以图搜图浅述（二）

如何把N维向量存储到elasticsearch中，以及如何搜索

用到了开源项目https://github.com/lior-k/fast-elasticsearch-vector-scoring

版本（5.6.0）

第一步，建索引+映射

PUT http://127.0.0.1:9200/my_index

{"mappings":{

    "my_type":{

        "properties":{

            "embedding_vector":{

                "type": "binary",

                "doc_values": true

            }

        }

    }

}}

第二步，插入数据

PUT http://127.0.0.1:9200/my_index/my_type/1

{

       "id": 1,

       "embedding_vector": "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"

}

PUT http://127.0.0.1:9200/my_index/my_type/2

{

       "id": 2,

       "embedding_vector": "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"

}

查询

GET http://127.0.0.1:9200/my_index/_search

{

  "query": {

    "function_score": {

      "boost_mode": "replace",

      "script_score": {

        "script": {

          "inline": "binary_vector_score",

          "lang": "knn",

          "params": {

            "cosine": true,

            "field": "embedding_vector",

            "vector": [

               -0.09217305481433868, 0.010635560378432274, -0.02878434956073761, 0.06988169997930527, 0.1273992955684662, -0.023723633959889412, 0.05490724742412567, -0.12124507874250412, -0.023694118484854698, 0.014595639891922474, 0.1471538096666336, 0.044936809688806534, -0.02795785665512085, -0.05665992572903633, -0.2441125512123108, 0.2755320072174072, 0.11451690644025803, 0.20242854952812195, -0.1387604922056198, 0.05219579488039017, 0.1145530641078949, 0.09967200458049774, 0.2161576747894287, 0.06157230958342552, 0.10350126028060913, 0.20387393236160278, 0.1367097795009613, 0.02070528082549572, 0.19238869845867157, 0.059613026678562164, 0.014012521132826805, 0.16701748967170715, 0.04985826835036278, -0.10990987718105316, -0.12032567709684372, -0.1450948715209961, 0.13585780560970306, 0.037511035799980164, 0.04251480475068092, 0.10693439096212387, -0.08861573040485382, -0.07457160204648972, 0.0549330934882164, 0.19136285781860352, 0.03346432000398636, -0.03652812913060188, -0.1902569830417633, 0.03250952064990997, -0.3061246871948242, 0.05219300463795662, -0.07879918068647385, 0.1403723508119583, -0.08893408626317978, -0.24330253899097443, -0.07105310261249542, -0.18161986768245697, 0.15501035749912262, -0.216160386800766, -0.06377710402011871, -0.07671763002872467, 0.05360138416290283, -0.052845533937215805, -0.02905619889497757, 0.08279753476381302

             ]

          }

        }

      }

    }

  },

"size":1

}

可以查询到一条最相似的结果。

分析过binary_vector_score 脚本的源码，属于全表扫描。