# Phase 2A — Embedding candidate compose override (Diagnose only)
#
# Profile-isolated: `--profile embed-cand` 명시 opt-in. default up 시 미기동.
# production fastapi/postgres/reranker 에 영향 0.
# 본 PR 종료 시 별 chore (PR-2A-Chunks-Cand-Cleanup-1) 에서 제거.
#
# 후보 상태 (2026-05-23):
#   - me5_large_inst : ✅ smoke PASS (dim 1024)
#   - bge_mgemma2    : ❌ Phase 2A-Extended 별 PR 이관 (9B FP16 → VRAM OOM risk + 다운로드 cost)
#   - me5_ko         : ❌ 폐기 (401 Unauthorized, gated/모델명 부정확)
#   - snowflake_l_v2 : 신규 추가 (Snowflake/snowflake-arctic-embed-l-v2.0, 2024-12, multilingual 강화)
#
# 사용:
#   docker compose -f docker-compose.yml -f docker-compose.override.cand.yml \
#     --profile embed-cand up -d embedding-cand-me5-inst
#
# 호출 (DS network 내부):
#   http://embedding-cand-me5-inst:80/embed
#   http://embedding-cand-snowflake-l-v2:80/embed

services:
  embedding-cand-me5-inst:
    image: ghcr.io/huggingface/text-embeddings-inference:1.7
    restart: unless-stopped
    container_name: hyungi_document_server-embedding-cand-me5-inst-1
    expose:
      - "80"
    environment:
      - MODEL_ID=intfloat/multilingual-e5-large-instruct
      - MAX_BATCH_TOKENS=8192
      - MAX_CONCURRENT_REQUESTS=4
    volumes:
      - embedding_cand_me5_inst_cache:/data
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-fsS", "http://localhost/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s
    profiles: ["embed-cand"]

  embedding-cand-snowflake-l-v2:
    image: ghcr.io/huggingface/text-embeddings-inference:1.7
    restart: unless-stopped
    container_name: hyungi_document_server-embedding-cand-snowflake-l-v2-1
    expose:
      - "80"
    environment:
      - MODEL_ID=Snowflake/snowflake-arctic-embed-l-v2.0
      - MAX_BATCH_TOKENS=8192
      - MAX_CONCURRENT_REQUESTS=4
    volumes:
      - embedding_cand_snowflake_l_v2_cache:/data
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-fsS", "http://localhost/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s
    profiles: ["embed-cand"]

  # ===== 비활성 후보 (Phase 2A-Extended 별 PR 이관 또는 폐기) =====
  # 진단 박제만 보존. 본 PR scope 외.

  embedding-cand-bge-mgemma2:
    image: ghcr.io/huggingface/text-embeddings-inference:1.7
    container_name: hyungi_document_server-embedding-cand-bge-mgemma2-1
    expose:
      - "80"
    environment:
      - MODEL_ID=BAAI/bge-multilingual-gemma2
      - MAX_BATCH_TOKENS=8192
      - MAX_CONCURRENT_REQUESTS=4
    volumes:
      - embedding_cand_bge_mgemma2_cache:/data
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-fsS", "http://localhost/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 300s
    profiles: ["embed-cand-extended"]   # 본 PR 미사용. extended 별 profile.

  embedding-cand-me5-ko:
    image: ghcr.io/huggingface/text-embeddings-inference:1.7
    container_name: hyungi_document_server-embedding-cand-me5-ko-1
    expose:
      - "80"
    environment:
      - MODEL_ID=dragonkue/multilingual-e5-large-ko
      - MAX_BATCH_TOKENS=8192
      - MAX_CONCURRENT_REQUESTS=4
    volumes:
      - embedding_cand_me5_ko_cache:/data
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-fsS", "http://localhost/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s
    profiles: ["embed-cand-disabled"]   # 401 fail. 사용 X.

volumes:
  embedding_cand_me5_inst_cache:
  embedding_cand_snowflake_l_v2_cache:
  embedding_cand_bge_mgemma2_cache:
  embedding_cand_me5_ko_cache: