Struct ChunkConfig 

pub struct ChunkConfig {
    pub max_chars: usize,
    pub overlap: usize,
    pub min_chunk_size: usize,
}

Configuration for text chunking.

Fields

max_chars: usize

Maximum characters per chunk. Default: 2000 (~500 tokens for most models).

overlap: usize

Number of characters to overlap between chunks. Default: 200 (~50 tokens) for context continuity.

min_chunk_size: usize

Minimum chunk size (avoids tiny trailing chunks). Default: 100 characters.

Implementations

impl ChunkConfig

pub fn for_ollama() -> Self

Create a config optimized for Ollama nomic-embed-text.

nomic-embed-text has an 8192 token context window. We use conservative chunking to stay well under the limit.

pub fn for_minilm() -> Self

Create a config for HuggingFace MiniLM models.

MiniLM models have a 256 token limit, so we use smaller chunks.

Trait Implementations

impl Clone for ChunkConfig

fn clone(&self) -> ChunkConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ChunkConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for ChunkConfig

fn default() -> Self

Returns the “default value” for a type.