Connect Dify to Telegram

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

Dify builds chat assistants, Chatflows, Agents and Workflows. LangBot calls the published app through its Service API, so prompts, tools and knowledge stay in Dify.

What you need

• A running LangBot instance: LangBot Cloud (no server needed) or a self-hosted deployment with Docker or uvx langbot.
• A Dify account or instance that LangBot can reach over the network.
• A bot token from @BotFather (send /newbot and pick a username ending in bot).

Networking

Telegram uses long polling: LangBot only needs outbound access to api.telegram.org. No public webhook URL is required, so a laptop or home server works.

1. Prepare Dify

1. Build and publish a Chat Assistant (including Chatflow), Agent or Workflow app in Dify.
2. Open the app's Access API page and create an API key.
3. For a Workflow app, output the answer under the key summary.

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.

3. Create the Telegram bot

1. Under Bots, create a bot and select the Telegram adapter (the new adapter in LangBot 4.11, not the deprecated legacy one).
2. Paste the token, enable Markdown and streaming if you want them, then enable and save the bot.

4. Bind and test

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

Press Start in a private chat with the bot and send a message. In groups, the message must match the pipeline's trigger rules (for example, mention the bot or reply to it).

Troubleshooting

• Self-hosted Dify in Docker on the same host: put both stacks on a shared Docker network and use the container address (for example http://dify-nginx/v1), not localhost.
• Chatflow apps only return what the Answer node outputs.
• Only one running instance may poll a token. If replies are missing, make sure the same bot is not enabled in another LangBot instance or script.
• 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 Telegram?

No. Telegram uses long polling: LangBot only needs outbound access to api.telegram.org. No public webhook URL is required, so a laptop or home server works.

Does the Telegram 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 Dify 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 Telegram setup guide
• Full Dify runner guide
• Other AI back ends on Telegram: n8n · Coze · Langflow · DeepSeek · OpenAI (ChatGPT models)
• Dify on other platforms: Discord · Slack · Lark (Feishu) · DingTalk · WeCom (internal app) · WeCom Intelligent Bot