Struct SearchResult 

pub struct SearchResult {
    pub experience: Experience,
    pub similarity: f32,
}

A search result pairing an experience with its similarity score.

Returned by PulseDB::search_similar() and PulseDB::search_similar_filtered(). Results are sorted by similarity descending (most similar first).

Similarity Score

The similarity field is computed as 1.0 - cosine_distance, where cosine distance ranges from 0.0 (identical) to 2.0 (opposite). This gives a similarity range of [-1.0, 1.0], where:

• 1.0 = identical vectors
• 0.0 = orthogonal vectors
• -1.0 = opposite vectors

In practice, experience embeddings from transformer models (e.g., all-MiniLM-L6-v2) produce non-negative values, so similarity is typically in [0.0, 1.0].

Example

let results = db.search_similar(collective_id, &query_embedding, 10)?;
for result in &results {
    println!(
        "similarity={:.3}: {}",
        result.similarity, result.experience.content
    );
}

Fields

experience: Experience

The full experience record.

similarity: f32

Similarity score (1.0 - cosine_distance).

Higher is more similar. Typically in [0.0, 1.0] for transformer embeddings. Theoretical range is [-1.0, 1.0].

Trait Implementations

impl Clone for SearchResult

fn clone(&self) -> SearchResult

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for SearchResult

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

Formats the value using the given formatter.