Struct TextExtractionConfig 

pub struct TextExtractionConfig {
    pub chunk_size: usize,
    pub chunk_overlap: usize,
    pub clean_control_chars: bool,
    pub min_chunk_size: usize,
    pub cleaning: Option<CleaningConfig>,
}

Text extraction and chunking configuration

Fields

chunk_size: usize

Chunk size for text splitting

chunk_overlap: usize

Overlap between chunks

clean_control_chars: bool

Clean control characters

min_chunk_size: usize

Minimum chunk size to keep

cleaning: Option<CleaningConfig>

Text cleaning options

Trait Implementations

impl Clone for TextExtractionConfig

fn clone(&self) -> TextExtractionConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TextExtractionConfig

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

Formats the value using the given formatter.

impl Default for TextExtractionConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for TextExtractionConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for TextExtractionConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.