Load Vector Index

Before using vector index, loading index into memory should be confirmed first. This chapter introduces how to load index.

curl -u shiva:shiva -XPOST 'localhost:8902/hippo/v1/{table}/_load_embedding_index?database_name={database_name}&pretty' -H 'Content-Type: application/json' -d'{
  "index_name" : "ivf_flat_index",
  "wait_for_completion" : true,
  "timeout" : "2m"
}';

Result:

{
  "job_id" : "b0dc39c6023041228a5e2888174f6396",
  "job_status" : "SHIVA_JOB_SUCCESS",
  "embedding_number" : 100,
  "task_results" : [
    {
      "id" : "ee4db1d2c5ee455db85db072b90b5e4a",
      "status" : "TASK_SUCCESS",
      "server" : "172.29.40.26:27861",
      "embedding_number" : 100,
      "execute_time" : 0.014
    }
  ]
}

Parameter description:

The parameters used in index release are similar to the ones used in index activation. After release is done, the number of vectors released will be returned and the whole job will not have negative impact on write operations.