Integrating DeepSeek AI with a WeChat Public Account: A Step‑by‑Step Backend Tutorial
This tutorial walks beginners through obtaining a DeepSeek API key, setting up an Alibaba Cloud ECS instance, configuring the server and WeChat public platform, installing required Python dependencies, editing configuration files, and finally running the chatbot so the public account can interact with the DeepSeek large‑language model.
1. Basic Principles & Risks
The guide uses a GitHub open‑source project to bridge DeepSeek API and the WeChat public‑account API; messages received by the account are forwarded to a cloud server, processed by the AI model, and the replies are sent back. Users are warned about potential mis‑configuration risks for both WeChat and the cloud server.
2. Obtaining a DeepSeek API Key
Visit https://platform.deepseek.com/ , register, create an API key on the dashboard and copy it for later use.
3. Getting WeChat Public‑Platform Credentials
Log in to the WeChat public platform, become a developer, and copy the AppID , AppSecret , generate an AESKey , and note the Token .
4. Creating a Cloud Server (Alibaba Cloud ECS)
Register on Alibaba Cloud , apply for the free ECS trial (Hong Kong region, 2 CPU + 2 GiB, Ubuntu 22.04), open port 80 in the security group, and obtain the public IP address.
5. Project Code Configuration
5.1 Clone the Project
git clone https://github.com/zhayujie/chatgpt-on-wechat.git5.2 Install Dependencies
pip3 install -r ./chatgpt-on-wechat/requirements.txt pip3 install -r ./chatgpt-on-wechat/requirements-optional.txt5.3 Edit the Configuration File
Create config.json with the collected credentials, e.g.:
{
"channel_type": "wechatmp",
"model": "deepseek-chat",
"open_ai_api_key": "YOUR_DEEPSEEK_API_KEY",
"open_ai_api_base": "https://api.deepseek.com/v1",
"wechatmp_app_id": "YOUR_APPID",
"wechatmp_app_secret": "YOUR_APPSECRET",
"wechatmp_aes_key": "YOUR_AESKEY",
"wechatmp_token": "YOUR_TOKEN",
"wechatmp_port": 80,
"conversation_max_tokens": 3000,
"temperature": 0.8,
"subscribe_msg": "Thanks for following! The public account is now connected to DeepSeek."
}5.4 Save the File
Use vi config.json , press I to edit, paste the JSON, then Esc :wq to save and quit.
5.5 Run the Project
sudo python3 app.pyFor unattended operation, use:
(cd chatgpt-on-wechat && nohup python3 app.py &) ; tail -f ./chatgpt-on-wechat/nohup.out6. WeChat Public‑Platform Configuration
In the WeChat console set the server URL to http://YOUR_SERVER_IP/wx , and fill the Token and AESKey with the same values from config.json . Choose “compatible mode”, submit, enable the configuration and verify success.
7. Post‑Deployment Tips
Periodically restart the ECS instance and re‑run the start command.
Customize the configuration (model, prompts, etc.) after understanding each field.
Monitor Alibaba Cloud free‑trial quota and DeepSeek API usage to avoid unexpected charges.
Following these steps will connect your WeChat public account to the DeepSeek large‑language model, enabling AI‑driven conversations.
Architect's Guide
Dedicated to sharing programmer-architect skills—Java backend, system, microservice, and distributed architectures—to help you become a senior architect.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.