# Unified Configuration for Multi-Tenant Search Engine

  # 统一配置文件，所有租户共用一套配置
  # 注意：索引结构由 mappings/search_products.json 定义，此文件只配置搜索行为

  
  # Elasticsearch Index
  es_index_name: "search_products"
  

  # ES Index Settings (基础设置)

  es_settings:
    number_of_shards: 1
    number_of_replicas: 0
    refresh_interval: "30s"
  

  # 字段权重配置（用于搜索时的字段boost）

  # 统一按“字段基名”配置；查询时按 search_langs 动态拼接 .{lang}。
  # 若需要按某个语言单独调权，也可以加显式 key（例如 title.de: 3.2）。

  field_boosts:

    title: 3.0
    brief: 1.5
    description: 1.0
    vendor: 1.5
    category_path: 1.5
    category_name_text: 1.5

    tags: 1.0
    option1_values: 0.5
    option2_values: 0.5
    option3_values: 0.5
  

  # Query Configuration（查询配置）

  query_config:

    # 支持的语言

    supported_languages:
      - "zh"
      - "en"

    default_language: "en"

    # 功能开关（翻译开关由tenant_config控制）

    enable_text_embedding: true
    enable_query_rewrite: true

    # 动态多语言检索字段配置
    # multilingual_fields 会被拼成 title.{lang}/brief.{lang}/... 形式；
    # shared_fields 为无语言后缀字段。
    search_fields:
      multilingual_fields:
        - "title"
        - "brief"
        - "description"
        - "vendor"
        - "category_path"
        - "category_name_text"
      shared_fields:
        - "tags"
        - "option1_values"
        - "option2_values"
        - "option3_values"
      core_multilingual_fields:
        - "title"
        - "brief"
        - "vendor"
        - "category_name_text"
  
    # 统一文本召回策略（主查询 + 翻译查询 + phrase/keywords）
    text_query_strategy:
      base_minimum_should_match: "75%"
      translation_minimum_should_match: "75%"
      translation_boost: 0.4
      translation_boost_when_source_missing: 1.0
      source_boost_when_missing: 0.6
      original_query_fallback_boost_when_translation_missing: 0.2
      keywords_boost: 0.1
      enable_phrase_query: true
      tie_breaker_base_query: 0.9
      tie_breaker_keywords: 0.9
  

    # Embedding字段名称
    text_embedding_field: "title_embedding"
    image_embedding_field: null

    # 翻译API配置（provider/URL 在 services.translation）

    translation_service: "deepl"

    translation_api_key: null  # 通过环境变量设置

    # 翻译提示词配置（用于提高翻译质量，作为DeepL API的context参数）
    translation_prompts:
      # 商品标题翻译提示词
      product_title_zh: "请将原文翻译成中文商品SKU名称，要求：确保精确、完整地传达原文信息的基础上，语言简洁清晰、地道、专业。"
      product_title_en: "Translate the original text into an English product SKU name. Requirements: Ensure accurate and complete transmission of the original information, with concise, clear, authentic, and professional language."
      # query翻译提示词
      query_zh: "电商领域"
      query_en: "e-commerce domain"
      # 默认翻译用词
      default_zh: "电商领域"
      default_en: "e-commerce domain"
    

    # 返回字段配置（_source includes）
    # null表示返回所有字段，[]表示不返回任何字段，列表表示只返回指定字段
    source_fields: null

    
    # KNN boost配置（向量召回的boost值）
    knn_boost: 0.25  # Lower boost for embedding recall

  # Function Score配置（ES层打分规则）
  function_score:
    score_mode: "sum"
    boost_mode: "multiply"

    functions: []
  

  # 重排配置（provider/URL 在 services.rerank）

  rerank:

    enabled: true

    rerank_window: 384

    timeout_sec: 15.0

    weight_es: 0.4
    weight_ai: 0.6

    rerank_query_template: "{query}"
    rerank_doc_template: "{title}"

  # 可扩展服务/provider 注册表（单一配置源）
  services:
    translation:
      provider: "direct"  # direct | http | google(reserved)
      base_url: "http://127.0.0.1:6006"
      model: "qwen"
      timeout_sec: 10.0
      providers:
        direct:
          model: "qwen"
        http:
          base_url: "http://127.0.0.1:6006"
          model: "qwen"
          timeout_sec: 10.0
        google:
          enabled: false
          project_id: ""
          location: "global"
          model: ""
    embedding:

      provider: "http"  # http

      base_url: "http://127.0.0.1:6005"
      providers:
        http:
          base_url: "http://127.0.0.1:6005"

      # 服务内文本后端（embedding 进程启动时读取）

      backend: "tei"  # tei | local_st

      backends:
        tei:
          base_url: "http://127.0.0.1:8080"

          timeout_sec: 20

          model_id: "Qwen/Qwen3-Embedding-0.6B"
        local_st:
          model_id: "Qwen/Qwen3-Embedding-0.6B"
          device: "cuda"
          batch_size: 32
          normalize_embeddings: true

    rerank:

      provider: "http"

      base_url: "http://127.0.0.1:6007"
      providers:
        http:
          base_url: "http://127.0.0.1:6007"

          service_url: "http://127.0.0.1:6007/rerank"
      # 服务内后端（reranker 进程启动时读取）

      backend: "dashscope_rerank"  # bge | qwen3_vllm | qwen3_transformers | dashscope_rerank

      backends:
        bge:
          model_name: "BAAI/bge-reranker-v2-m3"
          device: null
          use_fp16: true
          batch_size: 64
          max_length: 512
          cache_dir: "./model_cache"
          enable_warmup: true
        qwen3_vllm:
          model_name: "Qwen/Qwen3-Reranker-0.6B"
          engine: "vllm"

          max_model_len: 256

          tensor_parallel_size: 1

          gpu_memory_utilization: 0.36
          dtype: "float16"

          enable_prefix_caching: true
          enforce_eager: false

          infer_batch_size: 64
          sort_by_doc_length: true
          length_sort_mode: "char"  # char | token

          instruction: "Given a shopping query, rank product titles by relevance"

        qwen3_transformers:
          model_name: "Qwen/Qwen3-Reranker-0.6B"
          instruction: "Given a shopping query, rank product titles by relevance"
          max_length: 8192
          batch_size: 64
          use_fp16: true
          attn_implementation: "flash_attention_2"
        dashscope_rerank:
          model_name: "qwen3-rerank"
          # 按地域选择 endpoint:
          # 中国:   https://dashscope.aliyuncs.com/compatible-api/v1/reranks
          # 新加坡: https://dashscope-intl.aliyuncs.com/compatible-api/v1/reranks
          # 美国:   https://dashscope-us.aliyuncs.com/compatible-api/v1/reranks
          endpoint: "https://dashscope.aliyuncs.com/compatible-api/v1/reranks"

          api_key_env: "RERANK_DASHSCOPE_API_KEY_CN"
          timeout_sec: 10.0 # 

          top_n_cap: 0   # 0 表示 top_n=当前请求文档数；>0 则限制 top_n 上限

          batchsize: 64 # 0 关闭；>0 启用并发小包调度（top_n/top_n_cap 仍生效，分包后全局截断）

          instruct: "Given a shopping query, rank product titles by relevance"
          max_retries: 2
          retry_backoff_sec: 0.2

  # SPU配置（已启用，使用嵌套skus）

  spu_config:
    enabled: true

    spu_field: "spu_id"

    inner_hits_size: 10

    # 配置哪些option维度参与检索（进索引、以及在线搜索）
    # 格式为list，选择option1/option2/option3中的一个或多个
    searchable_option_dimensions: ['option1', 'option2', 'option3']

  
  # 租户配置（Tenant Configuration）

  # 每个租户可配置主语言 primary_language 与索引语言 index_languages（主市场语言，商家可勾选）
  # 默认 index_languages: [en, zh]，可配置为任意 SUPPORTED_INDEX_LANGUAGES 的子集

  tenant_config:

    default:

      primary_language: "en"

      index_languages: ["en", "zh"]

    tenants:
      "1":
        primary_language: "zh"

        index_languages: ["zh", "en"]

      "2":
        primary_language: "en"

        index_languages: ["en", "zh"]

      "3":
        primary_language: "zh"

        index_languages: ["zh", "en"]

      "162":
        primary_language: "zh"

        index_languages: ["zh", "en"]

      "170":
        primary_language: "en"

        index_languages: ["en", "zh"]