Struct PriorBundle 

pub struct PriorBundle {
    pub mean: Option<f64>,
    pub variance: Option<f64>,
    pub std_dev: Option<f64>,
    pub confidence: f64,
    pub count: u64,
    pub min: Option<f64>,
    pub max: Option<f64>,
    pub weighted_mean: Option<f64>,
}

Statistical priors from retrieved trajectories.

This is the core value proposition of RAG++ - surfacing implicit knowledge from past execution outcomes as queryable statistics.

Fields

mean: Option<f64>

Mean outcome of retrieved trajectories

variance: Option<f64>

Variance of outcomes

std_dev: Option<f64>

Standard deviation

confidence: f64

Confidence in the estimate (0-1, based on sample count)

count: u64

Number of samples contributing to statistics

min: Option<f64>

Minimum observed outcome

max: Option<f64>

Maximum observed outcome

weighted_mean: Option<f64>

Weighted mean (by retrieval score)

Implementations

impl PriorBundle

pub fn from_stats(stats: &OutcomeStats) -> Self

Create from outcome statistics.

pub fn from_outcomes(outcomes: &[f64], weights: Option<&[f64]>) -> Self

Create from a set of outcomes with optional weights.

pub fn is_reliable(&self) -> bool

Whether the prior has enough samples to be reliable.

pub fn is_empty(&self) -> bool

Whether any statistics are available.

Trait Implementations

impl Clone for PriorBundle

fn clone(&self) -> PriorBundle

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for PriorBundle

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

Formats the value using the given formatter.

impl Default for PriorBundle

fn default() -> PriorBundle

Returns the “default value” for a type.