LLM-Server/docker-compose.yml

services:
  llama-server:
    image: ghcr.io/ggml-org/llama.cpp:server-rocm
    container_name: llama-server
    devices:
      - /dev/kfd
      - /dev/dri
    group_add:
      - video
      - render
    security_opt:
      - seccomp=unconfined
    ipc: host
    volumes:
      - models:/models
    command: >
      -m /models/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf}
      --host 0.0.0.0
      --port 8080
      --n-gpu-layers ${LLAMA_GPU_LAYERS:-999}
      --ctx-size ${LLAMA_CTX_SIZE:-65536}
      --jinja
    # No published host port: llama-server is reached only via the litellm
    # proxy on the ai-stack docker network now — see issue #15. Its
    # unauthenticated API no longer needs to be LAN-reachable directly.
    expose:
      - "8080"
    restart: unless-stopped
    networks: [ai-stack]
    labels:
      # ponytail: idle-timeout tuning lives here, not in a separate lazytainer config file —
      # one place to look. Raise LAZYTAINER_INACTIVE_TIMEOUT if 15 min proves too eager.
      - "lazytainer.group.llamaserver.sleepMethod=stop"
      - "lazytainer.group.llamaserver.ports=8080"
      - "lazytainer.group.llamaserver.inactiveTimeout=${LAZYTAINER_INACTIVE_TIMEOUT:-900}"
      - "lazytainer.group.llamaserver.minPacketThreshold=2"

  embedding-server:
    image: ghcr.io/ggml-org/llama.cpp:server-rocm
    container_name: embedding-server
    devices:
      - /dev/kfd
      - /dev/dri
    group_add:
      - video
      - render
    security_opt:
      - seccomp=unconfined
    ipc: host
    volumes:
      - models:/models
    command: >
      -m /models/${EMBEDDING_MODEL_FILE:-nomic-embed-text-v1.5.Q8_0.gguf}
      --host 0.0.0.0
      --port 8080
      --embeddings
      --pooling mean
      --n-gpu-layers 999
      --ctx-size 8192
    # A dedicated embedding model — the chat model isn't embedding-trained
    # and llama.cpp serves one model per process, so this is a second small
    # instance, not a mode switch on llama-server. See
    # docs/research/litellm-knowledgebase.md. Small enough (~150MB Q8) to
    # run alongside the chat model's ~19.6GB in the R9700's 32GB VRAM.
    restart: unless-stopped
    networks: [ai-stack]

  # ponytail: one-off downloader, not a standing service — run via
  # `docker compose --profile tools run --rm downloader` (see scripts/download-model.sh).
  # Keeps the model file inside the named `models` volume instead of a host bind-mount.
  downloader:
    image: curlimages/curl:latest
    profiles: ["tools"]
    # ponytail: named volume is created root-owned; curl_user (uid 100) can't
    # write into it otherwise, so run as root for this one-off job.
    user: root
    volumes:
      - models:/models
    entrypoint: ["sh", "-c"]
    command:
      - >
        curl -L --fail --create-dirs -o /models/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf}
        https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf}

  # ponytail: same one-off pattern as `downloader`, for the embedding model —
  # run via `docker compose --profile tools run --rm downloader-embedding`.
  downloader-embedding:
    image: curlimages/curl:latest
    profiles: ["tools"]
    user: root
    volumes:
      - models:/models
    entrypoint: ["sh", "-c"]
    command:
      - >
        curl -L --fail --create-dirs -o /models/${EMBEDDING_MODEL_FILE:-nomic-embed-text-v1.5.Q8_0.gguf}
        https://huggingface.co/nomic-ai/nomic-embed-text-v1.5-GGUF/resolve/main/${EMBEDDING_MODEL_FILE:-nomic-embed-text-v1.5.Q8_0.gguf}

  qdrant:
    image: qdrant/qdrant:latest
    container_name: qdrant
    volumes:
      - qdrant-data:/qdrant/storage
    restart: unless-stopped
    networks: [ai-stack]
    healthcheck:
      test: ["CMD-SHELL", "bash -c 'exec 3<>/dev/tcp/localhost/6333'"]
      interval: 10s
      timeout: 5s
      retries: 5

  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    depends_on:
      qdrant:
        condition: service_healthy
      litellm:
        condition: service_healthy
    volumes:
      - openwebui-data:/app/backend/data
    env_file: .env
    environment:
      - WEBUI_AUTH=True
      # Routed through the litellm proxy, not llama-server directly — see issue #15.
      # OPENAI_API_KEY must be a virtual key created for Open WebUI per
      # docs/proxy-key-onboarding.md (name it "openwebui"), set as
      # OPENWEBUI_LITELLM_KEY in .env.
      - OPENAI_API_BASE_URL=http://litellm:4000/v1
      - OPENAI_API_KEY=${OPENWEBUI_LITELLM_KEY}
      - VECTOR_DB=qdrant
      - QDRANT_URI=http://qdrant:6333
    ports:
      - "${WEBUI_PORT:-8008}:8080"
    restart: unless-stopped
    networks: [ai-stack]

  litellm:
    image: ghcr.io/berriai/litellm:main-stable
    container_name: litellm
    depends_on:
      litellm-db:
        condition: service_healthy
      llama-server:
        condition: service_started
    volumes:
      - ./litellm-config.yaml:/app/config.yaml:ro
    # LITELLM_MASTER_KEY / LITELLM_SALT_KEY come straight from .env via env_file
    # (names match what litellm reads). LITELLM_SALT_KEY must not change after
    # first run — see .env.example.
    env_file: .env
    environment:
      - DATABASE_URL=postgresql://litellm:${LITELLM_DB_PASSWORD}@litellm-db:5432/litellm
    # The litellm container only joins the ai-stack bridge network, which has
    # no visibility into the LAN's mDNS/local-DNS names — search.home won't
    # resolve without this. Set SEARXNG_LAN_IP in .env to its stable LAN IP
    # (static DHCP reservation recommended). See docs/research/litellm-searxng-search.md.
    extra_hosts:
      - "search.home:${SEARXNG_LAN_IP}"
    command: ["--config", "/app/config.yaml", "--port", "4000"]
    ports:
      # published for LAN access (proxy.ai.home) and, via NPM, proxy.ai.haylan.ch —
      # NPM must deny the /ui path on the external host. See docs/network-access.md.
      - "${LITELLM_PORT:-4000}:4000"
    restart: unless-stopped
    networks: [ai-stack]
    healthcheck:
      test:
        - CMD-SHELL
        - python3 -c "import urllib.request; urllib.request.urlopen('http://localhost:4000/health/liveliness')"
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

  litellm-db:
    image: postgres:16-alpine
    container_name: litellm-db
    env_file: .env
    environment:
      - POSTGRES_USER=litellm
      - POSTGRES_PASSWORD=${LITELLM_DB_PASSWORD}
      - POSTGRES_DB=litellm
    volumes:
      - litellm-db-data:/var/lib/postgresql/data
    restart: unless-stopped
    networks: [ai-stack]
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -d litellm -U litellm"]
      interval: 5s
      timeout: 5s
      retries: 10

  # Separate Postgres instance (with the pgvector extension) for the
  # knowledgebase — NOT the same database as litellm-db, which is plain
  # postgres:16-alpine and has no vector extension installed. See
  # docs/research/litellm-knowledgebase.md.
  pgvector-db:
    image: pgvector/pgvector:pg16
    container_name: pgvector-db
    env_file: .env
    environment:
      - POSTGRES_USER=litellm_pgvector
      - POSTGRES_PASSWORD=${PGVECTOR_DB_PASSWORD}
      - POSTGRES_DB=litellm_pgvector
    volumes:
      - pgvector-db-data:/var/lib/postgresql/data
    restart: unless-stopped
    networks: [ai-stack]
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -d litellm_pgvector -U litellm_pgvector"]
      interval: 5s
      timeout: 5s
      retries: 10

  # LiteLLM's native knowledgebase/vector-store feature has no Qdrant backend
  # (the qdrant service above only serves Open WebUI's own RAG/Memory), so
  # this small in-repo service wraps langchain_postgres.PGVector directly
  # against pgvector-db instead — simpler than a vendored third-party
  # connector (see docs/research/langchain-pgvector-vs-litellm-pgvector.md,
  # which replaced the earlier litellm-pgvector approach). It still calls
  # back into litellm for embeddings, same gateway boundary as everything
  # else in this stack.
  memory-retrieval:
    build:
      context: ./services/memory-retrieval
    container_name: memory-retrieval
    depends_on:
      pgvector-db:
        condition: service_healthy
      litellm:
        condition: service_healthy
    environment:
      - DATABASE_URL=postgresql+psycopg://litellm_pgvector:${PGVECTOR_DB_PASSWORD}@pgvector-db:5432/litellm_pgvector
      - LITELLM_BASE_URL=http://litellm:4000/v1
      # A virtual key for this workload — see docs/proxy-key-onboarding.md.
      - LITELLM_API_KEY=${MEMORY_RETRIEVAL_EMBEDDING_KEY}
      - EMBEDDING_MODEL=local-embedding
      - SERVER_API_KEY=${MEMORY_RETRIEVAL_API_KEY}
      - COLLECTION_NAME=memory-and-notes
    restart: unless-stopped
    networks: [ai-stack]

  lazytainer:
    image: ghcr.io/vmorganp/lazytainer:master
    container_name: lazytainer
    network_mode: host
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock:ro
    restart: unless-stopped
    depends_on:
      - llama-server

networks:
  ai-stack:

volumes:
  models:
  qdrant-data:
  openwebui-data:
  litellm-db-data:
  pgvector-db-data: