# Infinity — OpenAI-compatible embeddings + reranker server.
#
# Serves embedding and reranker models simultaneously from one container
# on port 7997 (HTTP).  Consumers: AIPA agents (search/retrieval), LibreChat
# RAG, anything that needs vector embeddings.
#
# All tunables live in .env — edit that, not this file.
#
# Pre-download models to avoid first-run delay:
#   HF_HOME=/tank/aimodels/huggingface hf download Qwen/Qwen3-Embedding-0.6B
#   HF_HOME=/tank/aimodels/huggingface hf download Qwen/Qwen3-Reranker-0.6B

services:
  infinity:
    image: michaelf34/infinity:${INFINITY_VERSION}
    container_name: infinity
    restart: unless-stopped
    ports:
      - "${INFINITY_PORT}:7997"
    volumes:
      - /tank/aimodels/huggingface:/hfcache
    environment:
      - HF_HOME=/hfcache
      - HF_HUB_CACHE=/hfcache/hub
      - HUGGING_FACE_HUB_TOKEN=${HF_TOKEN:-}
    command: >
      v2
      --model-id ${EMBED_MODEL}
      --model-id ${RERANK_MODEL}
      --engine ${ENGINE}
      --device cuda
      --batch-size ${BATCH_SIZE}
      --host 0.0.0.0
      --port 7997
      --api-key ${API_KEY:-}
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids:
                - "${GPU_ID}"
              capabilities:
                - gpu
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:7997/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 120s
    networks:
      - tnet
    labels:
      - homepage.group=AI Systems
      - homepage.name=Infinity
      - homepage.icon=mdi-vector-arrange-below
      - homepage.description=Embeddings + Reranker API (ana-ml2)
      - homepage.href=http://10.250.50.54:7997/docs

networks:
  tnet:
    name: traefik-net
    external: true