Build a WeCom Customer Service AI Bot with Ollama

This recipe puts a Ollama model behind a WeCom Customer Service bot. LangBot receives messages from WeCom Customer Service, runs them through a pipeline, and sends the answer back, so you do not write any platform code.

Run open models locally with Ollama and serve them through LangBot's built-in Agent, so conversations never leave your machines.

What you need

• A running LangBot instance: LangBot Cloud (no server needed) or a self-hosted deployment with Docker or uvx langbot.
• A Ollama account or server you can call from LangBot.
• WeCom Customer Service (WeChat Kefu) with API access: Corporate ID, Secret, and a callback Token and EncodingAESKey.

Networking

Customer Service delivers events to a callback URL, so LangBot needs a public HTTPS address. LangBot Cloud includes one.

1. Add the Ollama model

1. Install Ollama and pull a model (for example ollama pull followed by the model name).
2. In LangBot, open Models and add an LLM model with the provider set to Ollama and the request URL pointing at your Ollama server (by default port 11434).
3. If LangBot runs in Docker, localhost is the container itself: use the host's address (for example host.docker.internal) instead.

2. Create a pipeline

Open Pipelines in the LangBot WebUI, create a pipeline (or edit the default one) and set AI as follows.

3. Create the WeCom Customer Service bot

1. In WeCom Customer Service Developer Settings, generate the Token and EncodingAESKey and enter them with the Corporate ID in a bot using the WeCom Customer Service adapter.
2. Enable the bot, paste its webhook callback URL into the admin console, then fill in the Secret and restart the bot. Generate the customer service link or QR code users will open.

4. Bind and test

Open the bot, select the pipeline you created, save and make sure the bot is enabled.

Open the customer service link or scan the QR code in WeChat and send a message.

Troubleshooting

• Small local models may not support tool calling well; leave Tool Use off for models that do not support it.
• Welcome messages can only be sent when WeChat supplies a welcome_code, and only once before it expires.
• 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 Customer Service?

Yes, or use LangBot Cloud. Customer Service delivers events to a callback URL, so LangBot needs a public HTTPS address. LangBot Cloud includes one.

Does the WeCom Customer Service bot support streaming replies?

Check the platform feature matrix for what this platform supports. Replies are delivered once the AI back end has finished.

Can the same Ollama 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 Customer Service setup guide
• Model configuration
• Other AI back ends on WeCom Customer Service: Dify · n8n · Coze · Langflow · DeepSeek
• Ollama on other platforms: Telegram · Discord · Slack · Lark (Feishu) · DingTalk · WeCom (internal app)