![]() ![]() Whether to enable the cache expiration policy. If the off-heap memory usage exceeds its upper limit, the circuit breaker will be triggered. Upper limit of off-heap memory usage of the vector index.įor example, if the overall memory of a host is 128 GB and the heap memory occupies 31 GB, the default upper limit of the off-heap memory usage is 43.65 GB, that is, (128 - 31) x 45%. Whether to enable the circuit breaker for off-heap memory. The plug-in automatically sets the number of fragments based on the vector length. Number of cluster centroids of each fragment. A larger value indicates a higher precision and slower indexing speed. Maximum number of nodes that can be scanned. A larger value indicates a higher precision and slower build speed. Queue size of the neighboring node during HNSW build. Scaling ratio of the upper-layer graph nodes during HNSW build. A larger index results in a slower build and query speed.Ĭropping coefficient during HNSW build. A larger value indicates higher query precision. Number of neighbors of each vector in a graph index. ![]() This algorithm is applicable to scenarios where there are more than 1 billion files in shards and high retrieval performance is required. IVF_GRAPH_PQ: combination of the PQ algorithm with the IVF or HNSW algorithm to further improve the system capacity and reduce the system overhead.You can use this algorithm if you require high performance when searching for data among hundreds of millions of records. The entire space is divided into multiple cluster centroids, which makes search much faster but slightly inaccurate. IVF_GRAPH: combination of IVF and HNSW.The PQ algorithm reduces the storage overhead of original vectors, so that HNSW can easily search for data among hundreds of millions of records. GRAPH_PQ: combination of the HNSW algorithm and the PQ algorithm.This algorithm is mainly used in scenarios where high performance and precision are required and the data records of a single shard is fewer than 10 million. GRAPH: Hierarchical Navigable Small Worlds (HNSW) algorithm for graph indexes.You can use this algorithm if you require high recall accuracy. The algorithm relies on sheer computing power and its recall rate reaches 100%. FLAT: brute-force algorithm that calculates the distance between the target vector and all vectors in sequence.
0 Comments
Leave a Reply. |