Build a WeCom Intelligent Bot AI Bot with Qwen
Step-by-step guide to running a Qwen-powered AI bot on WeCom Intelligent Bot with LangBot: model setup, bot credentials, networking, testing and troubleshooting.
This recipe puts a Qwen model behind a WeCom Intelligent Bot bot. LangBot receives messages from WeCom Intelligent Bot, runs them through a pipeline, and sends the answer back, so you do not write any platform code.
Use Alibaba Cloud's Qwen models through Model Studio (DashScope) with LangBot's built-in Agent.
What you need
- A running LangBot instance: LangBot Cloud (no server needed) or a self-hosted deployment with Docker or
uvx langbot. - A Qwen account or server you can call from LangBot.
- A WeCom intelligent bot in long connection API mode: its BotID and long-connection Secret. One-click setup can fill both.
Networking
Long connection mode needs no public callback URL. The alternative callback-URL mode does, and the two modes cannot be used at the same time.
1. Add the Qwen model
- Create an API key in the Aliyun Bailian (DashScope) console.
- In LangBot, open Models, add an LLM model with the provider set to Aliyun Bailian (DashScope) and request URL
https://dashscope.aliyuncs.com/compatible-mode/v1, then paste the API key and the model ID. - Enable Tool Use if the model supports function calling; MCP tools, Skills and the sandbox need it.
- Use a Qwen model ID listed in Model Studio.
2. Create a pipeline
Open Pipelines in the LangBot WebUI, create a pipeline (or edit the default one) and set AI as follows.
| Field | Value |
|---|---|
| Runner | Local Agent (built-in Agent) |
| Model | The model you just added. You can add fallback models. |
| Prompt | Instructions: who the bot is, tone, what it must not do. |
| Knowledge Bases | Optional. Attach a knowledge base so answers come from your documents. |
3. Create the WeCom Intelligent Bot bot
- Create a bot with the WeCom Intelligent Bot adapter and use One-Click Setup, or create the bot in WeCom, switch its API mode to long connection and enter the BotID and Secret.
- Set the bot's visibility scope so the right people can use it, then save and enable.
4. Bind and test
Open the bot, select the pipeline you created, save and make sure the bot is enabled.
Find the bot in the WeCom client, chat with it directly, then add it to a group chat and mention it.
Troubleshooting
- International accounts use a different DashScope endpoint; copy the OpenAI-compatible URL shown in your console.
- The long-connection Secret differs from the callback Token/EncodingAESKey. Switching the API mode to callback URL invalidates existing long connections.
- Check Monitoring in the WebUI: every message, pipeline run and error is recorded there.
FAQ
Do I need a server with a public IP for WeCom Intelligent Bot?
No. Long connection mode needs no public callback URL. The alternative callback-URL mode does, and the two modes cannot be used at the same time.
Does the WeCom Intelligent Bot bot support streaming replies?
Yes. Enable streaming on the bot; the AI back end must also stream. See the platform feature matrix for details.
Can the same Qwen setup serve other platforms too?
Yes. A pipeline can be bound to many bots, so one configuration can answer on several platforms at once.
Related guides
- Full WeCom Intelligent Bot setup guide
- Model configuration
- Other AI back ends on WeCom Intelligent Bot: Dify · n8n · Coze · Langflow · DeepSeek
- Qwen on other platforms: Telegram · Discord · Slack · Lark (Feishu) · DingTalk · WeCom (internal app)
Build a WeCom (internal app) AI Bot with Qwen
Step-by-step guide to running a Qwen-powered AI bot on WeCom (internal app) with LangBot: model setup, bot credentials, networking, testing and troubleshooting.
Build a WeCom Customer Service AI Bot with Qwen
Step-by-step guide to running a Qwen-powered AI bot on WeCom Customer Service with LangBot: model setup, bot credentials, networking, testing and troubleshooting.