jenkins分布式构建

1、http请求方式

如果elasticsearch服务设置账号密码，则在请求的header中添加 Basic Auth 认证

1.1、余弦相似

请求方式：Post

请求地址：/index_name/_search

请求body：json格式

{
 "size": 10, //返回条数
 "min_score": 0.8,  // 设置最低相似分值
 "_source": ["file_name", "length", "_es_doc_type"],  // 只返回指定字段
  "query": {
    "script_score": {
      "query": {
        "match_all": {}
      },
      "script": {
	    // _img_vector 为设置的向量索引字段  
        "source": "cosineSimilarity(params.query_vector, '_img_vector') + 0.0",
        "params": {
          "query_vector": [-1,1,-0.07559559,-0.007800484,0.11229578,0.064164124,....]
        }
      }
    }
  }
}

主要参数说明：

返回结果如下：

{
	"took": 3,
	"timed_out": false,
	"_shards": {
		"total": 1,
		"successful": 1,
		"skipped": 0,
		"failed": 0
	},
	"hits": {
		"total": {
			"value": 1,
			"relation": "eq"
		},
		"max_score": 0.9014968,
		"hits": [
			{
				"_index": "vedms",
				"_type": "_doc",
				"_id": "04a40e806be82e87f3c3a2f3877225bd.jpg",
				"_score": 0.9014968,
				"_source": {
					"file_name": "04a40e806be82e87f3c3a2f3877225bd.jpg",
					"_es_doc_type": "IMAGE",
					"length": 89690
				}
			}
		]
	}
}

需要确保传入的query_vector 长度一致性，前面的章节中以设定1024长度。

否则会出现如下错误：

1.2、点积相似

{
 "size": 10, //返回条数
 "_source": ["file_name", "length", "_es_doc_type"],  // 只返回指定字段
  "query": {
    "script_score": {
      "query": {
        "match_all": {}
      },
      "script": {
	    // _img_vector 为设置的向量索引字段  
        "source": "dotProduct(params.query_vector, '_img_vector') + 0.0",
        "params": {
          "query_vector": [-1,1,-0.07559559,-0.007800484,0.11229578,0.064164124,....]
        }
      }
    }
  }
}

返回结果如下，注意 此时 max_score = 8.157833 ，不再是余弦相似的【0-1】

不在适用使用min_score 参数条件

{
	"took": 14,
	"timed_out": false,
	"_shards": {
		"total": 1,
		"successful": 1,
		"skipped": 0,
		"failed": 0
	},
	"hits": {
		"total": {
			"value": 51,
			"relation": "eq"
		},
		"max_score": 8.157833,
		"hits": [
			{
				"_index": "vedms",
				"_type": "_doc",
				"_id": "04a40e806be82e87f3c3a2f3877225bd.jpg",
				"_score": 8.157833,
				"_source": {
					"file_name": "04a40e806be82e87f3c3a2f3877225bd.jpg",
					"_es_doc_type": "IMAGE",
					"length": 89690
				}
			},
......

2、Java调用脚本

SearchRequest  不允许在script设置 _source 属性内容，所以干脆将from、size、score一并拿出，只保留vector数据

_img_vector为前面定义的向量索引字段

public List<Map<String, Object>> search(EsVectorSearchReq req) {
        float[] vector = getImgFeature(req);
        if (null == vector || vector.length == 0) {
            return Collections.emptyList();
        }
        String queryJson = String.format(VECTOR_FORMAT, vectorToJson(vector));
        log.debug("向量检索入参条件={}", queryJson);
        Reader input = new StringReader(queryJson);
        // 使用查询 DSL 进行搜索
        SearchRequest searchRequest = new SearchRequest.Builder()
                .index(req.getIndexLib())
                .from(req.getFrom())
                .size(req.getSize())
                .minScore(req.getScore())
                .source(SourceConfig.of(src -> src
                        .filter(SourceFilter.of(i -> i.includes(req.getColumns())))))
                .withJson(input)
                .build();

        // 执行查询
        List<Map<String, Object>> result = new ArrayList<>();
        try {
            SearchResponse<Map> searchResponse = esClient.search(searchRequest, Map.class);
            // 输出结果
            for (Hit<Map> hit : searchResponse.hits().hits()) {
                result.add(hit.source());
            }
            log.info("成功查询{}条", result.size());
        } catch (IOException e) {
            e.printStackTrace();
        }
        return result;
    }

private String vectorToJson(float[] vector) {
        StringBuilder sb = new StringBuilder("[");
        for (int i = 0; i < vector.length; i++) {
            sb.append(vector[i]);
            if (i < vector.length - 1) {
                sb.append(",");
            }
        }
        sb.append("]");
        return sb.toString();
    }

private static final String VECTOR_FORMAT = "{\n" +
            "  \"query\": {\n" +
            "    \"script_score\": {\n" +
            "      \"query\": {\n" +
            "        \"match_all\": {}\n" +
            "      },\n" +
            "      \"script\": {\n" +
            "        \"source\": \"cosineSimilarity(params.query_vector, 'img_vector') + 0.0\",\n" +
            "        \"params\": {\n" +
            "          \"query_vector\": %s\n" +
            "        }\n" +
            "      }\n" +
            "    }\n" +
            "  }\n" +
            "}";

传入参数格式如下：

{
  "query": {
    "script_score": {
      "query": {
        "match_all": {}
      },
      "script": {
        "source": "cosineSimilarity(params.query_vector, '_img_vector') + 0.0",
        "params": {
          "query_vector": [-0.033....]
        }
      }
    }
  }
}

返回结果如下：