chunzhi/chatgpt_academic
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update dockerfiles

Browse Source
This commit is contained in:
binary-husky 2023-09-06 23:33:15 +08:00
parent 9a5ee86434
commit 7855325ff9
4 changed files with 7 additions and 148 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
docs/Dockerfile+ChatGLM
View File

@ -1,62 +1,2 @@
# How to build | 如何构建: docker build -t gpt-academic --network=host -f Dockerfile+ChatGLM .
# How to run | (1) 我想直接一键运行（选择0号GPU）: docker run --rm -it --net=host --gpus \"device=0\" gpt-academic
# How to run | (2) 我想运行之前进容器做一些调整（选择1号GPU）: docker run --rm -it --net=host --gpus \"device=1\" gpt-academic bash
# 此Dockerfile不再维护，请前往docs/GithubAction+ChatGLM+Moss
# 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
# 在这里填写主机的代理协议（用于从github拉取代码）
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pytorch
RUN $useProxyNetwork python3 -m pip install torch --extra-index-url https://download.pytorch.org/whl/cu113
# 下载分支
WORKDIR /gpt
RUN $useProxyNetwork git clone https://github.com/binary-husky/gpt_academic.git
WORKDIR /gpt/gpt_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 -r request_llm/requirements_newbing.txt
# 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
# 预热Tiktoken模块
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
# 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,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
# [说明: 以下内容与`config.py`一一对应，请查阅config.py来完成一下配置的填写]
RUN echo ' \n\
API_KEY = "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx,fkxxxxxx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \n\
USE_PROXY = True \n\
LLM_MODEL = "chatglm" \n\
LOCAL_MODEL_DEVICE = "cuda" \n\
proxies = { "http": "socks5h://localhost:10880", "https": "socks5h://localhost:10880", } ' >> config_private.py
# 启动
CMD ["python3", "-u", "main.py"]

60
docs/Dockerfile+JittorLLM
View File

@ -1,59 +1 @@
# How to build | 如何构建: docker build -t gpt-academic-jittor --network=host -f Dockerfile+ChatGLM .
# How to run | (1) 我想直接一键运行（选择0号GPU）: docker run --rm -it --net=host --gpus \"device=0\" gpt-academic-jittor bash
# How to run | (2) 我想运行之前进容器做一些调整（选择1号GPU）: docker run --rm -it --net=host --gpus \"device=1\" gpt-academic-jittor 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 g++
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
# 在这里填写主机的代理协议（用于从github拉取代码）
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pytorch
RUN $useProxyNetwork python3 -m pip install torch --extra-index-url https://download.pytorch.org/whl/cu113
# 下载分支
WORKDIR /gpt
RUN $useProxyNetwork git clone https://github.com/binary-husky/gpt_academic.git
WORKDIR /gpt/gpt_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 -r request_llm/requirements_newbing.txt
RUN $useProxyNetwork python3 -m pip install -r request_llm/requirements_jittorllms.txt -i https://pypi.jittor.org/simple -I
# 下载JittorLLMs
RUN $useProxyNetwork git clone https://github.com/binary-husky/JittorLLMs.git --depth 1 request_llm/jittorllms
# 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
# 预热Tiktoken模块
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
# 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,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
# [说明: 以下内容与`config.py`一一对应，请查阅config.py来完成一下配置的填写]
RUN echo ' \n\
API_KEY = "sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx,fkxxxxxx-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \n\
USE_PROXY = True \n\
LLM_MODEL = "chatglm" \n\
LOCAL_MODEL_DEVICE = "cuda" \n\
proxies = { "http": "socks5h://localhost:10880", "https": "socks5h://localhost:10880", } ' >> config_private.py
# 启动
CMD ["python3", "-u", "main.py"]
# 此Dockerfile不再维护，请前往docs/GithubAction+JittorLLMs

28
docs/Dockerfile+NoLocal+Latex
View File

@ -1,27 +1 @@
# 此Dockerfile适用于“无本地模型”的环境构建，如果需要使用chatglm等本地模型，请参考 docs/Dockerfile+ChatGLM
# - 1 修改 `config.py`
# - 2 构建 docker build -t gpt-academic-nolocal-latex -f docs/Dockerfile+NoLocal+Latex .
# - 3 运行 docker run -v /home/fuqingxu/arxiv_cache:/root/arxiv_cache --rm -it --net=host gpt-academic-nolocal-latex
FROM fuqingxu/python311_texlive_ctex:latest
# 指定路径
WORKDIR /gpt
ARG useProxyNetwork=''
RUN $useProxyNetwork pip3 install gradio openai numpy arxiv rich -i https://pypi.douban.com/simple/
RUN $useProxyNetwork pip3 install colorama Markdown pygments pymupdf -i https://pypi.douban.com/simple/
# 装载项目文件
COPY . .
# 安装依赖
RUN $useProxyNetwork pip3 install -r requirements.txt -i https://pypi.douban.com/simple/
# 可选步骤，用于预热模块
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
# 启动
CMD ["python3", "-u", "main.py"]
# 此Dockerfile不再维护，请前往docs/GithubAction+NoLocal+Latex

5
docs/GithubAction+NoLocal+Latex
View File

@ -1,6 +1,6 @@
# 此Dockerfile适用于“无本地模型”的环境构建，如果需要使用chatglm等本地模型，请参考 docs/Dockerfile+ChatGLM
# - 1 修改 `config.py`
# - 2 构建 docker build -t gpt-academic-nolocal-latex -f docs/Dockerfile+NoLocal+Latex .
# - 2 构建 docker build -t gpt-academic-nolocal-latex -f docs/GithubAction+NoLocal+Latex .
# - 3 运行 docker run -v /home/fuqingxu/arxiv_cache:/root/arxiv_cache --rm -it --net=host gpt-academic-nolocal-latex
FROM fuqingxu/python311_texlive_ctex:latest
@ -10,6 +10,9 @@ WORKDIR /gpt
RUN pip3 install gradio openai numpy arxiv rich
RUN pip3 install colorama Markdown pygments pymupdf
RUN pip3 install python-docx moviepy pdfminer
RUN pip3 install nougat-ocr
RUN pip3 install aliyun-python-sdk-core==2.13.3 pyOpenSSL scipy git+https://github.com/aliyun/alibabacloud-nls-python-sdk.git
# 装载项目文件
COPY . .