Skip to content

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

1.3 KB
Raw Blame
services:
  # Hardened stack: for testing the proxy under non-root, read-only, proxy-enforced constraints.
  # Keep this file focused on hardening/QA scenarios; leave the main docker-compose.yml for default dev usage.
  litellm:
    build:
      context: .
      dockerfile: docker/Dockerfile.non_root
      target: runtime
    depends_on:
      - squid
    user: "101:101"
    group_add:
      - "2345"
    read_only: true
    cap_drop:
      - ALL
    security_opt:
      - no-new-privileges:true
    tmpfs:
      - /app/cache:rw,noexec,nosuid,nodev,size=128m,uid=101,gid=101,mode=1777
      - /app/migrations:rw,noexec,nosuid,nodev,size=64m,uid=101,gid=101,mode=1777
    volumes:
      - ./proxy_server_config.yaml:/app/config.yaml:ro
    environment:
      LITELLM_NON_ROOT: "true"
      PRISMA_BINARY_CACHE_DIR: "/app/cache/prisma-python/binaries"
      XDG_CACHE_HOME: "/app/cache"
      LITELLM_MIGRATION_DIR: "/app/migrations"
      HTTP_PROXY: "http://squid:3128"
      HTTPS_PROXY: "http://squid:3128"
      NO_PROXY: "localhost,127.0.0.1,db"
    command:
      - "--port"
      - "4000"
      - "--config"
      - "/app/config.yaml"
  squid:
    image: sameersbn/squid:3.5.27-2
    restart: unless-stopped
    ports:
      - "3128:3128"
    tmpfs:
      - /var/spool/squid:rw,noexec,nosuid,nodev,size=64m
      - /var/log/squid:rw,noexec,nosuid,nodev,size=16m