Liking cljdoc? Tell your friends :D

chunk.core

This namespace splits text recursively into chunks for RAG and LLM pipelines.

split breaks text into overlapping chunks. No chunk is larger than a target size. split tries an ordered list of separators, from coarsest (paragraph) to finest (character), so chunks use natural boundaries. :length-fn measures the size. Its default is count, which measures characters. Pass a token counter, for example tokenizers-clj's count-tokens, to chunk by tokens. Tokens are the correct unit for a model with a token limit.

This namespace splits text recursively into chunks for RAG and LLM pipelines.

`split` breaks text into overlapping chunks. No chunk is larger than a target size.
`split` tries an ordered list of separators, from coarsest (paragraph) to finest
(character), so chunks use natural boundaries. `:length-fn` measures the size. Its
default is `count`, which measures characters. Pass a token counter, for example
tokenizers-clj's `count-tokens`, to chunk by tokens. Tokens are the correct unit for
a model with a token limit.
raw docstring

cljdoc builds & hosts documentation for Clojure/Script libraries

Keyboard shortcuts
Ctrl+kJump to recent docs
Move to previous article
Move to next article
Ctrl+/Jump to the search field
× close