Build a WeChat Official Account AI Bot with Ollama

This recipe puts a Ollama model behind a WeChat Official Account bot. LangBot receives messages from WeChat Official Account, 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.
• A WeChat Official Account or Service Account: AppID, AppSecret, a server Token and EncodingAESKey, with LangBot's server IP in the IP whitelist.

Networking

Official Accounts require a public domain with HTTPS and must get a response within 5 seconds. Slow AI replies need passive or auto mode. LangBot Cloud includes a public domain.

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 WeChat Official Account bot

1. Create a bot with the WeChat Official Account adapter and choose a reply mode: drop (reply within the 5-second callback), passive or auto (answer later through the customer service API when the account is enterprise-verified).
2. Paste the bot's callback URL into the account's server configuration and save.

4. Bind and test

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

Follow the account in WeChat and send it a message.

Troubleshooting

• Small local models may not support tool calling well; leave Tool Use off for models that do not support it.
• Users see the loading message but no answer: in passive mode (or after auto falls back) the user must send another message to retrieve the queued answer.
• Customer service messages require an enterprise-verified account; identity verification alone is not enough.
• 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 WeChat Official Account?

Yes, or use LangBot Cloud. Official Accounts require a public domain with HTTPS and must get a response within 5 seconds. Slow AI replies need passive or auto mode. LangBot Cloud includes a public domain.

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