Indexer - Elasticsearch 7

go get github.com/cloudwego/eino-ext/components/indexer/es7@latest

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

        "github.com/cloudwego/eino/components/embedding"
        "github.com/cloudwego/eino/schema"
        elasticsearch "github.com/elastic/go-elasticsearch/v7"

        "github.com/cloudwego/eino-ext/components/embedding/ark"
        "github.com/cloudwego/eino-ext/components/indexer/es7"
)

const (
        indexName          = "eino_example"
        fieldContent       = "content"
        fieldContentVector = "content_vector"
        fieldExtraLocation = "location"
        docExtraLocation   = "location"
)

func main() {
        ctx := context.Background()

        // ES 支持多种连接方式
        username := os.Getenv("ES_USERNAME")
        password := os.Getenv("ES_PASSWORD")

        client, _ := elasticsearch.NewClient(elasticsearch.Config{
                Addresses: []string{"http://localhost:9200"},
                Username:  username,
                Password:  password,
        })

        // 使用 Volcengine ARK 创建 embedding 组件
        emb, _ := ark.NewEmbedder(ctx, &ark.EmbeddingConfig{
                APIKey: os.Getenv("ARK_API_KEY"),
                Region: os.Getenv("ARK_REGION"),
                Model:  os.Getenv("ARK_MODEL"),
        })

        // 加载文档
        docs := []*schema.Document{
                {
                        ID:      "1",
                        Content: "Eiffel Tower: Located in Paris, France.",
                        MetaData: map[string]any{
                                docExtraLocation: "France",
                        },
                },
                {
                        ID:      "2",
                        Content: "The Great Wall: Located in China.",
                        MetaData: map[string]any{
                                docExtraLocation: "China",
                        },
                },
        }

        // 创建 ES 索引器组件
        indexer, _ := es7.NewIndexer(ctx, &es7.IndexerConfig{
                Client:    client,
                Index:     indexName,
                BatchSize: 10,
                DocumentToFields: func(ctx context.Context, doc *schema.Document) (field2Value map[string]es7.FieldValue, err error) {
                        return map[string]es7.FieldValue{
                                fieldContent: {
                                        Value:    doc.Content,
                                        EmbedKey: fieldContentVector, // 对文档内容进行向量化并保存到 "content_vector" 字段
                                },
                                fieldExtraLocation: {
                                        Value: doc.MetaData[docExtraLocation],
                                },
                        }, nil
                },
                Embedding: emb,
        })

        ids, err := indexer.Store(ctx, docs)
        if err != nil {
                fmt.Printf("index error: %v\n", err)
                return
        }
        fmt.Println("indexed ids:", ids)
}

type IndexerConfig struct {
    Client *elasticsearch.Client // 必填：Elasticsearch 客户端实例
    Index  string                // 必填：存储文档的索引名称
    BatchSize int                // 选填：最大文本嵌入批次大小（默认：5）

    // 必填：将 Document 字段映射到 Elasticsearch 字段的函数
    DocumentToFields func(ctx context.Context, doc *schema.Document) (map[string]FieldValue, error)

    // 选填：仅在需要向量化时必填
    Embedding embedding.Embedder
}

// FieldValue 定义了字段应如何存储和向量化
type FieldValue struct {
    Value     any    // 要存储的原始值
    EmbedKey  string // 如果设置，Value 将被向量化并保存
    Stringify func(val any) (string, error) // 选填：自定义字符串转换
}