隨機抽樣Compatible with Milvus 2.6.x

在處理大規模資料集時，您通常不需要處理所有資料，就能獲得洞察力或測試篩選邏輯。隨機抽樣提供了一個解決方案，讓您可以處理具有統計代表性的資料子集，大幅減少查詢時間和資源消耗。

隨機抽樣在區段層級運作，可確保高效的效能，同時在您的集合資料分佈中維持抽樣的隨機性。

主要用例：

• 資料探索：以最少的資源使用量快速預覽資料集結構與內容

• 開發測試：在全面部署之前，在可管理的資料樣本上測試複雜的篩選邏輯

• 資源最佳化：降低探索性查詢和統計分析的計算成本

語法

filter = "RANDOM_SAMPLE(sampling_factor)"

String filter = "RANDOM_SAMPLE(sampling_factor)"

filter := "RANDOM_SAMPLE(sampling_factor)"

// node

# restful

參數：

• sampling_factor:取樣係數，範圍為 (0，1)，不包括邊界。例如，RANDOM_SAMPLE(0.001) 會選取約 0.1% 的結果。

重要規則：

• 表達式不區分大小寫 (RANDOM_SAMPLE 或random_sample)

• 取樣係數必須在 (0, 1) 的範圍內，不包括邊界

與其他篩選器結合

隨機抽樣運算符號必須使用邏輯AND 與其他篩選表達式結合。結合篩選器時，Milvus 會先套用其他條件，然後在結果集上執行隨機抽樣。

# Correct: Filter first, then sample
filter = 'color == "red" AND RANDOM_SAMPLE(0.001)'
# Processing: Find all red items → Sample 0.1% of those red items

# Incorrect: OR doesn't make logical sense
filter = 'color == "red" OR RANDOM_SAMPLE(0.001)'  # ❌ Invalid logic
# This would mean: "Either red items OR sample everything" - which is meaningless

// Correct: Filter first, then sample
String filter = 'color == "red" AND RANDOM_SAMPLE(0.001)';
// Processing: Find all red items → Sample 0.1% of those red items

// Incorrect: OR doesn't make logical sense
String filter = 'color == "red" OR RANDOM_SAMPLE(0.001)';  // ❌ Invalid logic
// This would mean: "Either red items OR sample everything" - which is meaningless

// Correct: Filter first, then sample
filter := 'color == "red" AND RANDOM_SAMPLE(0.001)'
// Processing: Find all red items → Sample 0.1% of those red items

filter := 'color == "red" OR RANDOM_SAMPLE(0.001)' // ❌ Invalid logic
// This would mean: "Either red items OR sample everything" - which is meaningless

// node

# restful

範例

範例 1：資料探索

快速預覽您的集合結構：

from pymilvus import MilvusClient

client = MilvusClient(uri="http://localhost:19530")

# Sample approximately 1% of the entire collection
result = client.query(
    collection_name="product_catalog",
    filter="RANDOM_SAMPLE(0.01)",
    output_fields=["id", "product_name"],
    limit=10
)

print(f"Sampled {len(result)} products from collection")

import io.milvus.v2.client.*;
import io.milvus.v2.service.vector.request.QueryReq
import io.milvus.v2.service.vector.request.QueryResp

ConnectConfig config = ConnectConfig.builder()
        .uri("http://localhost:19530")
        .build();
MilvusClientV2 client = new MilvusClientV2(config);

QueryReq queryReq = QueryReq.builder()
        .collectionName("product_catalog")
        .filter("RANDOM_SAMPLE(0.01)")
        .outputFields(Arrays.asList("id", "product_name"))
        .limit(10)
        .build();

QueryResp queryResp = client.query(queryReq);

List<QueryResp.QueryResult> results = queryResp.getQueryResults();
for (QueryResp.QueryResult result : results) {
    System.out.println(result.getEntity());
}

import (
    "context"
    "fmt"

    "github.com/milvus-io/milvus/client/v2/entity"
    "github.com/milvus-io/milvus/client/v2/milvusclient"
)

ctx, cancel := context.WithCancel(context.Background())
defer cancel()

milvusAddr := "localhost:19530"
client, err := milvusclient.New(ctx, &milvusclient.ClientConfig{
    Address: milvusAddr,
})
if err != nil {
    fmt.Println(err.Error())
    // handle error
}
defer client.Close(ctx)

resultSet, err := client.Query(ctx, milvusclient.NewQueryOption("product_catalog").
    WithFilter("RANDOM_SAMPLE(0.01)").
    WithOutputFields("id", "product_name"))
if err != nil {
    fmt.Println(err.Error())
    // handle error
}

fmt.Println("id: ", resultSet.GetColumn("id").FieldData().GetScalars())
fmt.Println("product_name: ", resultSet.GetColumn("product_name").FieldData().GetScalars())

// node

# restful

範例 2：結合篩選與隨機抽樣

在可管理的子集中測試篩選邏輯：

# First filter by category and price, then sample 0.5% of results
filter_expression = 'category == "electronics" AND price > 100 AND RANDOM_SAMPLE(0.005)'

result = client.query(
    collection_name="product_catalog",
    filter=filter_expression,
    output_fields=["product_name", "price", "rating"],
    limit=10
)

print(f"Found {len(result)} electronics products in sample")

String filter = "category == \"electronics\" AND price > 100 AND RANDOM_SAMPLE(0.005)";

QueryReq queryReq = QueryReq.builder()
        .collectionName("product_catalog")
        .filter(filter)
        .outputFields(Arrays.asList("product_name", "price", "rating"))
        .limit(10)
        .build();

QueryResp queryResp = client.query(queryReq);

filter := "category == \"electronics\" AND price > 100 AND RANDOM_SAMPLE(0.005)"

resultSet, err := client.Query(ctx, milvusclient.NewQueryOption("product_catalog").
    WithFilter(filter).
    WithOutputFields("product_name", "price", "rating"))
if err != nil {
    fmt.Println(err.Error())
    // handle error
}

// node

# restful

範例 3：快速分析

在篩選過的資料上執行快速統計分析：

# Get insights from ~0.1% of premium customer data
filter_expression = 'customer_tier == "premium" AND region == 'North America' AND RANDOM_SAMPLE(0.001)'

result = client.query(
    collection_name="customer_profiles",
    filter=filter_expression,
    output_fields=["purchase_amount", "satisfaction_score", "last_purchase_date"],
    limit=10
)

# Analyze sample for quick insights
if result:
    average_purchase = sum(r["purchase_amount"] for r in result) / len(result)
    average_satisfaction = sum(r["satisfaction_score"] for r in result) / len(result)
    
    print(f"Sample size: {len(result)}")
    print(f"Average purchase amount: ${average_purchase:.2f}")
    print(f"Average satisfaction score: {average_satisfaction:.2f}")

String filter = "customer_tier == \"premium\" AND region == \"North America\" AND RANDOM_SAMPLE(0.001)";

QueryReq queryReq = QueryReq.builder()
        .collectionName("customer_profiles")
        .filter(filter)
        .outputFields(Arrays.asList("purchase_amount", "satisfaction_score", "last_purchase_date"))
        .limit(10)
        .build();

QueryResp queryResp = client.query(queryReq);

filter := "customer_tier == \"premium\" AND region == \"North America\" AND RANDOM_SAMPLE(0.001)"

resultSet, err := client.Query(ctx, milvusclient.NewQueryOption("customer_profiles").
    WithFilter(filter).
    WithOutputFields("purchase_amount", "satisfaction_score", "last_purchase_date"))
if err != nil {
    fmt.Println(err.Error())
    // handle error
}

// node

# restful

範例 4：結合向量搜尋

在篩選搜尋情境中使用隨機抽樣：

# Search for similar products within a sampled subset
search_results = client.search(
    collection_name="product_catalog",
    data=[[0.1, 0.2, 0.3, 0.4, 0.5]],  # query vector
    filter='category == "books" AND RANDOM_SAMPLE(0.01)',
    search_params={"metric_type": "L2", "params": {}},
    output_fields=["title", "author", "price"],
    limit=10
)

print(f"Found {len(search_results[0])} similar books in sample")

import io.milvus.v2.service.vector.request.SearchReq
import io.milvus.v2.service.vector.request.data.FloatVec;
import io.milvus.v2.service.vector.response.SearchResp

FloatVec queryVector = new FloatVec(new float[]{0.1f, 0.2f, 0.3f, 0.4f, 0.5f});
SearchReq searchReq = SearchReq.builder()
        .collectionName("product_catalog")
        .data(Collections.singletonList(queryVector))
        .topK(10)
        .filter("category == \"books\" AND RANDOM_SAMPLE(0.01)")
        .outputFields(Arrays.asList("title", "author", "price"))
        .build();

SearchResp searchResp = client.search(searchReq);

List<List<SearchResp.SearchResult>> searchResults = searchResp.getSearchResults();
for (List<SearchResp.SearchResult> results : searchResults) {
    System.out.println("TopK results:");
    for (SearchResp.SearchResult result : results) {
        System.out.println(result);
    }
}

queryVector := []float32{0.1, 0.2, 0.3, 0.4, 0.5}

resultSets, err := client.Search(ctx, milvusclient.NewSearchOption(
    "product_catalog", // collectionName
    10,               // limit
    []entity.Vector{entity.FloatVector(queryVector)},
).WithConsistencyLevel(entity.ClStrong).
    WithFilter("category == \"books\" AND RANDOM_SAMPLE(0.01)").
    WithOutputFields("title", "author", "price"))
if err != nil {
    fmt.Println(err.Error())
    // handle error
}

for _, resultSet := range resultSets {
    fmt.Println("title: ", resultSet.GetColumn("title").FieldData().GetScalars())
    fmt.Println("author: ", resultSet.GetColumn("author").FieldData().GetScalars())
    fmt.Println("price: ", resultSet.GetColumn("price").FieldData().GetScalars())
}

// node

# restful

最佳實務

• 從小處開始：從較小的取樣因子 (0.001-0.01)開始進行初步探索

• 開發工作流程：在開發過程中使用取樣，在生產查詢中移除取樣

• 統計有效性：較大的樣本可提供更精確的統計表現

• 效能測試：監控查詢效能，並視需要調整取樣因子