# 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

  #
  # 约定：下列键为必填；进程环境变量可覆盖 infrastructure / runtime 中同名语义项
  #（如 ES_HOST、API_PORT 等），未设置环境变量时使用本文件中的值。
  
  # Process / bind addresses (环境变量 APP_ENV、RUNTIME_ENV、ES_INDEX_NAMESPACE 可覆盖前两者的语义)
  runtime:
    environment: "prod"
    index_namespace: ""
    api_host: "0.0.0.0"
    api_port: 6002
    indexer_host: "0.0.0.0"
    indexer_port: 6004
    embedding_host: "0.0.0.0"
    embedding_port: 6005
    embedding_text_port: 6005
    embedding_image_port: 6008
    translator_host: "127.0.0.1"
    translator_port: 6006
    reranker_host: "127.0.0.1"
    reranker_port: 6007
  
  # 基础设施连接（敏感项优先读环境变量：ES_*、REDIS_*、DB_*、DASHSCOPE_API_KEY、DEEPL_AUTH_KEY）
  infrastructure:
    elasticsearch:
      host: "http://localhost:9200"
      username: null
      password: null
    redis:
      host: "localhost"
      port: 6479
      snapshot_db: 0
      password: null
      socket_timeout: 1
      socket_connect_timeout: 1
      retry_on_timeout: false
      cache_expire_days: 720
      embedding_cache_prefix: "embedding"
      anchor_cache_prefix: "product_anchors"
      anchor_cache_expire_days: 30
    database:
      host: null
      port: 3306
      database: null
      username: null
      password: null
    secrets:
      dashscope_api_key: null
      deepl_auth_key: null

  
  # Elasticsearch Index
  es_index_name: "search_products"
  

  # 检索域 / 索引列表（可为空列表；每项字段均需显式给出）
  indexes: []
  

  # Config assets
  assets:
    query_rewrite_dictionary_path: "config/dictionaries/query_rewrite.dict"
  

  # Product content understanding (LLM enrich-content) configuration
  product_enrich:
    max_workers: 40
  

  # 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；查询时按实际检索语言动态拼接 .{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

    qanchors: 1.5

    vendor: 1.5
    category_path: 1.5
    category_name_text: 1.5

    tags: 1.0

    option1_values: 0.6
    option2_values: 0.4
    option3_values: 0.4

  # 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

    # 查询翻译模型（须与 services.translation.capabilities 中某项一致）
    # 源语种在租户 index_languages 内：主召回可打在源语种字段，用下面三项。
    # zh_to_en_model: "opus-mt-zh-en"
    # en_to_zh_model: "opus-mt-en-zh"
    # default_translation_model: "nllb-200-distilled-600m"
    zh_to_en_model: "deepl"
    en_to_zh_model: "deepl"
    default_translation_model: "deepl"
    # 源语种不在 index_languages：翻译对可检索文本更关键，可单独指定（缺省则与上一组相同）
    zh_to_en_model__source_not_in_index: "deepl"
    en_to_zh_model__source_not_in_index: "deepl"
    default_translation_model__source_not_in_index: "deepl"
  

    # 查询解析阶段：翻译与 query 向量并发执行，共用同一等待预算（毫秒）。
    # 检测语言已在租户 index_languages 内：较短；不在索引语言内：较长（翻译对召回更关键）。

    translation_embedding_wait_budget_ms_source_in_index: 500 # 80
    translation_embedding_wait_budget_ms_source_not_in_index: 500 #200

    # 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）

    text_query_strategy:
      base_minimum_should_match: "75%"
      translation_minimum_should_match: "75%"

      translation_boost: 0.6

      tie_breaker_base_query: 0.9

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

    # 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

    # 下列字段与 api/result_formatter.py（SpuResult 填充）及 search/searcher.py（SKU 排序/主图替换）一致
    source_fields:
      - spu_id
      - handle
      - title
      - brief
      - description
      - vendor
      - category_name
      - category_name_text
      - category_path
      - category_id
      - category_level
      - category1_name
      - category2_name
      - category3_name
      - tags
      - min_price
      - compare_at_price
      - image_url
      - sku_prices
      - sku_weights
      - sku_weight_units
      - total_inventory
      - option1_name
      - option1_values
      - specifications
      - skus

    
    # KNN boost配置（向量召回的boost值）

    knn_boost: 2.0  # 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: 400

    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:

      service_url: "http://127.0.0.1:6006"

      default_model: "nllb-200-distilled-600m"

      default_scene: "general"

      timeout_sec: 10.0

      cache:

        ttl_seconds: 62208000
        sliding_expiration: true

        # When false, cache keys are exact-match per request model only (ignores model_quality_tiers for lookups).
        enable_model_quality_tier_cache: true
        # Higher tier = better quality. Multiple models may share one tier (同级).
        # A request may reuse Redis keys from models with tier > A or tier == A (not from lower tiers).
        model_quality_tiers:
          deepl: 30
          qwen-mt: 30
          llm: 30
          nllb-200-distilled-600m: 20
          opus-mt-zh-en: 10
          opus-mt-en-zh: 10

      capabilities:

        qwen-mt:

          enabled: true

          backend: "qwen_mt"

          model: "qwen-mt-flash"

          base_url: "https://dashscope-us.aliyuncs.com/compatible-mode/v1"

          timeout_sec: 10.0

          use_cache: true

        llm:

          enabled: true

          backend: "llm"

          model: "qwen-flash"

          base_url: "https://dashscope-us.aliyuncs.com/compatible-mode/v1"

          timeout_sec: 30.0

          use_cache: true

        deepl:

          enabled: true

          backend: "deepl"
          api_url: "https://api.deepl.com/v2/translate"

          timeout_sec: 10.0

          glossary_id: ""

          use_cache: true

        nllb-200-distilled-600m:
          enabled: true
          backend: "local_nllb"
          model_id: "facebook/nllb-200-distilled-600M"
          model_dir: "./models/translation/facebook/nllb-200-distilled-600M"

          ct2_model_dir: "./models/translation/facebook/nllb-200-distilled-600M/ctranslate2-float16"
          ct2_compute_type: "float16"
          ct2_conversion_quantization: "float16"
          ct2_auto_convert: true

          ct2_inter_threads: 4

          ct2_intra_threads: 0

          ct2_max_queued_batches: 32

          ct2_batch_type: "examples"

          ct2_decoding_length_mode: "source"
          ct2_decoding_length_extra: 8
          ct2_decoding_length_min: 32

          device: "cuda"
          torch_dtype: "float16"

          batch_size: 64

          max_input_length: 256

          max_new_tokens: 64

          num_beams: 1

          use_cache: true

        opus-mt-zh-en:
          enabled: true
          backend: "local_marian"
          model_id: "Helsinki-NLP/opus-mt-zh-en"
          model_dir: "./models/translation/Helsinki-NLP/opus-mt-zh-en"

          ct2_model_dir: "./models/translation/Helsinki-NLP/opus-mt-zh-en/ctranslate2-float16"
          ct2_compute_type: "float16"
          ct2_conversion_quantization: "float16"
          ct2_auto_convert: true
          ct2_inter_threads: 1
          ct2_intra_threads: 0
          ct2_max_queued_batches: 0
          ct2_batch_type: "examples"

          device: "cuda"
          torch_dtype: "float16"
          batch_size: 16
          max_input_length: 256
          max_new_tokens: 256
          num_beams: 1

          use_cache: true

        opus-mt-en-zh:
          enabled: true
          backend: "local_marian"
          model_id: "Helsinki-NLP/opus-mt-en-zh"
          model_dir: "./models/translation/Helsinki-NLP/opus-mt-en-zh"

          ct2_model_dir: "./models/translation/Helsinki-NLP/opus-mt-en-zh/ctranslate2-float16"
          ct2_compute_type: "float16"
          ct2_conversion_quantization: "float16"
          ct2_auto_convert: true
          ct2_inter_threads: 1
          ct2_intra_threads: 0
          ct2_max_queued_batches: 0
          ct2_batch_type: "examples"

          device: "cuda"
          torch_dtype: "float16"
          batch_size: 16
          max_input_length: 256
          max_new_tokens: 256
          num_beams: 1

          use_cache: true

    embedding:

      provider: "http"  # http

      providers:
        http:

          text_base_url: "http://127.0.0.1:6005"
          image_base_url: "http://127.0.0.1:6008"

      # 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

      # 服务内图片后端（embedding 进程启动时读取）
      image_backend: "clip_as_service"  # clip_as_service | local_cnclip
      image_backends:
        clip_as_service:
          server: "grpc://127.0.0.1:51000"
          model_name: "CN-CLIP/ViT-L-14"
          batch_size: 8
          normalize_embeddings: true
        local_cnclip:
          model_name: "ViT-L-14"
          device: null
          batch_size: 8
          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"

      request:
        max_docs: 1000
        normalize: true

      # 服务内后端（reranker 进程启动时读取）

      backend: "qwen3_vllm"  # 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: 160

          cache_dir: "./model_cache"
          enable_warmup: true
        qwen3_vllm:
          model_name: "Qwen/Qwen3-Reranker-0.6B"
          engine: "vllm"

          max_model_len: 160

          tensor_parallel_size: 1

          gpu_memory_utilization: 0.20

          dtype: "float16"

          enable_prefix_caching: true
          enforce_eager: false

          infer_batch_size: 100

          sort_by_doc_length: true

          # "rank products by given query" 比 “Given a query, score the product for relevance” 更好点
          instruction: "rank products by given query" 
          # instruction: "Given a query, score the product for relevance"

        qwen3_transformers:
          model_name: "Qwen/Qwen3-Reranker-0.6B"

          instruction: "rank products by given query"

          # instruction: "Score the product’s relevance to the given query"

          max_length: 8192
          batch_size: 64
          use_fp16: true

          # sdpa：默认无需 flash-attn；若已安装 flash_attn 可改为 flash_attention_2
          attn_implementation: "sdpa"

        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 SOURCE_LANG_CODE_MAP.keys() 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"]