services:
  weaviate:
    command:
      - --host
      - 0.0.0.0
      - --port
      - "8080"
      - --scheme
      - http
    image: cr.weaviate.io/semitechnologies/weaviate:1.32.0 # Required for text2vec-google taskType support
    ports:
      - 8080:8080
      - 50051:50051
    volumes:
      - product_profile_ingestion_weaviate_data:/var/lib/weaviate
    restart: on-failure:0
    depends_on:
      - reranker-transformers
    environment:
      QUERY_DEFAULTS_LIMIT: 25
      PERSISTENCE_DATA_PATH: "/var/lib/weaviate"
      CLUSTER_HOSTNAME: "node1"
      # Swap OpenAI to Google modules
      ENABLE_MODULES: "text2vec-google,reranker-transformers"
      DEFAULT_VECTORIZER_MODULE: "text2vec-google"
      RERANKER_INFERENCE_API: "http://reranker-transformers:8080"

  # Local cross-encoder. Reranks the near_text candidate pool; no external API key.
  reranker-transformers:
    image: cr.weaviate.io/semitechnologies/reranker-transformers:cross-encoder-ms-marco-MiniLM-L-6-v2
    environment:
      ENABLE_CUDA: 0

  # Self-hosted tracing/eval UI (Arize Phoenix). Opt-in from the pipeline's
  # side (config.yaml observability.enabled / PHOENIX_TRACING_ENABLED); this
  # container can run continuously with no effect on `batch` when tracing is
  # off. SQLite on a mounted volume is sufficient for a single-machine setup
  # (see README "Observability"); do not add Postgres.
  phoenix:
    image: arizephoenix/phoenix:20.3.0
    ports:
      - 6006:6006 # UI + OTLP/HTTP collector (POST .../v1/traces)
    environment:
      PHOENIX_WORKING_DIR: /mnt/data
    volumes:
      - phoenix_data:/mnt/data
    restart: unless-stopped

volumes:
  product_profile_ingestion_weaviate_data:
    external: true
  phoenix_data: