docker-compose.yml

version: "3.6"

services:
        glm3_api:
                image: python:3.10.13-slim
                restart: unless-stopped
                working_dir: /glm3
                container_name: glm3_api
                env_file: ./.env
                networks:
                        - v_glm3
                deploy:
                        resources:
                                reservations:
                                        devices:
                                                - driver: nvidia
                                                  count: 1
                                                  capabilities: [gpu]
                environment:
                        - MODEL_PATH=/models/chatglm3-6b
                        - EMBEDDING_PATH=/models/bge-large-zh-v1.5
                        - TZ=Asia/Shanghai
                        - PYTHONDONTWRITEBYTECODE=1
                        - PYTHONUNBUFFERED=1
                        - DOCKER=True
                ports:
                        - 8100:8000
                volumes:
                        - ./:/glm3
                        - ${LOCAL_MODEL_PATH}:/models/chatglm3-6b
                        - ${LOCAL_EMBEDDING_MODEL_PATH}:/models/bge-large-zh-v1.5
                command:
                        - sh
                        - -c
                        - |
                          sed -i s/deb.debian.org/mirrors.tencentyun.com/g /etc/apt/sources.list
                          sed -i s/security.debian.org/mirrors.tencentyun.com/g /etc/apt/sources.list
                          apt-get update
                          python -m pip install -i  https://mirror.sjtu.edu.cn/pypi/web/simple --upgrade pip
                          pip install -r requirements.txt -i  https://pypi.tuna.tsinghua.edu.cn/simple
                          python api_server.py
networks:
        v_glm3:
                driver: bridge