文本信息相似性检索

// link database
Database db = client.database("db-test");
// link collection
Collection collection = db.collection("book-emb");
// search by id

SearchByEmbeddingItemsParam searchByEmbeddingItemsParam = SearchByEmbeddingItemsParam.newBuilder()
        .withEmbeddingItems(Arrays.asList("天下大势，分久必合")) 
        // 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))
        // 设置标量字段的 Filter 表达式，过滤所需查询的文档
        .withRetrieveVector(false)
         // 指定 Top K 的 K 值        
        .withLimit(5)
        // 使用 filter 过滤数据                
        .withFilter(new Filter("bookName=\\"三国演义\\"")) 
        // 指定返回的 fields                
        .withOutputFields(Arrays.asList("id", "bookName"))       
        .build();
List<List<Document>> siDocs = collection.searchByEmbeddingItems(searchByEmbeddingItemsParam);
int i = 0;
for (List<Document> docs : siDocs) {
    System.out.println("\\tres: " + i++);
    for (Document doc : docs) {    
        System.out.println(doc.toString());    
    }
}


res: 0
res: {"id":"0004","score":0.7809984683990479,"bookName":"三国演义"}
res: {"id":"0005","score":0.7298625707626343,"bookName":"三国演义"}
res: {"id":"0003","score":0.7266470193862915,"bookName":"三国演义"}