OpenSearch k-NN 向量检索索引与查询实战

OpenSearch k-NN 向量检索索引与查询实战索引与映射PUT /vectors

{

"settings": { "index.knn": true },

"mappings": {

"properties": {

"title": { "type": "text" },

"vec": { "type": "knn_vector", "dimension": 768 }

}

}

}

插入POST /vectors/_doc

{ "title": "doc1", "vec": [0.12, 0.03, ...] }

查询（k-NN）POST /vectors/_search

{

"knn": {

"field": "vec",

"query_vector": [0.11, 0.02, ...],

"k": 10,

"num_candidates": 100

}

}

总结启用 `index.knn` 并使用 `knn_vector` 映射即可进行向量检索，`num_candidates` 影响召回与性能。