写入向量数据并检索

import com.tencentcloudapi.client.VectorDBClient;
import com.tencentcloudapi.model.*;

package main
?
import (
    "context"
    "log"
    "time"
?
    "github.com/tencent/vectordatabase-sdk-go/tcvectordb"
)

public class VectorDBExample {
    public static void main(String[] args) {
        // 创建VectorDB Client
        ConnectParam connectParam = ConnectParam.newBuilder()
                .withUrl("http://10.0.X.X:80")
                .withUsername("root")
                .withKey("eC4bLRy2va******************************")
                .withTimeout(30)
                .build();
        VectorDBClient client = new VectorDBClient(connectParam, ReadConsistencyEnum.EVENTUAL_CONSISTENCY);
    } 
}

func main() {
    var defaultOption = &tcvectordb.ClientOption{
        Timeout:            time.Second * 5,
        MaxIdldConnPerHost: 2,
        IdleConnTimeout:    time.Minute,
        ReadConsistency:    tcvectordb.EventualConsistency,
    }
    client, err := tcvectordb.NewClient("http://10.0.X.X:80", "root", "eC4bLRy2va******************************", defaultOption)
    if err != nil {
        panic(err)
    }
}

var (
    ctx                 = context.Background()
    database            = "db-test"
)
db, _ := client.CreateDatabase(ctx, database)

Document doc1 = Document.newBuilder()
        .withId("0001")
        .withVector(Arrays.asList(0.2123, 0.23, 0.213))
        .addDocField(new DocField("bookName", "三国演义"))
        .addDocField(new DocField("author", "吴承恩"))
        .addDocField(new DocField("page", 21))
        .build();
Document doc2 = Document.newBuilder()        
        .withId("0002")
        .withVector(Arrays.asList(0.2123, 0.22, 0.213))
        .addDocField(new DocField("bookName", "西游记"))
        .addDocField(new DocField("author", "吴承恩"))
        .addDocField(new DocField("page", 22))
        .build();
Document doc3 = Document.newBuilder()        
        .withId("0003")
        .withVector(Arrays.asList(0.2123, 0.21, 0.213))
        .addDocField(new DocField("bookName", "红楼梦"))
        .addDocField(new DocField("author", "曹雪芹"))
        .addDocField(new DocField("page", 23))
        .build();
InsertParam insertParam = InsertParam.newBuilder()
        .addDocument(doc1)        
        .addDocument(doc2)        
        .addDocument(doc3)     
        .build();
collection.upsert(insertParam);

result, err := coll.Upsert(ctx, []tcvectordb.Document{
    {
        Id:     "0001",
        Vector: []float32{0.2123, 0.23, 0.213},
        Fields: map[string]tcvectordb.Field{
            "bookName": {Val: "三国演义"},
            "author":   {Val: "罗贯中"},
            "page":     {Val: 21},
        },
    },
    {
        Id:     "0002",
        Vector: []float32{0.2123, 0.22, 0.213},
        Fields: map[string]tcvectordb.Field{
            "bookName": {Val: "西游记"},
            "author":   {Val: "吴承恩"},
            "page":     {Val: 22},
        },
    },
    {
        Id:     "0003",
        Vector: []float32{0.2123, 0.21, 0.213},
        Fields: map[string]tcvectordb.Field{
            "bookName": {Val: "红楼梦"},
            "author":   {Val: "曹雪芹"},
            "page":     {Val: 23},
        },
    },
}, &tcvectordb.UpsertDocumentParams{})
?
log.Printf("upsert result: %+v", result)

curl -i -X POST \\
  -H 'Content-Type: application/json' \\
  -H 'Authorization: Bearer account=root&api_key=A5VOgsMpGWJhUI0WmUbY********************' \\
  http://10.0.X.X:80/document/upsert \\
  -d '{
    "database": "db-test",
    "collection": "book-vector",
    "documents": [
        {
            "id": "0001",
            "vector": [
                0.2123,
                0.23,
                0.213
            ],
            "author": "罗贯中",
            "bookName": "三国演义",
            "page": 21
        },
        {
            "id": "0002",
            "vector": [
                0.2123,
                0.22,
                0.213
            ],
            "author": "吴承恩",
            "bookName": "西游记",
            "page": 22
        },
        {
            "id": "0003",
            "vector": [
                0.2123,
                0.21,
                0.213
            ],
            "author": "曹雪芹",
            "bookName": "红楼梦",
            "page": 23
        }
    ]
}'

{
    "code": 0,
    "msg": "operation success",
    "affectedCount": 3
}

SearchByVectorParam searchByVectorParam = SearchByVectorParam.newBuilder()
         // Vectors 指定了需检索的向量数据
        .withVectors(Arrays.asList(Arrays.asList(0.3123, 0.43, 0.213), Arrays.asList(0.315, 0.4, 0.216), Arrays.asList(0.40, 0.38, 0.26)))             
        // 若使用 HNSW 索引，则需要指定参数 ef，ef 越大，召回率越高，但也会影响检索速度       
        .withParams(new HNSWSearchParams(200))
         // 指定返回的最相似的 Top K 的 K 值        
        .withLimit(3)
        // 设置标量字段的 Filter 表达式，过滤所需查询的文档                
        .withFilter(new Filter(Filter.in("bookName", Arrays.asList("三国演义","西游记")))) 
        .build();
// 输出相似度检索结果        
List<List<Document>> svDocs = collection.search(searchByVectorParam);
int i = 0;
for (List<Document> docs : svDocs) {
    System.out.println("\\tres: " + i++);
    for (Document doc : docs) {    
        System.out.println("\\tres: " + doc.toString());    
    }
}