int32>
required

The number of characters after which a new chunk is created.

​
overlap
integer<int32>
required

The number of characters to overlap between chunks.

​
similarity_threshold
number<float>
required

Threshold for similarity when chunking by similarity, with a value between 0.0 and 1.0.

Required range: 0 <= x <= 1
​
overlap_all
boolean
required

Indicates whether to apply overlap to all chunks or only between adjacent chunks.