Vector Search

After vector is activated, users can perform vector search. The example is shown below:

curl -u shiva:shiva -XGET 'localhost:8902/hippo/v1/{table}/_search?pretty' -H 'Content-Type: application/json' -d'{  
"output_fields": ["book_id"],  
"search_params": {  
"anns_field": "book_intro",  
"topk": 2,  
"params": {  
"ef_search": 10  
},  
"embedding_index": "sparse_index"  
},  
"sparse_vectors": [ ["1:1", "1:1"], ["2:1", "3:1"] ],  
"round_decimal": 2,  
"only_explain" : false  
}';  

Result:

{  
  "num_queries" : 2,  
  "top_k" : 2,  
  "results" : [  
    {  
      "query" : 0,  
      "fields_data" : [  
        {  
          "field_name" : "book_id",  
          "field_values" : [  
            100,  
            99  
          ]  
        }  
      ],  
      "scores" : [  
        100.0,  
        99.0  
      ]  
    },  
    {  
      "query" : 1,  
      "fields_data" : [  
        {  
          "field_name" : "book_id",  
          "field_values" : [  
            3,  
            2  
          ]  
        }  
      ],  
      "scores" : [  
        1.0,  
        1.0  
      ]  
    }  
  ]  
}