Struct RetentionRatioTruncation 

pub struct RetentionRatioTruncation {
    pub retention_ratio: f32,
    pub type: String,
    pub token_limits: Option<TokenLimits>,
}

Fields

retention_ratio: f32

Fraction of post-instruction conversation tokens to retain (0.0 - 1.0) when the conversation exceeds the input token limit. Setting this to 0.8 means that messages will be dropped until 80% of the maximum allowed tokens are used. This helps reduce the frequency of truncations and improve cache rates.

type: String

Use retention ratio truncation.

token_limits: Option<TokenLimits>

Optional custom token limits for this truncation strategy. If not provided, the model’s default token limits will be used.

Trait Implementations

impl Clone for RetentionRatioTruncation

fn clone(&self) -> RetentionRatioTruncation

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RetentionRatioTruncation

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for RetentionRatioTruncation

fn deserialize<__D>( __deserializer: __D, ) -> Result<RetentionRatioTruncation, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for RetentionRatioTruncation

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

where __S: Serializer,

Serialize this value into the given Serde serializer.