# How to build | 如何构建: docker build -t gpt-academic --network=host  -f Dockerfile+ChatGLM .
# How to run | 如何运行 (1) 直接运行: docker run --rm -it --net=host --gpus=all gpt-academic
# How to run | 如何运行 (2) 我想运行之前进容器做一些调整: docker run --rm -it --net=host --gpus=all gpt-academic bash
 
# 从NVIDIA源，从而支持显卡运损（检查宿主的nvidia-smi中的cuda版本必须>=11.3）
FROM nvidia/cuda:11.3.1-runtime-ubuntu20.04
ARG useProxyNetwork=''
RUN apt-get update
RUN apt-get install -y curl proxychains curl 
RUN apt-get install -y git python python3 python-dev python3-dev --fix-missing

# 配置代理网络（构建Docker镜像时使用）
# # comment out below if you do not need proxy network | 如果不需要翻墙 - 从此行向下删除
# RUN $useProxyNetwork curl cip.cc
# RUN sed -i '$ d' /etc/proxychains.conf
# RUN sed -i '$ d' /etc/proxychains.conf
# RUN echo "socks5 127.0.0.1 10880" >> /etc/proxychains.conf
# ARG useProxyNetwork=proxychains
# # comment out above if you do not need proxy network | 如果不需要翻墙 - 从此行向上删除


# use python3 as the system default python
RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8

# 下载分支
WORKDIR /gpt
RUN $useProxyNetwork git clone https://github.com/binary-husky/chatgpt_academic.git -b v3.1
WORKDIR /gpt/chatgpt_academic
RUN $useProxyNetwork python3 -m pip install -r requirements.txt
RUN $useProxyNetwork python3 -m pip install -r request_llm/requirements_chatglm.txt
RUN $useProxyNetwork python3 -m pip install torch --extra-index-url https://download.pytorch.org/whl/cu113

# 预热CHATGLM参数（非必要 可选步骤）
RUN echo ' \n\
from transformers import AutoModel, AutoTokenizer \n\
chatglm_tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) \n\
chatglm_model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).float() ' >> warm_up_chatglm.py
RUN python3 -u warm_up_chatglm.py

# 禁用缓存，确保更新代码
ADD "https://www.random.org/cgi-bin/randbyte?nbytes=10&format=h" skipcache
RUN $useProxyNetwork git pull

# 为chatgpt-academic配置代理和API-KEY （非必要 可选步骤）
# 可同时填写多个API-KEY，支持openai的key和api2d的key共存，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey1,fkxxxx-api2dkey2"
# LLM_MODEL 是选择初始的模型
# LOCAL_MODEL_DEVICE 是选择chatglm等本地模型运行的设备，可选 cpu 和 cuda
RUN echo ' \n\
API_KEY = "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \n\
USE_PROXY = True \n\
LLM_MODEL = "chatglm" \n\
LOCAL_MODEL_DEVICE = "cpu" \n\
proxies = { "http": "socks5h://localhost:10880", "https": "socks5h://localhost:10880", } ' >> config_private.py

# 启动
CMD ["python3", "-u", "main.py"]