AgapHost/openai/docker-compose.yml

services:
  ollama:
    image: ollama/ollama
    container_name: ollama
    ports:
      - "11436:11434"
    volumes:
      - /mnt/ssd/ai/ollama:/root/.ollama
      - /mnt/ssd/ai/open-webui:/app/backend/data
    restart: always
    environment:
      # Allow qwen3:8b + qwen2.5:1.5b to coexist in VRAM (~6.7-7.7 GB on 8 GB GPU)
      - OLLAMA_MAX_LOADED_MODELS=2
      # One GPU inference at a time — prevents compute contention between models
      - OLLAMA_NUM_PARALLEL=1
      # Force all layers to GPU — fail instead of falling back to CPU
      - OLLAMA_NUM_GPU=999
    runtime: nvidia
    mem_limit: 4g

  ollama-cpu:
    image: ollama/ollama
    container_name: ollama-cpu
    ports:
      - "11435:11434"
    volumes:
      - /mnt/ssd/ai/ollama-cpu:/root/.ollama
    restart: always
   
  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    ports:
      - "3125:8080"
    volumes:
      - /mnt/ssd/ai/open-webui:/app/backend/data
    extra_hosts:
      - "host.docker.internal:host-gateway"
    restart: always
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    environment:
      - ANTHROPIC_API_KEY=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
      - OPENAI_API_BASE_URL=http://host.docker.internal:4000/v1
      - OPENAI_API_KEY=dummy
      # STT — Faster-Whisper large-v3-turbo
      - AUDIO_STT_ENGINE=openai
      - AUDIO_STT_OPENAI_API_BASE_URL=http://host.docker.internal:8880/v1
      - AUDIO_STT_OPENAI_API_KEY=dummy
      - AUDIO_STT_MODEL=deepdml/faster-whisper-large-v3-turbo-ct2
      # TTS — Silero v4
      - AUDIO_TTS_ENGINE=openai
      - AUDIO_TTS_OPENAI_API_BASE_URL=http://host.docker.internal:8881/v1
      - AUDIO_TTS_OPENAI_API_KEY=dummy
      - AUDIO_TTS_MODEL=silero
      - AUDIO_TTS_VOICE=onyx

  litellm-db:
    image: postgres:16-alpine
    container_name: litellm-db
    environment:
      - POSTGRES_DB=litellm
      - POSTGRES_USER=litellm
      - POSTGRES_PASSWORD=litellm
    volumes:
      - /mnt/ssd/dbs/litellm/postgres:/var/lib/postgresql/data
    restart: always

  litellm:
    image: ghcr.io/berriai/litellm:main-latest
    container_name: litellm
    ports:
      - "4000:4000"
    volumes:
      - ./litellm-config.yaml:/app/config.yaml
    environment:
      - DATABASE_URL=postgresql://litellm:litellm@litellm-db:5432/litellm
      - LITELLM_MASTER_KEY=sk-fjQC1BxAiGFSMs
      - LANGFUSE_PUBLIC_KEY=${LANGFUSE_PUBLIC_KEY:-changeme}
      - LANGFUSE_SECRET_KEY=${LANGFUSE_SECRET_KEY:-changeme}
      - LANGFUSE_HOST=http://langfuse:3000
      - OPENROUTER_API_KEY=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
    command: ["--config", "/app/config.yaml", "--port", "4000"]
    extra_hosts:
      - "host.docker.internal:host-gateway"
    depends_on:
      - litellm-db
      - langfuse
    restart: always

  langfuse-db:
    image: postgres:16-alpine
    container_name: langfuse-db
    environment:
      - POSTGRES_DB=langfuse
      - POSTGRES_USER=langfuse
      - POSTGRES_PASSWORD=langfuse
    volumes:
      - /mnt/ssd/dbs/langfuse/postgres:/var/lib/postgresql/data
    restart: always

  langfuse:
    image: ghcr.io/langfuse/langfuse:2
    container_name: langfuse
    ports:
      - "3200:3000"
    environment:
      - DATABASE_URL=postgresql://langfuse:langfuse@langfuse-db:5432/langfuse
      - NEXTAUTH_URL=https://lf.alogins.net
      - NEXTAUTH_SECRET=532a746b24ac40afa39f9d317031cab94d4d6881107ea3b1209b28020f1a9761
      - SALT=7927b3b0092afe4542274940b557becea6418a5fed79f7acd25c3a789349fdc9
      - AUTH_DISABLE_SIGNUP=true
    depends_on:
      - langfuse-db
    restart: always

  searxng:
    image: docker.io/searxng/searxng:latest
    container_name: searxng
    volumes:
      - /mnt/ssd/ai/searxng/config/:/etc/searxng/
      - /mnt/ssd/ai/searxng/data/:/var/cache/searxng/
    restart: always
    ports:
      - "11437:8080"

  qdrant:
    image: qdrant/qdrant
    container_name: qdrant
    ports:
      - "6333:6333"
      - "6334:6334"
    restart: always
    volumes:
      - /mnt/ssd/dbs/qdrant:/qdrant/storage:z

  faster-whisper:
    image: fedirz/faster-whisper-server:latest-cuda
    container_name: faster-whisper
    runtime: nvidia
    ports:
      - "8880:8000"
    environment:
      - WHISPER__MODEL=deepdml/faster-whisper-large-v3-turbo-ct2
      - WHISPER__INFERENCE_DEVICE=cuda
      - WHISPER__COMPUTE_TYPE=int8
      - WHISPER__LANGUAGE=ru
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
    volumes:
      - /mnt/ssd/ai/faster-whisper:/root/.cache/huggingface
    restart: always

  silero-tts:
    build: ./silero-tts
    container_name: silero-tts
    ports:
      - "8881:8881"
    volumes:
      - /mnt/ssd/ai/silero-tts:/cache/torch
    restart: always

  pipecat:
    build: ./pipecat
    container_name: pipecat
    ports:
      - "8882:8882"
    environment:
      - LIVEKIT_URL=ws://host.docker.internal:7880
      - LIVEKIT_PUBLIC_URL=wss://lk.alogins.net
      - LIVEKIT_API_KEY=devkey
      - LIVEKIT_SECRET=ef3ef4b903ca8469b09b2dd7ab6af529c4d2f3c95668f53832fc351cf67777a9
      - ADOLF_URL=http://host.docker.internal:8000/v1
      - STT_URL=http://host.docker.internal:8880/v1
      - TTS_URL=http://host.docker.internal:8881/v1
      - STT_MODEL=deepdml/faster-whisper-large-v3-turbo-ct2
      - TTS_VOICE=onyx
    extra_hosts:
      - "host.docker.internal:host-gateway"
    restart: unless-stopped