Querying Vectors

Standard Query

Standard vector query syntax is provided for vector fields with vector indexes. The following command will return n (specified by size/topk) data records that are most close to the query vector.

POST my_index/_search
{
  "size":2,
  "_source": false, 
  "query": {
    "vector": {
      "my_vector": {
        "vector": [1, 1],
        "topk":2
      }
    }
  }
}

Compound Query

Vector search can be used together with other Elasticsearch subqueries, such as Boolean query and post-filtering, for compound query.

In the following two examples, top 10 (topk) results closest to the query vector are queried first. filter retains only the results whose my_label field is red.

• Example of a Boolean query

  POST my_index/_search
  {
    "size": 10,
    "query": {
      "bool": {
        "must": {
          "vector": {
            "my_vector": {
              "vector": [1, 2],
              "topk": 10
            }
          }
        },
        "filter": {
          "term": { "my_label": "red" }
        }
      }
    }
  }

• Example of post-filtering

  GET my_index/_search
  {
    "size": 10,
    "query": {
      "vector": {
        "my_vector": {
          "vector": [1, 2],
          "topk": 10
        }
      }
    },
    "post_filter": {
      "term": { "my_label": "red" }
    }
  }

ScriptScore Query

You can use script_score to perform Nearest Neighbor Search (NSS) on vectors. The query syntax is provided below.

The pre-filtering condition can be any query. script_score traverses only the pre-filtered results, calculates the vector similarity, and sorts and returns the results. The performance of this query depends on the size of the intermediate result set after the pre-filtering. If the pre-filtering condition is set to match_all, brute-force search is performed on all data.

POST my_index/_search 
 { 
   "size":2, 
   "query": { 
   "script_score": { 
       "query": { 
         "match_all": {} 
       }, 
       "script": { 
         "source": "vector_score", 
         "lang": "vector", 
         "params": { 
           "field": "my_vector", 
           "vector": [1.0, 2.0], 
           "metric": "euclidean" 
         } 
       } 
     } 
   } 
 }

Re-Score Query

If the GRAPH_PQ or IVF_GRAPH_PQ index is used, the query results are sorted based on the asymmetric distance calculated by PQ. CSS supports re-scoring and sorting of query results to improve the recall rate.

Assuming that my_index is a PQ index, an example of re-scoring the query results is as follows:

GET my_index/_search 
 { 
   "size": 10, 
   "query": { 
     "vector": { 
       "my_vector": { 
         "vector": [1.0, 2.0], 
         "topk": 100 
       } 
     } 
   }, 
   "rescore": { 
     "window_size": 100, 
     "vector_rescore": { 
       "field": "my_vector", 
       "vector": [1.0, 2.0], 
       "metric": "euclidean" 
     } 
   } 
 }