【ElasticSearch】ES 5.6.15 向量插件支持

参考 :
https://github.com/lior-k/fast-elasticsearch-vector-scoring

1. 下载插件

2. 安装插件
   插件目录：
   elasticsearch/plugins,
   安装后的目录如下

    plugins
    └── vector
        ├── elasticsearch-binary-vector-scoring-5.6.9.jar
        └── plugin-descriptor.properties
   

   修改 plugin-descriptor.properties 中的 elasticsearch.version 为 5.6.15（因为这里使用的是5.6.15版本ES），安装完成后重启ES。

3. 构建测试索引

   PUT /vector_test
   {
     "settings": {
       "index": {
         "number_of_shards": 3,
         "number_of_replicas": 0
       }
     },
     "mappings": {
       "resume": {
         "dynamic": "strict",
         "properties": {
           "file_hash": {
             "type": "keyword"
           },
           "embedding_vector": {
             "type": "binary",
             "doc_values": true
           },
           "doc": {
             "type": "text"
           }
         }
       }
     }
   }
   

4. 构建测试数据

使用如下方法生成向量base64字符串

import base64
import numpy as np
 
dfloat32 = np.dtype('>f4')
 
def decode_float_list(base64_string):
    bytes = base64.b64decode(base64_string)
    return np.frombuffer(bytes, dtype=dfloat32).tolist()
 
def encode_array(arr):
    base64_str = base64.b64encode(np.array(arr).astype(dfloat32)).decode("utf-8")
    return base64_str

print(encode_array([0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9,1.0]))
print(encode_array([0.001,0.002,0.003,0.004,0.005,0.006,0.007,0.008,0.009,0.010]))

将上述得到的结果放到下面内容(embedding_vector)中,这里 embedding_vector 要求传入上述方式base64生成的字符串

PUT /vector_test/resume/1
{
  "file_hash": "hash1",
  "embedding_vector": "PczMzT5MzM0+mZmaPszMzT8AAAA/GZmaPzMzMz9MzM0/ZmZmP4AAAA==",
  "doc": "This is the content of the first document."
}

PUT /vector_test/resume/2
{
  "file_hash": "hash2",
  "embedding_vector": "OoMSbzsDEm87RJumO4MSbzuj1wo7xJumO+VgQjwDEm88E3S8PCPXCg==",
  "doc": "This is the content of the second document."
}

5. 查询测试

   POST /vector_test/resume/_search
   {
     "query": {
       "function_score": {
         "boost_mode": "replace",
         "script_score": {
           "script": {
             "source": "binary_vector_score",
             "lang": "knn",
             "params": {
               "cosine": true,
               "field": "embedding_vector",
               "vector": [
                 1.0,
                 0.8,
                 0.2223,
                 0.7,
                 0.6,
                 0.5,
                 0.4,
                 0.3,
                 0.2,
                 0.1
               ]
             }
           }
         }
       }
     },
     "size": 2,
     "_source": [
       "file_hash"
     ]
   }
   

   查询结果

   {
     "took": 1,
     "timed_out": false,
     "_shards": {
       "total": 5,
       "successful": 5,
       "skipped": 0,
       "failed": 0
     },
     "hits": {
       "total": 4,
       "max_score": 0.998783,
       "hits": [
         {
           "_index": "vector_test",
           "_type": "resume",
           "_id": "4",
           "_score": 0.998783,
           "_source": {
             "file_hash": "hash4"
           }
         },
         {
           "_index": "vector_test",
           "_type": "resume",
           "_id": "1",
           "_score": 0.5818508,
           "_source": {
             "file_hash": "hash1"
           }
         }
       ]
     }
   }
   

原文地址：https://blog.csdn.net/qq_20623849/article/details/140326854

免责声明：本站文章内容转载自网络资源，如本站内容侵犯了原著者的合法权益，可联系本站删除。更多内容请关注自学内容网（zxcms.com）！