Change Description

The Kunpeng Blazing-fast embedding similarity search thruster (KBest) is an efficient, Huawei-developed graph search algorithm. It optimizes the performance and precision of the nearest neighbor search by using methods such as quantization and vector instructions, delivering search capabilities equivalent to the open source Faiss HNSW algorithm. Through the integration of KBest into the Milvus vector database, a more efficient search algorithm is ready for use on the Kunpeng server.

V1.1.0 further optimizes the KBest algorithm and adds the build_index_type, graph_opt_iter, reorder, adding_pref, patience, and level parameters.