# Build a DingTalk AI Bot with Gemini

Source: https://langbot.app/docs/en/recipes/gemini/dingtalk

Step-by-step guide to running a Gemini-powered AI bot on DingTalk with LangBot: model setup, bot credentials, networking, testing and troubleshooting.

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

Use Google's Gemini models with LangBot's built-in Agent, including image input when the model supports vision.

## What you need

- A running LangBot instance: [LangBot Cloud](https://space.langbot.app/cloud) (no server needed) or a [self-hosted deployment](https://langbot.app/docs/en/deploy/langbot/docker.md) with Docker or `uvx langbot`.
- A Gemini account or server you can call from LangBot.
- A DingTalk app robot (**Client ID** and **Client Secret**). The one-click setup fills both after you authorize on your phone.

## Networking

In Stream Mode LangBot connects out to DingTalk, so no public callback URL is needed.

## 1. Add the Gemini model

1. Create an API key in the Google Gemini console.
2. In LangBot, open **Models**, add an LLM model with the provider set to Google Gemini, then paste the API key and the model ID.
3. Enable **Tool Use** if the model supports function calling; MCP tools, Skills and the sandbox need it.
4. Create the key in Google AI Studio. Enable **Vision** on the model if you want the bot to read images.

## 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 DingTalk bot

1. Create a bot with the **DingTalk** adapter and use **One-Click Setup**, or create the robot manually and enter its credentials.
2. Use **Stream Mode** for event delivery. For streaming replies, import LangBot's `dingtalk_stream_card.json` card template, enable **Use Card Replies** and paste the Card Template ID.

## 4. Bind and test

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

Message the robot directly, then add it to a group and @mention it.

## Troubleshooting

- Images are ignored: enable **Vision** on the model and check that the platform adapter forwards images.
- Replies arrive as plain text instead of streaming: the card template is not imported or **Use Card Replies** is off.
- Messages do not arrive: publish the app version and check that Stream Mode is selected under event subscriptions.
- 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 DingTalk?

No. In Stream Mode LangBot connects out to DingTalk, so no public callback URL is needed.

### Does the DingTalk bot support streaming replies?

Yes. Enable streaming on the bot; the AI back end must also stream. See the [platform feature matrix](https://langbot.app/docs/en/insight/platform-features.md) for details.

### Can the same Gemini 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 DingTalk setup guide](https://langbot.app/docs/en/usage/platforms/dingtalk.md)
- [Model configuration](https://langbot.app/docs/en/usage/models/readme.md)
- Other AI back ends on DingTalk: [Dify](https://langbot.app/docs/en/recipes/dify/dingtalk.md) · [n8n](https://langbot.app/docs/en/recipes/n8n/dingtalk.md) · [Coze](https://langbot.app/docs/en/recipes/coze/dingtalk.md) · [Langflow](https://langbot.app/docs/en/recipes/langflow/dingtalk.md) · [DeepSeek](https://langbot.app/docs/en/recipes/deepseek/dingtalk.md)
- Gemini on other platforms: [Telegram](https://langbot.app/docs/en/recipes/gemini/telegram.md) · [Discord](https://langbot.app/docs/en/recipes/gemini/discord.md) · [Slack](https://langbot.app/docs/en/recipes/gemini/slack.md) · [Lark (Feishu)](https://langbot.app/docs/en/recipes/gemini/lark.md) · [WeCom (internal app)](https://langbot.app/docs/en/recipes/gemini/wecom.md) · [WeCom Intelligent Bot](https://langbot.app/docs/en/recipes/gemini/wecombot.md)