我正在建立一個(gè) Elasticsearch 集群來搜索與一個(gè) id 關(guān)聯(lián)的向量。例如，鑒于此數(shù)據(jù)：Parent id / Object id / vectorsP1 / BD / 123, 125, 235 ... 10304, 50305 P1 / DF / 125, 235, 240 ... 10305, 10306P1 / ED / 123, 235, 350 ... 10010, 10344... P2 / AB / 125, 535, 740 ... 9315, 10306P2 / VC / 133, 435, 350 ... 3010, 20344P2 / RF / 113, 353, 390 ... 10110, 30344...There are millions of parentshundreds of objects in a parent1000 vectors in an object所以基本上我想索引所有向量給定輸入 P999，通過找到最多的相似對(duì)象來從集群中搜索相似的父對(duì)象。（相似對(duì)象：至少 50 個(gè)向量匹配）這是我期望的示例結(jié)果Input:P999 / HH / xxx, xxx ...P999 / YH / xxx, xxx ...P999 / GJ / xxx, xxx ......Output:[result sorted desc] P20 has 60 similar objectsP4 has 45 similar objectsP501 has 41 similar objects...similar objects: at least 50 vector matches為了實(shí)現(xiàn)這一點(diǎn)，我需要好的架構(gòu)存儲(chǔ)向量的查詢按降序搜索相似對(duì)象列表的查詢我需要這三個(gè)方面的幫助。