LangBot Docs
DeepSeek

Build a a website chat widget AI Bot with DeepSeek

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

This recipe puts a DeepSeek model 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.

Use DeepSeek models directly with LangBot's built-in Agent: no separate agent platform needed, with optional knowledge bases, MCP tools and Skills.

What you need

  • A running LangBot instance: LangBot Cloud (no server needed) or a self-hosted deployment with Docker or uvx langbot.
  • A DeepSeek account or server you can call from LangBot.
  • 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. Add the DeepSeek model

  1. Create an API key in the DeepSeek console.
  2. In LangBot, open Models, add an LLM model with the provider set to DeepSeek and request URL https://api.deepseek.com, 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. Typical model IDs are deepseek-chat and deepseek-reasoner; check DeepSeek's documentation for the current list.

2. Create a pipeline

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

FieldValue
RunnerLocal Agent (built-in Agent)
ModelThe model you just added. You can add fallback models.
PromptInstructions: who the bot is, tone, what it must not do.
Knowledge BasesOptional. Attach a knowledge base so answers come from your documents.

3. Create the a website chat widget bot

  1. Create a bot with the Web Page Bot adapter and bind a pipeline.
  2. Copy the embed code into your site and replace localhost:5300 with 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

  • 401 errors: the API key is wrong or has no balance in the DeepSeek console.
  • 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 DeepSeek setup serve other platforms too?

Yes. A pipeline can be bound to many bots, so one configuration can answer on several platforms at once.

Build a Mattermost AI Bot with DeepSeek

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

Build a Telegram AI Bot with OpenAI (ChatGPT models)

Step-by-step guide to running a OpenAI (ChatGPT models)-powered AI bot on Telegram with LangBot: model setup, bot credentials, networking, testing and troubleshooting.

On this page

What you needNetworking1. Add the DeepSeek model2. Create a pipeline3. Create the a website chat widget bot4. Bind and testTroubleshootingFAQDo I need a server with a public IP for a website chat widget?Does the a website chat widget bot support streaming replies?Can the same DeepSeek setup serve other platforms too?Related guides