Function main

sample/python/hnsw_rabitq_indexing.py:19–53

(args=None)

def main(args=None) -> None:
    # 1. Load data
    data = read_fvecs(args.data_file)
    print(f"Data shape: {data.shape}")

    # 2. Cluster with FAISS
    centroids, cluster_ids = cluster_data(data, args.num_clusters, args.metric, args.num_threads)
    print(f"Centroids: {centroids.shape}, cluster_ids: {cluster_ids.shape}")

    # 3. Build HNSW index
    n, dim = data.shape
    print(f"\nBuilding HNSW index: n={n}, dim={dim}, M={args.degree}, "
          f"ef={args.ef_construction}, bits={args.total_bits}, metric={args.metric}")

    idx = HnswIndex(
        dim=dim,
        max_elements=n,
        M=args.degree,
        ef_construction=args.ef_construction,
        nbits=args.total_bits,
        metric=args.metric,
    )

    t0 = time()
    idx.build(
        data,
        centroids,
        cluster_ids,
        num_threads=args.num_threads,
        fast_quantization=args.faster_quant,
    )
    print(f"Indexing time: {time() - t0:.2f}s")

    idx.save(args.index_file)
    print(f"Index saved → {args.index_file}")


if __name__ == "__main__":