deepflow部署

文章主要介绍如何在linux上部署deepflow

环境要求

• Python 3.12+
• Node.js 22+
• 足够的内存和GPU资源（建议16GB内存以上）

配置环境

# install Node.js 22 curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - sudo apt-get install -y nodejs # install uv curl -LsSf https://astral.sh/uv/install.sh | sh

下载deepflow以及创建需要的环境

# clone 仓库 git clone https://github.com/bytedance/deer-flow.git cd deer-flow # create anaconda环境 conda create --prefix=/yourpath/envs/deerflow python=3.12 # activate anaconda环境 conda activate /yourpath/envs/deerflow

生成本地配置文件

在项目根目录（deer-flow/）执行：

make config

配置.env(该文件为隐藏文件)

# 使用vim编辑器打开.env vim .env

使用tavily

或查看文档（介绍info quest）

https://docs.byteplus.com/en/docs/InfoQuest/What_is_Info_Quest

以下为tavily的网址，需注册并生成apikey

https://www.tavily.com/

此处提前配置两个密钥，因为作者是使用tavily(有免费额度)和deepseek，所以需要这两个密钥

TAVILY_API_KEY=your-Tavily-api-key # Jina API Key # JINA_API_KEY=your-jina-api-key # InfoQuest API Key # INFOQUEST_API_KEY=your-infoquest-api-key # CORS Origins (comma-separated) - e.g., http://localhost:3000,http://localhost:3001 # CORS_ORIGINS=http://localhost:3000 # Optional: # FIRECRAWL_API_KEY=your-firecrawl-api-key # VOLCENGINE_API_KEY=your-volcengine-api-key # OPENAI_API_KEY=your-openai-api-key # GEMINI_API_KEY=your-gemini-api-key DEEPSEEK_API_KEY=your-deepseek-api-key # NOVITA_API_KEY=your-novita-api-key # OpenAI-compatible, see https://novita.ai # MINIMAX_API_KEY=your-minimax-api-key # OpenAI-compatible, see https://platform.minimax.io # VLLM_API_KEY=your-vllm-api-key # OpenAI-compatible # FEISHU_APP_ID=your-feishu-app-id # FEISHU_APP_SECRET=your-feishu-app-secret # SLACK_BOT_TOKEN=your-slack-bot-token # SLACK_APP_TOKEN=your-slack-app-token # TELEGRAM_BOT_TOKEN=your-telegram-bot-token # Enable LangSmith to monitor and debug your LLM calls, agent runs, and tool executions. # LANGSMITH_TRACING=true # LANGSMITH_ENDPOINT=https://api.smith.langchain.com # LANGSMITH_API_KEY=your-langsmith-api-key # LANGSMITH_PROJECT=your-langsmith-project # GitHub API Token # GITHUB_TOKEN=your-github-token # WECOM_BOT_ID=your-wecom-bot-id # WECOM_BOT_SECRET=your-wecom-bot-secret

配置config.yaml(以deepseek为例)

- name: deepseek-v3 display_name: DeepSeek V3 (Thinking) use: deerflow.models.patched_deepseek:PatchedChatDeepSeek model: deepseek-reasoner api_key: $DEEPSEEK_API_KEY timeout: 600.0 max_retries: 2 max_tokens: 8192 supports_thinking: true supports_vision: false # DeepSeek V3 does not support vision when_thinking_enabled: extra_body: thinking: type: enabled when_thinking_disabled: extra_body: thinking: type: disabled

也就是放开这部分的注释

运行应用（确保nodejs 22+，uv）

安装nvm

# install nvm curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash # load environment export NVM_DIR="$HOME/.nvm" [ -s "$NVM_DIR/nvm.sh" ] && \. "$NVM_DIR/nvm.sh" # verify nvm -v # install nodejs NVM_NODEJS_ORG_MIRROR=https://npmmirror.com/mirrors/node/ nvm install 22 nvm use 22 # install pnpm corepack enable corepack prepare pnpm@latest --activate # fresh environment source ~/.bashrc # install nginx sudo apt update sudo apt install -y nginx

若出现版本问题，可以使用下面的代码强行安装并切换nodejs版本

NVM_NODEJS_ORG_MIRROR=https://npmmirror.com/mirrors/node/ nvm install v22.14.0

以及安装必要的uv

pip install uv

检查依赖环境：

make check

安装依赖

make install

安装完毕后

启动服务：

make dev

部署完毕