Retriever - Milvus v2 (推荐)

go get github.com/cloudwego/eino-ext/components/retriever/milvus2

package main

import (
        "context"
        "fmt"
        "log"
        "os"

        "github.com/cloudwego/eino-ext/components/embedding/ark"
        "github.com/milvus-io/milvus/client/v2/milvusclient"

        milvus2 "github.com/cloudwego/eino-ext/components/retriever/milvus2"
        "github.com/cloudwego/eino-ext/components/retriever/milvus2/search_mode"
)

func main() {
        // 获取环境变量
        addr := os.Getenv("MILVUS_ADDR")
        username := os.Getenv("MILVUS_USERNAME")
        password := os.Getenv("MILVUS_PASSWORD")
        arkApiKey := os.Getenv("ARK_API_KEY")
        arkModel := os.Getenv("ARK_MODEL")

        ctx := context.Background()

        // 创建 embedding 模型
        emb, err := ark.NewEmbedder(ctx, &ark.EmbeddingConfig{
                APIKey: arkApiKey,
                Model:  arkModel,
        })
        if err != nil {
                log.Fatalf("Failed to create embedding: %v", err)
                return
        }

        // 创建 retriever
        retriever, err := milvus2.NewRetriever(ctx, &milvus2.RetrieverConfig{
                ClientConfig: &milvusclient.ClientConfig{
                        Address:  addr,
                        Username: username,
                        Password: password,
                },
                Collection: "my_collection",
                TopK:       10,
                SearchMode: search_mode.NewApproximate(milvus2.COSINE),
                Embedding:  emb,
        })
        if err != nil {
                log.Fatalf("Failed to create retriever: %v", err)
                return
        }
        log.Printf("Retriever created successfully")

        // 检索文档
        documents, err := retriever.Retrieve(ctx, "search query")
        if err != nil {
                log.Fatalf("Failed to retrieve: %v", err)
                return
        }

        // 打印文档
        for i, doc := range documents {
                fmt.Printf("Document %d:\n", i)
                fmt.Printf("  ID: %s\n", doc.ID)
                fmt.Printf("  Content: %s\n", doc.Content)
                fmt.Printf("  Score: %v\n", doc.Score())
        }
}

mode := search_mode.NewApproximate(milvus2.COSINE)

// L2: 距离 <= Radius
// IP/Cosine: 分数 >= Radius
mode := search_mode.NewRange(milvus2.L2, 0.5).
    WithRangeFilter(0.1) // 可选: 环形搜索的内边界

// 纯稀疏搜索 (BM25) 需要指定 OutputFields 以获取内容
// MetricType: BM25 (默认) 或 IP
mode := search_mode.NewSparse(milvus2.BM25)

// 在配置中，使用 "*" 或特定字段以确保返回内容:
// OutputFields: []string{"*"}

import (
    "github.com/milvus-io/milvus/client/v2/milvusclient"
    milvus2 "github.com/cloudwego/eino-ext/components/retriever/milvus2"
    "github.com/cloudwego/eino-ext/components/retriever/milvus2/search_mode"
)

// 定义稠密 + 稀疏子请求的混合搜索
hybridMode := search_mode.NewHybrid(
    milvusclient.NewRRFReranker().WithK(60), // RRF 重排序器
    &search_mode.SubRequest{
        VectorField: "vector",             // 稠密向量字段
        VectorType:  milvus2.DenseVector,  // 默认值，可省略
        TopK:        10,
        MetricType:  milvus2.L2,
    },
    // 稀疏子请求 (Sparse SubRequest)
    &search_mode.SubRequest{
        VectorField: "sparse_vector",       // 稀疏向量字段
        VectorType:  milvus2.SparseVector,  // 指定稀疏类型
        TopK:        10,
        MetricType:  milvus2.BM25,          // 使用 BM25 或 IP
    },
)

// 创建 retriever (稀疏向量生成由 Milvus Function 服务器端处理)
retriever, err := milvus2.NewRetriever(ctx, &milvus2.RetrieverConfig{
    ClientConfig:      &milvusclient.ClientConfig{Address: "localhost:19530"},
    Collection:        "hybrid_collection",
    VectorField:       "vector",             // 默认稠密字段
    SparseVectorField: "sparse_vector",      // 默认稀疏字段
    TopK:              5,
    SearchMode:        hybridMode,
    Embedding:         denseEmbedder,        // 稠密向量的标准 Embedder
})

// 100 是批次大小 (每次网络调用的条目数)
mode := search_mode.NewIterator(milvus2.COSINE, 100).
    WithSearchParams(map[string]string{"nprobe": "10"})

// 使用 RetrieverConfig.TopK 设置总限制 (IteratorLimit)。

mode := search_mode.NewScalar()

// 使用过滤表达式查询
docs, err := retriever.Retrieve(ctx, `category == "electronics" AND year >= 2023`)