Nova RouterNova Router
Quick StartAPI ReferenceAgent Tool Integrations

LangBot - Instant Messaging Bot Development Platform

LangBot integration guide — build AI-powered chatbots for Feishu, DingTalk, Telegram, Discord, and more. Supports Knowledge Base, Agent, and MCP with Nova Router.

LangBot is an open-source instant messaging bot development platform that supports various instant messaging platforms such as Feishu, DingTalk, WeChat, QQ, Telegram, Discord, Slack, etc. It integrates with mainstream global AI models, supports various AI application capabilities like Knowledge Base, Agent, MCP, and is perfectly compatible with Nova Router.

Integrating Nova Router

LangBot supports integrating with locally deployed Nova Router services and third-party compatible services.

Usage

  1. Obtain an API key from Nova Router

    If Nova Router is deployed locally, please configure the API address yourself (refer to Container Network Connection). If using a third-party compatible service, you can copy the address from the page. Note that /v1 needs to be appended to the address.

    Get API Key

  2. Add a model in LangBot, select Nova Router as the provider, and fill in the corresponding API key and API address

    • Open LangBot's Model Configuration
    • Create a new OpenAI-compatible model provider, or choose the provider type that matches Nova Router
    • Set the provider name to something easy to recognize, such as <BrandName />
    • Fill in API URL, API Key, and Model Name using the table below
    • Save the configuration and confirm that the new model appears in the LangBot model list

    Recommended fields:

    FieldWhat to enter
    ProviderSelect the provider that maps to Nova Router
    API URLEnter your endpoint and make sure it ends with /v1
    API KeyPaste the key obtained from Nova Router
    Model NameUse a model name exposed by your Nova Router deployment
  3. Select the model to use in the pipeline

    Select the model in the pipeline

  4. Use it by chatting in conversation debugging or by chatting with a bot bound to the pipeline

    For deploying and configuring bots, please refer to Deploying Bots.

    Debug chat

How to confirm it worked

  • The newly added Nova Router model appears in the model list
  • The pipeline can select that model successfully
  • Debug chat or a real bot conversation returns responses normally

Using LangBot Knowledge Base

LangBot supports using Nova Router embedding models and utilizing them as vector models for the knowledge base.

  1. Add an embedding model in LangBot, select Nova Router as the provider

    Use the embedding model in the knowledge base

  2. Select the embedding model when creating a new knowledge base

For more usage instructions, please refer to the LangBot official documentation: https://docs.langbot.app

How is this guide?