Function common_embd_normalize

smallthinker/common/common.cpp:1341–1375

//

void common_embd_normalize(const float * inp, float * out, int n, int embd_norm) {
    double sum = 0.0;

    switch (embd_norm) {
        case -1: // no normalisation
            sum = 1.0;
            break;
        case 0: // max absolute
            for (int i = 0; i < n; i++) {
                if (sum < std::abs(inp[i])) {
                    sum = std::abs(inp[i]);
                }
            }
            sum /= 32760.0; // make an int16 range
            break;
        case 2: // euclidean
            for (int i = 0; i < n; i++) {
                sum += inp[i] * inp[i];
            }
            sum = std::sqrt(sum);
            break;
        default: // p-norm (euclidean is p-norm p=2)
            for (int i = 0; i < n; i++) {
                sum += std::pow(std::abs(inp[i]), embd_norm);
            }
            sum = std::pow(sum, 1.0 / embd_norm);
            break;
    }

    const float norm = sum > 0.0 ? 1.0 / sum : 0.0f;

    for (int i = 0; i < n; i++) {
        out[i] = inp[i] * norm;
    }
}

float common_embd_similarity_cos(const float * embd1, const float * embd2, int n){
    double sum  = 0.0;