INNER CODE UNIT · Swift

findNearest

ZachNagengast/similarity-search-kit · Sources/SimilaritySearchKit/Core/Embeddings/EmbeddingProtocols.swift:46

    func findNearest(for queryEmbedding: [Float], in neighborEmbeddings: [[Float]], resultsCount: Int) -> [(Float, Int)]

    /// Calculate the distance between two embedding vectors.
    ///
    /// - Parameters:
    ///   - firstEmbedding: A `[Float]` array representing the first embedding vector.
    ///   - secondEmbedding: A `[Float]` array representing the second embedding vector.
    ///
    /// - Returns: A `Float` value representing the distance between the two input embedding vectors. Depending on the similarity metric implementation, the distance can represent different notions of similarity or dissimilarity.
    func distance(between firstEmbedding: [Float], and secondEmbedding: [Float]) -> Float
}

public protocol TextSplitterProtocol {
    /// Splits the input text into a tuple of chunks and optionally token ids.
    ///
    /// - Parameters:
    ///   - text: The input text to be chunked.
    ///   - chunkSize: The number of tokens per chunk.

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…