Connect Coze to a website chat widget
Step-by-step guide to running your Coze app as a a website chat widget bot with LangBot: Coze setup, bot credentials, networking, testing and troubleshooting.
This recipe puts your Coze app behind a a website chat widget bot. LangBot receives messages from a website chat widget, runs them through a pipeline, and sends the answer back, so you do not write any platform code.
Coze builds agents visually. LangBot calls a Coze bot through the Coze API, so you can reach platforms Coze does not publish to and keep one bot across many channels.
What you need
- A running LangBot instance: LangBot Cloud (no server needed) or a self-hosted deployment with Docker or
uvx langbot. - A Coze account or instance that LangBot can reach over the network.
- Nothing from a third party. Optionally a Cloudflare Turnstile site key and secret key for anti-abuse.
Networking
Visitors' browsers talk to LangBot directly, so LangBot must be reachable at a public HTTPS address. LangBot Cloud includes one.
1. Prepare Coze
- In the Coze developer console, create a token under API Management (coze.com offers Personal Access Tokens; coze.cn also supports service credentials).
- Publish your agent with the API channel selected and copy its
bot_id.
2. Create a pipeline
Open Pipelines in the LangBot WebUI, create a pipeline (or edit the default one) and set AI as follows. If the runner is not listed, install the official runner plugin from Plugins or the LangBot Space marketplace.
| Field | Value |
|---|---|
| Runner | Coze (official Coze Agent runner plugin) |
| API Key | The Coze token |
| Bot ID | The agent's bot_id |
| API Base URL | https://api.coze.cn for coze.cn or https://api.coze.com for coze.com |
3. Create the a website chat widget bot
- Create a bot with the Web Page Bot adapter and bind a pipeline.
- Copy the embed code into your site and replace
localhost:5300with LangBot's public address.
4. Bind and test
Open the bot, select the pipeline you created, save and make sure the bot is enabled.
Open the page with the widget and start a conversation.
Troubleshooting
- Calls fail: check the token and
bot_idfor extra spaces, that the agent was published with the API channel, and that the base URL matches the Coze site. - The widget does not load: the embed code still points at
localhost, or the LangBot address is not served over HTTPS. - 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 a website chat widget?
Yes, or use LangBot Cloud. Visitors' browsers talk to LangBot directly, so LangBot must be reachable at a public HTTPS address. LangBot Cloud includes one.
Does the a website chat widget 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 Coze 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 a website chat widget setup guide
- Full Coze runner guide
- Other AI back ends on a website chat widget: Dify · n8n · Langflow · DeepSeek · OpenAI (ChatGPT models)
- Coze on other platforms: Telegram · Discord · Slack · Lark (Feishu) · DingTalk · WeCom (internal app)
Connect Coze to Mattermost
Step-by-step guide to running your Coze app as a Mattermost bot with LangBot: Coze setup, bot credentials, networking, testing and troubleshooting.
Connect Langflow to Telegram
Step-by-step guide to running your Langflow app as a Telegram bot with LangBot: Langflow setup, bot credentials, networking, testing and troubleshooting.
