INNER CODE UNIT · Swift

distance

ZachNagengast/similarity-search-kit · Sources/SimilaritySearchKit/Core/Embeddings/EmbeddingProtocols.swift:55

    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.
    ///   - overlapSize: The number of overlapping tokens between consecutive chunks.
    /// - Returns: A tuple containing an array of chunked text and an optional array of token ids.
    func split(text: String, chunkSize: Int, overlapSize: Int) -> ([String], [[String]]?)
}

public protocol TokenizerProtocol {
    func tokenize(text: String) -> [String]
    func detokenize(tokens: [String]) -> String
}

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…