buildfastwithai /
gen-ai-experiments
Collection of Jupyter notebooks is designed to provide you with a comprehensive guide to various AI tools and technologies
86/100 healthLoading repository data…
DjangoPeng / repository
A comprehensive guide to understanding and implementing large language models with hands-on examples using LangChain for GenAI applications.
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
本项目旨在为所有对大型语言模型及其在生成式人工智能(AIGC)场景中应用的人们提供一站式学习资源。通过提供理论基础,开发基础,和实践示例,该项目对这些前沿主题提供了全面的指导。
大语言模型的理论和开发基础:深入探讨BERT和GPT系列等大型语言模型的内部工作原理,包括它们的架构、训练方法、应用等。
基于OpenAI的二次开发:OpenAI的Embedding、GPT-3.5、GPT-4模型的快速上手和应用,以及函数调用(Function Calling)和ChatGPT插件等最佳实践
使用LangChain进行GenAI应用开发:通过实例和教程,利用LangChain开发GenAI应用程序,展示大型语言模型(AutoGPT、RAG-chatbot、机器翻译)的实际应用。
LLM技术栈与生态:数据隐私与法律合规性,GPU技术选型指南,Hugging Face快速入门指南,ChatGLM的使用。
你可以通过克隆此仓库到你的本地机器来开始:
git clone https://github.com/DjangoPeng/openai-quickstart.git
然后导航至目录,并按照单个模块的指示开始操作。
本项目使用 Python v3.10 开发,完整 Python 依赖软件包见requirements.txt。
关键依赖的官方文档如下:
以下是详细的安装指导(以 Ubuntu 操作系统为例):
mkdir -p ~/miniconda3
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda3/miniconda.sh
bash ~/miniconda3/miniconda.sh -b -u -p ~/miniconda3
rm -rf ~/miniconda3/miniconda.sh
安装完成后,建议新建一个 Python 虚拟环境,命名为 langchain。
conda create -n langchain python=3.10
# 激活环境
conda activate langchain
之后每次使用需要激活此环境。
pip install -r requirements.txt
根据你使用的命令行工具,在 ~/.bashrc 或 ~/.zshrc 中配置 OPENAI_API_KEY 环境变量:
export OPENAI_API_KEY="xxxx"
上述开发环境安装完成后,使用 Miniconda 安装 Jupyter Lab:
conda install -c conda-forge jupyterlab
使用 Jupyter Lab 开发的最佳实践是后台常驻,下面是相关配置(以 root 用户为例):
# 生成 Jupyter Lab 配置文件,
jupyter lab --generate-config
打开上面执行输出的jupyter_lab_config.py配置文件后,修改以下配置项:
c.ServerApp.allow_root = True # 非 root 用户启动,无需修改
c.ServerApp.ip = '*'
使用 nohup 后台启动 Jupyter Lab
$ nohup jupyter lab --port=8000 --NotebookApp.token='替换为你的密码' --notebook-dir=./ &
Jupyter Lab 输出的日志将会保存在 nohup.out 文件(已在 .gitignore中过滤)。
完整文档请移步:大模型(LLMs)应用开发快速入门指南课程大纲
贡献是使开源社区成为学习、激励和创造的惊人之处。非常感谢你所做的任何贡献。如果你有任何建议或功能请求,请先开启一个议题讨论你想要改变的内容。
该项目根据Apache-2.0许可证的条款进行许可。详情请参见LICENSE文件。
Django Peng - pjt73651@email.com
项目链接: https://github.com/DjangoPeng/openai-quickstart
Selected from shared topics, language and repository description—not editorial ratings.
buildfastwithai /
Collection of Jupyter notebooks is designed to provide you with a comprehensive guide to various AI tools and technologies
86/100 healthprincepal9120 /
AI Learning: A comprehensive repository for Artificial Intelligence and Machine Learning resources, primarily using Jupyter Notebooks and Python. Explore tutorials, projects, and guides covering foundational to advanced concepts in AI, ML, DL and Gen/Agentic Ai.
55/100 healthNimraAslamkhan /
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow is a comprehensive machine learning project that guides users through the implementation of various algorithms and techniques, from basic linear regression to complex deep learning models. This repository includes code examples and Jupyter notebooks that demonstrate the concepts cov
57/100 healthfarzadasgari /
A comprehensive Machine Learning course, guiding beginners to build and train machine learning models. It includes Jupyter Notebooks, exercises, and resources for a structured learning experience. (Work in Progress!)
77/100 healthIn this comprehensive guide, we’ll walk you through two reliable methods to get Jupyter Notebook running on Android
58/100 healthDanNBullock /
A collection of jupyter notebooks designed to provide a comprehensive exploration of concepts related to white matter segmentation.
26/100 health