Elasticsearch（实践一）相似度方法L1、L2 、cos-Toy模板网

这篇具有很好参考价值的文章主要介绍了Elasticsearch（实践一）相似度方法L1、L2 、cos。希望对大家有所帮助。如果存在错误或未考虑完全的地方，请大家不吝赐教，您也可以点击"举报违法"按钮提交疑问。

在文本使用三维向量的相似度时，对三种相似度的对比。当前基于已经搭建好的Elasticsearch、Kibana。

1、创建索引库

PUT my-index-000002
{
  "mappings": {
    "properties": {
      "my_dense_vector": {
        "type": "dense_vector",
        "dims": 3
      },
      "status" : {
        "type" : "keyword"
      }
    }
  }
}

创建成功：

{
  "acknowledged": true,
  "shards_acknowledged": true,
  "index": "my-index-000002"
}

2、放入数据

PUT my-index-000002/_doc/1
{
  "my_dense_vector": [1, 0,0],
  "status" : "published"
}

PUT my-index-000002/_doc/2
{
  "my_dense_vector": [0,1,0],
  "status" : "published"
}

PUT my-index-000002/_doc/3
{
  "my_dense_vector": [0,0,1],
  "status" : "published"
}

返回结果类似如下

{
  "_index": "my-index-000002",
  "_id": "3",
  "_version": 1,
  "result": "created",
  "_shards": {
    "total": 2,
    "successful": 1,
    "failed": 0
  },
  "_seq_no": 2,
  "_primary_term": 1
}

3、查看所有数据

GET my-index-000002/_search

结果如下：

{
  "took": 2,
  "timed_out": false,
  "_shards": {
    "total": 1,
    "successful": 1,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": {
      "value": 3,
      "relation": "eq"
    },
    "max_score": 1,
    "hits": [
      {
        "_index": "my-index-000002",
        "_id": "1",
        "_score": 1,
        "_source": {
          "my_dense_vector": [
            1,
            0,
            0
          ],
          "status": "published"
        }
      },
      {
        "_index": "my-index-000002",
        "_id": "2",
        "_score": 1,
        "_source": {
          "my_dense_vector": [
            0,
            1,
            0
          ],
          "status": "published"
        }
      },
      {
        "_index": "my-index-000002",
        "_id": "3",
        "_score": 1,
        "_source": {
          "my_dense_vector": [
            0,
            0,
            1
          ],
          "status": "published"
        }
      }
    ]
  }
}

4、L1方法查询数据

GET my-index-000002/_search
{
  "query": {
    "script_score": {
      "query" : {
        "bool" : {
          "filter" : {
            "term" : {
              "status" : "published"
            }
          }
        }
      },
      "script": {
        "source": "1 / (1 + l1norm(params.queryVector, 'my_dense_vector'))",
        "params": {
          "queryVector": [0, 0, 1]
        }
      }
    }
  }
}

{
  "took": 2,
  "timed_out": false,
  "_shards": {
    "total": 1,
    "successful": 1,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": {
      "value": 3,
      "relation": "eq"
    },
    "max_score": 1,
    "hits": [
      {
        "_index": "my-index-000002",
        "_id": "3",
        "_score": 1,
        "_source": {
          "my_dense_vector": [
            0,
            0,
            1
          ],
          "status": "published"
        }
      },
      {
        "_index": "my-index-000002",
        "_id": "1",
        "_score": 0.33333334,
        "_source": {
          "my_dense_vector": [
            1,
            0,
            0
          ],
          "status": "published"
        }
      },
      {
        "_index": "my-index-000002",
        "_id": "2",
        "_score": 0.33333334,
        "_source": {
          "my_dense_vector": [
            0,
            1,
            0
          ],
          "status": "published"
        }
      }
    ]
  }
}

结果中，id1和id2得分相同，但在文本向量空间中他们不同。

5、使用l2查询

GET my-index-000002/_search
{
  "query": {
    "script_score": {
      "query" : {
        "bool" : {
          "filter" : {
            "term" : {
              "status" : "published"
            }
          }
        }
      },
      "script": {
        "source": "1 / (1 + l2norm(params.queryVector, 'my_dense_vector'))",
        "params": {
          "queryVector": [0, 0, 1]
        }
      }
    }
  }
}

{
  "took": 2,
  "timed_out": false,
  "_shards": {
    "total": 1,
    "successful": 1,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": {
      "value": 3,
      "relation": "eq"
    },
    "max_score": 1,
    "hits": [
      {
        "_index": "my-index-000002",
        "_id": "3",
        "_score": 1,
        "_source": {
          "my_dense_vector": [
            0,
            0,
            1
          ],
          "status": "published"
        }
      },
      {
        "_index": "my-index-000002",
        "_id": "1",
        "_score": 0.41421357,
        "_source": {
          "my_dense_vector": [
            1,
            0,
            0
          ],
          "status": "published"
        }
      },
      {
        "_index": "my-index-000002",
        "_id": "2",
        "_score": 0.41421357,
        "_source": {
          "my_dense_vector": [
            0,
            1,
            0
          ],
          "status": "published"
        }
      }
    ]
  }
}

同样出现相同情况，l1和l2计算文本的距离有相同得分

6、cos 查询

GET my-index-000002/_search
{
  "query": {
    "script_score": {
      "query" : {
        "bool" : {
          "filter" : {
            "term" : {
              "status" : "published"       
            }
          }
        }
      },
      "script": {
        "source": "cosineSimilarity(params.query_vector, 'my_dense_vector') + 1.0",    
        "params": {
          "query_vector": [0, 0, 1]      
        }
      }
    }
  }
}

结果

{
  "took": 1,
  "timed_out": false,
  "_shards": {
    "total": 1,
    "successful": 1,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": {
      "value": 3,
      "relation": "eq"
    },
    "max_score": 2,
    "hits": [
      {
        "_index": "my-index-000002",
        "_id": "3",
        "_score": 2,
        "_source": {
          "my_dense_vector": [
            0,
            0,
            1
          ],
          "status": "published"
        }
      },
      {
        "_index": "my-index-000002",
        "_id": "1",
        "_score": 1,
        "_source": {
          "my_dense_vector": [
            1,
            0,
            0
          ],
          "status": "published"
        }
      },
      {
        "_index": "my-index-000002",
        "_id": "2",
        "_score": 1,
        "_source": {
          "my_dense_vector": [
            0,
            1,
            0
          ],
          "status": "published"
        }
      }
    ]
  }
}

三种方法都会产生不同向量的相同分数情况

GET my-index-000002/_search
{
  "query": {
    "script_score": {
      "query" : {
        "bool" : {
          "filter" : {
            "term" : {
              "status" : "published"       
            }
          }
        }
      },
      "script": {
        "source": "cosineSimilarity(params.query_vector, 'my_dense_vector') + 1.0",    
        "params": {
          "query_vector": [0, 0, 100]      
        }
      }
    }
  }
}

结果：

{
  "took": 2,
  "timed_out": false,
  "_shards": {
    "total": 1,
    "successful": 1,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": {
      "value": 3,
      "relation": "eq"
    },
    "max_score": 2,
    "hits": [
      {
        "_index": "my-index-000002",
        "_id": "3",
        "_score": 2,
        "_source": {
          "my_dense_vector": [
            0,
            0,
            1
          ],
          "status": "published"
        }
      },
      {
        "_index": "my-index-000002",
        "_id": "1",
        "_score": 1,
        "_source": {
          "my_dense_vector": [
            1,
            0,
            0
          ],
          "status": "published"
        }
      },
      {
        "_index": "my-index-000002",
        "_id": "2",
        "_score": 1,
        "_source": {
          "my_dense_vector": [
            0,
            1,
            0
          ],
          "status": "published"
        }
      }
    ]
  }
}

三种方法都会存在不同空间位置，得到向量距离可能相同的情况文章来源地址https://www.toymoban.com/news/detail-784637.html

到了这里，关于Elasticsearch（实践一）相似度方法L1、L2 、cos的文章就介绍完了。如果您还想了解更多内容，请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章，希望大家以后多多支持TOY模板网！