如何使用AI 网关(LiteLLM): 统一管理AI大语言模型接入

mkdir litellm-server
cd litellm-server

echo 'LITELLM_MASTER_KEY="sk-1234"' > .env
echo 'LITELLM_SALT_KEY="sk-1234"' > .env

source .env

model_list:
  - model_name: gpt-4o-mini
    litellm_params:
      model: gpt-4o-mini
      api_key: os.environ/OPENROUTER_API_KEY
      api_base: https://openrouter.ai/api/v1
  - model_name: "gpt-4o"
    litellm_params:
      model: "openrouter/openai/gpt-4o"
      api_base: "https://openrouter.ai/api/v1"
      api_key: "os.environ/OPENROUTER_API_KEY"

general_settings:
  store_model_in_db: true
  store_prompts_in_spend_logs: true

version: "3.11"
services:
  litellm:
    build:
      context: .
      args:
        target: runtime
    image: ghcr.io/berriai/litellm:main-stable
    #########################################
    ## Uncomment these lines to start proxy with a config.yaml file ##
    volumes:
      - ./config.yaml:/app/config.yaml #<<- this is missing in the docker-compose file currently
    command:
      - "--config=/app/config.yaml"
    ##############################################
    ports:
      - "4000:4000" # Map the container port to the host, change the host port if necessary
    environment:
        DATABASE_URL: "postgresql://llmproxy:dbpassword9090@db:5432/litellm"
        STORE_MODEL_IN_DB: "True" # allows adding models to proxy via UI
    env_file:
      - .env # Load local .env file
    depends_on:
      - db  # Indicates that this service depends on the 'db' service, ensuring 'db' starts first
    healthcheck:  # Defines the health check configuration for the container
      test: [ "CMD", "curl", "-f", "http://localhost:4000/health/liveliness || exit 1" ]  # Command to execute for health check
      interval: 30s  # Perform health check every 30 seconds
      timeout: 10s   # Health check command times out after 10 seconds
      retries: 3     # Retry up to 3 times if health check fails
      start_period: 40s  # Wait 40 seconds after container start before beginning health checks

  db:
    image: postgres:16
    restart: always
    environment:
      POSTGRES_DB: litellm
      POSTGRES_USER: llmproxy
      POSTGRES_PASSWORD: dbpassword9090
    ports:
      - "54321:5432"
    volumes:
      - postgres_data:/var/lib/postgresql/data  # Persists Postgres data across container restarts
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -d litellm -U llmproxy"]
      interval: 1s
      timeout: 5s
      retries: 10

  prometheus:
    image: prom/prometheus
    volumes:
      - prometheus_data:/prometheus
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
    ports:
      - "9099:9090"
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=15d'
    restart: always

volumes:
  prometheus_data:
    driver: local
  postgres_data:
    name: litellm_postgres_data  # Named volume for Postgres data persistence

# 启动服务
docker-compose up -d

# 查看服务状态
docker-compose ps

# 查看日志
docker-compose logs -f

export $LITELLM_API_KEY=xxxx 
curl http://localhost:4000/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LITELLM_API_KEY" \
  -d '{
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "system",
      "content": "你是一个助手. 叫 李四三"
    },
    {
      "role": "user",
      "content": "how are you? what your name?"
    }
  ]
}'