具有余弦相似度运行时错误的弹性搜索查询？

如何解决具有余弦相似度运行时错误的弹性搜索查询？

创建了数据类型为dense_vector => dims: 512 的索引并将json格式数据上传到elasticsearch中，根据查询向量[4,3.4,-0.2]得到具有余弦相似度的搜索查询。

参考文章https://medium.com/version-1/vector-based-semantic-search-using-elasticsearch-48d7167b38f5

创建索引：

put jsonsample2/
{
    "settings": {"number_of_shards": 2,"number_of_replicas": 1},"mappings": 
    {
        "dynamic": "true","_source": {"enabled": "true"},"properties": 
        {
            "Document_name": {"type": "text"},"Doc_vector": {"type": "dense_vector","dims": 512}
        }
    }
}

基于查询向量的余弦相似度 搜索查询：

GET jsonsample2/_search
{
  "query": {
    "script_score": {
      "query" : {
        "match_all": {}
        },"script": 
      {
        "source": "cosinesimilarity(params.query_vector,'Doc_vector')","params": 
        {
          "query_vector": [4,-0.2]  
        }
      }
    }
    }
}

余弦相似度搜索运行时错误。 运行时错误

    {
      "took" : 1,"timed_out" : false,"_shards" : {
        "total" : 2,"successful" : 1,"skipped" : 0,"Failed" : 1,"failures" : [
          {
            "shard" : 0,"index" : "jsonsample2","node" : "e9WAytp6Si65x_YDRuLQcg","reason" : {
              "type" : "script_exception","reason" : "runtime error","script_stack" : [                   "org.elasticsearch.xpack.vectors.query.scoreScriptUtils$DenseVectorFunction.getEncodedVector(scoreScriptUtils.java:100)","org.elasticsearch.xpack.vectors.query.scoreScriptUtils$Cosinesimilarity.cosinesimilarity(scoreScriptUtils.java:179)","cosinesimilarity(params.query_vector,"                                      ^---- HERE"

              ],"script" : "cosinesimilarity(params.query_vector,"lang" : "painless","position" : {
                "offset" : 38,"start" : 0,"end" : 51
              },"caused_by" : {
                "type" : "illegal_argument_exception","reason" : "A document doesn't have a value for a vector field!"
              }
            }
          }
        ]
      },"hits" : {
        "total" : {
          "value" : 0,"relation" : "eq"
        },"max_score" : null,"hits" : [ ]
      }
    }

解决方法

问题描述如下：

"reason" : "文档没有向量字段的值！"

要检查文档是否有缺失值，您可以使用 doc['field'].size() == 0

你的脚本应该是这样的：

"source": "doc['Doc_vector'].size() == 0 ? 0 : cosineSimilarity(params.query_vector,'Doc_vector')"