__init__.py 文件源码

def closestNeighbor(query, embedding_array, normed=False, top_k=1):
    '''Gets the index of the closest neighbor of embedding_array
    to the query point.  Distance metric is cosine.

    SLOW. DO NOT USE THIS FOR RAPID COMPUTATION.
    '''
    embedding_array = numpy.array(embedding_array)
    if not normed:
        embedding_array = numpy.array([
            (embedding_array[i] / numpy.linalg.norm(embedding_array[i]))
                for i in range(embedding_array.shape[0])
        ])

    ## assuming embeddings are unit-normed by this point;
    ## norm(query) is a constant factor, so we can ignore it
    dists = numpy.array([
        numpy.dot(query, embedding_array[i])
            for i in range(embedding_array.shape[0])
    ])
    sorted_ixes = numpy.argsort(-1 * dists)
    return sorted_ixes[:top_k]