Ollama: Dockerコンテナデプロイ

# One command to run Ollama in container
docker run -d --gpus all -v ollama_data:/root/.ollama ollama/ollama

# Or with Docker Compose for full stack
docker compose up -d

# Run Ollama in container (CPU mode)
docker run -d \
  --name ollama \
  -p 11434:11434 \
  -v ollama_data:/root/.ollama \
  ollama/ollama

# Verify it's running
docker ps | grep ollama

# Pull a model inside the container
docker exec ollama ollama pull qwen2.5

# Test the API
curl http://localhost:11434/api/tags

I'm a helpful AI assistant running locally on your machine...

# Run Ollama with GPU support
docker run -d \
  --name ollama-gpu \
  --gpus all \
  -p 11434:11434 \
  -v ollama_data:/root/.ollama \
  ollama/ollama

# Verify GPU is visible inside container
docker exec ollama-gpu nvidia-smi

# Test GPU inference speed
docker exec ollama-gpu ollama run --verbose llama3.2 "Hello"

# Specify which GPUs to use
docker run -d \
  --gpus '"device=0,1"' \
  -p 11434:11434 \
  -v ollama_data:/root/.ollama \
  ollama/ollama

I'm a helpful AI assistant running locally on your machine...

# Run Ollama with AMD GPU (ROCm)
docker run -d \
  --name ollama-rocm \
  --device /dev/kfd \
  --device /dev/dri \
  -p 11434:11434 \
  -v ollama_data:/root/.ollama \
  ollama/ollama:rocm

I'm a helpful AI assistant running locally on your machine...

# docker-compose.yml
version: "3.8"

services:
  ollama:
    image: ollama/ollama
    container_name: ollama
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    restart: unless-stopped

  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    ports:
      - "3000:8080"
    environment:
      - OLLAMA_BASE_URL=http://ollama:11434
    volumes:
      - webui_data:/app/backend/data
    depends_on:
      - ollama
    restart: unless-stopped

  chroma:
    image: chromadb/chroma
    container_name: chroma
    ports:
      - "8001:8000"
    volumes:
      - chroma_data:/chroma/chroma
    environment:
      - ANONYMIZED_TELEMETRY=FALSE
    restart: unless-stopped

volumes:
  ollama_data:
  webui_data:
  chroma_data:

# Start all services
docker compose up -d

# Pull model inside ollama container
docker exec ollama ollama pull qwen2.5
docker exec ollama ollama pull nomic-embed-text

# Check all services
docker compose ps

# View logs
docker compose logs -f ollama

[+] Running 4/4
 ✔ Network ollama_default  Created
 ✔ Container ollama        Started
 ✔ Container open-webui    Started
 ✔ Container chroma        Started

# docker-compose.prod.yml
version: "3.8"

services:
  ollama:
    image: ollama/ollama
    container_name: ollama
    ports:
      - "11434:11434"
    volumes:
      - /data/ollama/models:/root/.ollama
    environment:
      - OLLAMA_HOST=0.0.0.0:11434
      - OLLAMA_KEEP_ALIVE=30m
      - OLLAMA_NUM_PARALLEL=4
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
        limits:
          memory: 16G
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:11434/api/tags"]
      interval: 30s
      timeout: 10s
      retries: 3

  app:
    build: ./app
    container_name: supportbot
    ports:
      - "8000:8000"
    environment:
      - OLLAMA_HOST=http://ollama:11434
    depends_on:
      ollama:
        condition: service_healthy
    restart: unless-stopped

networks:
  default:
    name: supportbot-net

# Verify configuration file syntax
docker compose config --quiet && echo "✅ Configuration file syntax is correct"
# Output: ✅ Configuration file syntax is correct

# ============================================
# Comprehensive: SupportBot full-stack Docker
# Ollama + FastAPI + Chroma + Open WebUI
# ============================================

# docker-compose.yml
version: "3.8"

services:
  ollama:
    image: ollama/ollama
    container_name: ollama
    ports:
      - "11434:11434"
    volumes:
      - ollama_models:/root/.ollama
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:11434/api/tags || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 5
    restart: unless-stopped

  init-models:
    image: curlimages/curl
    container_name: init-models
    depends_on:
      ollama:
        condition: service_healthy
    command: >
      sh -c "
        curl -s http://ollama:11434/api/pull -d '{\"name\":\"qwen2.5\"}' &&
        curl -s http://ollama:11434/api/pull -d '{\"name\":\"nomic-embed-text\"}' &&
        curl -s http://ollama:11434/api/pull -d '{\"name\":\"llava\"}'
      "

  chroma:
    image: chromadb/chroma
    container_name: chroma
    ports:
      - "8001:8000"
    volumes:
      - chroma_data:/chroma/chroma
    environment:
      - ANONYMIZED_TELEMETRY=FALSE
    restart: unless-stopped

  supportbot:
    build:
      context: ./app
      dockerfile: Dockerfile
    container_name: supportbot
    ports:
      - "8000:8000"
    environment:
      - OLLAMA_HOST=http://ollama:11434
      - CHROMA_HOST=http://chroma:8000
      - EMBED_MODEL=nomic-embed-text
      - CHAT_MODEL=qwen2.5
    depends_on:
      ollama:
        condition: service_healthy
      chroma:
        condition: service_started
    restart: unless-stopped

  webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: webui
    ports:
      - "3000:8080"
    environment:
      - OLLAMA_BASE_URL=http://ollama:11434
    volumes:
      - webui_data:/app/backend/data
    depends_on:
      - ollama
    restart: unless-stopped

volumes:
  ollama_models:
  chroma_data:
  webui_data:

#!/bin/bash
# Deploy SupportBot stack

# Start all services
docker compose up -d

# Wait for Ollama to be healthy
echo "Waiting for Ollama to be ready..."
until curl -s http://localhost:11434/api/tags > /dev/null 2>&1; do
    sleep 2
done
echo "Ollama is ready!"

# Pull required models
docker exec ollama ollama pull qwen2.5
docker exec ollama ollama pull nomic-embed-text

# Verify all services
docker compose ps
echo "SupportBot stack deployed!"
echo "  Ollama API:  http://localhost:11434"
echo "  SupportBot:  http://localhost:8000"
echo "  WebUI:       http://localhost:3000"
echo "  Chroma:      http://localhost:8001"

Waiting for Ollama to be ready...
Ollama is ready!
NAME                IMAGE                              STATUS
ollama              ollama/ollama                      Up (healthy)
chroma              chromadb/chroma                    Up
supportbot          custom/app                         Up
webui               ghcr.io/open-webui/open-webui      Up
SupportBot stack deployed!
  Ollama API:  http://localhost:11434
  SupportBot:  http://localhost:8000
  WebUI:       http://localhost:3000
  Chroma:      http://localhost:8001