# AI Full-Stack Development Quick Start Guide

A hands-on quick-start guide for using the DeepSeek API, covering environment setup, an OpenAI-compatible client, and optional local GPU deployment with CUDA, Miniconda and Jupyter Lab.

This repository is a getting-started guide for building applications on the DeepSeek API. It walks through cloning the repository, setting up a Python 3.13 environment with Miniconda, and installing Jupyter Lab for interactive development, since the accompanying material is organized as notebooks.

It documents an optional path for privacy-sensitive or private deployments: installing the CUDA toolkit and GPU driver so models can run locally, since the DeepSeek API is compatible with the OpenAI SDK format and can be swapped for a self-hosted, OpenAI-compatible server. It also covers configuring a DeepSeek API key as an environment variable and setting up Docker and Docker Compose for related self-hosted tools such as Ollama, Dify and LangBot.

Website: https://github.com/DjangoPeng/deepseek-quickstart