lfnovo--open-notebook/examples/docker-compose-full-local.yml

# Docker Compose - 100% Local AI Setup
#
# This is the complete privacy-focused setup with NO external APIs needed:
# - Ollama: Local LLM and embeddings (mistral, llama, nomic-embed, etc.)
# - Speaches: Local TTS (text-to-speech) and STT (speech-to-text)
# - Open Notebook: Your research assistant
# - SurrealDB: Local database
#
# Perfect for:
# - Complete privacy (nothing leaves your machine)
# - Offline work
# - No API costs
# - Air-gapped environments
# - Testing and development
#
# Usage:
#   1. Copy this file to your project folder as docker-compose.yml
#   2. Change OPEN_NOTEBOOK_ENCRYPTION_KEY below
#   3. Run: docker compose up -d
#   4. Pull models (see instructions below)
#   5. Configure providers in UI
#
# Full documentation:
# - Ollama setup: https://github.com/lfnovo/open-notebook/blob/main/examples/README.md
# - TTS setup: https://github.com/lfnovo/open-notebook/blob/main/docs/5-CONFIGURATION/local-tts.md
# - STT setup: https://github.com/lfnovo/open-notebook/blob/main/docs/5-CONFIGURATION/local-stt.md

services:
  surrealdb:
    image: surrealdb/surrealdb:v2
    command: start --log info --user root --pass root rocksdb:/mydata/mydatabase.db
    user: root
    ports:
      # Localhost only — the database uses default credentials, so never
      # publish this port on 0.0.0.0
      - "127.0.0.1:8000:8000"
    volumes:
      - ./surreal_data:/mydata
    environment:
      - SURREAL_EXPERIMENTAL_GRAPHQL=true
    restart: always
    pull_policy: always

  ollama:
    image: ollama/ollama:latest
    ports:
      - "11434:11434"
    volumes:
      - ollama_models:/root/.ollama
    restart: always
    pull_policy: always
    # For GPU acceleration (NVIDIA), add:
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: 1
    #           capabilities: [gpu]

  speaches:
    image: ghcr.io/speaches-ai/speaches:latest-cpu
    container_name: speaches
    ports:
      - "8969:8000"
    volumes:
      - hf-hub-cache:/home/ubuntu/.cache/huggingface/hub
    restart: unless-stopped
    # For GPU acceleration, use: ghcr.io/speaches-ai/speaches:latest-cuda
    # and add GPU device mapping (see docs)

  open_notebook:
    image: lfnovo/open_notebook:v1-latest
    ports:
      - "8502:8502"
      - "5055:5055"
    environment:
      # REQUIRED: Change this to your own secret string
      - OPEN_NOTEBOOK_ENCRYPTION_KEY=change-me-to-a-secret-string

      # Database connection
      - SURREAL_URL=ws://surrealdb:8000/rpc
      - SURREAL_USER=root
      - SURREAL_PASSWORD=root
      - SURREAL_NAMESPACE=open_notebook
      - SURREAL_DATABASE=open_notebook

      # Ollama connection (optional, can also configure via UI)
      - OLLAMA_BASE_URL=http://ollama:11434
    volumes:
      - ./notebook_data:/app/data
    depends_on:
      - surrealdb
      - ollama
      - speaches
    restart: always
    pull_policy: always

volumes:
  ollama_models:
  hf-hub-cache:

# ==========================================
# AFTER STARTING: Download Models
# ==========================================
#
# Ollama Models (LLM):
#   docker exec open_notebook-ollama-1 ollama pull mistral
#   docker exec open_notebook-ollama-1 ollama pull llama3.1
#   docker exec open_notebook-ollama-1 ollama pull qwen2.5
#
# Ollama Models (Embeddings):
#   docker exec open_notebook-ollama-1 ollama pull nomic-embed-text
#   docker exec open_notebook-ollama-1 ollama pull mxbai-embed-large
#
# Speaches (TTS):
#   docker compose exec speaches uv tool run speaches-cli model download speaches-ai/Kokoro-82M-v1.0-ONNX
#
# Speaches (STT):
#   docker compose exec speaches uv tool run speaches-cli model download Systran/faster-whisper-small
#
# ==========================================
# CONFIGURATION IN OPEN NOTEBOOK
# ==========================================
#
# 1. Configure Ollama:
#    - Go to Settings → API Keys
#    - Add Credential → Select "Ollama"
#    - Base URL: http://ollama:11434
#    - Save → Test Connection → Discover Models → Register Models
#
# 2. Configure Speaches (TTS/STT):
#    - Go to Settings → API Keys
#    - Add Credential → Select "OpenAI-Compatible"
#    - Name: "Local Speaches"
#    - Base URL for TTS: http://host.docker.internal:8969/v1  (macOS/Windows)
#                    or: http://172.17.0.1:8969/v1           (Linux)
#    - Base URL for STT: (same as TTS)
#    - Save → Test Connection
#
# 3. Discover Speech Models:
#    - In the Speaches credential you just created, click Discover Models
#    - Select and register the models you need (e.g. TTS and STT)
#    - If models aren't discovered automatically, add them manually:
#      * TTS: speaches-ai/Kokoro-82M-v1.0-ONNX
#      * STT: Systran/faster-whisper-small
#
# ==========================================
# RECOMMENDED MODELS
# ==========================================
#
# For LLM (choose based on your hardware):
# - Fast: mistral (7B), qwen2.5 (7B)
# - Balanced: llama3.1 (8B)
# - Best quality: qwen2.5 (14B+), llama3.1 (70B) - requires powerful GPU
#
# For Embeddings:
# - nomic-embed-text (recommended, 137M params)
# - mxbai-embed-large (334M params, better quality)
#
# For TTS:
# - speaches-ai/Kokoro-82M-v1.0-ONNX (good quality, fast)
#
# For STT (Whisper):
# - faster-whisper-small (balanced, ~500MB)
# - faster-whisper-base (faster, less accurate)
# - faster-whisper-large-v3 (best quality, slower, ~3GB)
#
# ==========================================
# HARDWARE REQUIREMENTS
# ==========================================
#
# Minimum (CPU only):
# - 8 GB RAM
# - 20 GB disk space
# - 4 CPU cores
#
# Recommended (with GPU):
# - 16+ GB RAM
# - 8+ GB VRAM (NVIDIA GPU)
# - 50 GB disk space
# - 8+ CPU cores
#
# ==========================================
# COST COMPARISON
# ==========================================
#
# Local (this setup):
# - Cost: $0 (after hardware)
# - Privacy: 100% private
# - Speed: Depends on hardware
#
# Cloud (OpenAI + ElevenLabs):
# - LLM: ~$0.01-0.10 per 1K tokens
# - Embeddings: ~$0.0001 per 1K tokens
# - TTS: ~$0.015 per minute
# - STT: ~$0.006 per minute
# - Privacy: Data sent to providers
# - Speed: Usually faster