Skip to main content

Create a knowledge base chatbot with OpenAI and Notion for website embedding

Workflow preview

Workflow preview
100%
Create a knowledge base chatbot with OpenAI and Notion for website embedding preview
Open on n8n.io

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

This workflow creates an AI chatbot that uses your Notion database as a knowledge base and allows for website embedding (e.g., as a customer support chatbot). The AI agent can automatically query y...

Best for

  • Support Chatbot automation workflows
  • AI RAG automation workflows
  • intermediate n8n builders looking for reusable templates

Tools used

n8n-nodes-base.stickynote, @n8n/n8n-nodes-langchain.lmchatopenai, @n8n/n8n-nodes-langchain.chattrigger, @n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.memorybufferwindow, n8n-nodes-base.notiontool

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Gegenfeld.

Original n8n.io source

1.1 Workflow description

Title
Create a knowledge base chatbot with OpenAI and Notion for website embedding
Workflow name
Create a knowledge base chatbot with OpenAI and Notion for website embedding

This workflow creates an AI chatbot that uses your Notion database as a knowledge base and allows for website embedding (e.g., as a customer support chatbot). The AI agent can automatically query your Notion pages and databases to provide accurate, contextual responses based on your stored content.

Who's it for

This template is perfect for:

  • Support teams who maintain their knowledge base in Notion
  • Content creators and teams managing documentation in Notion databases
  • Businesses looking to make their Notion workspace conversationally accessible
  • Anyone who wants to turn their Notion content into an interactive AI assistant

How it works

The workflow combines OpenAI's language model with Notion's database capabilities to create a smart chatbot. When users ask questions, the AI agent automatically determines which Notion pages or database entries are relevant and uses that content to generate helpful responses. The system maintains conversation history for natural, contextual interactions.

How to set up

  1. Add your credentials:

    • Configure your Notion API integration in the Set & Get Notion Database node
    • Set up your OpenAI API credentials in the OpenAI Chat Model node
  2. Configure your Notion connection:

    • Click the Set & Get Notion Database node
    • Select your Notion database or page containing your knowledge base content
    • The AI will automatically determine relevant pages - no need to specify individual page IDs
  3. Customize the AI model:

    • Open the OpenAI Chat Model node
    • Choose your preferred model (GPT-4, GPT-3.5-turbo, etc.)
    • Adjust token limits if needed
  4. Test the chatbot:

    • Click the Chat button to start a conversation
    • Ask questions related to your Notion content
  5. Optional - Make it public:

    • Enable public access in the Chat Trigger node
    • Embed the provided code into your website

Requirements

  • n8n instance (cloud or self-hosted)
  • Notion workspace with databases or pages you want to query
  • OpenAI API key with available credits
  • Notion API integration with proper permissions

How to customize the workflow

Change the AI Provider: You can replace the OpenAI Chat Model with other providers like Anthropic Claude, Google Gemini, or local models by swapping the language model node.

Adjust Context Window: Modify the "Remember Chat History" node to increase or decrease how many previous messages the AI remembers (default is 10 interactions).

Update System Instructions: Edit the Smart AI Agent's system message to change how the assistant behaves or add specific instructions for your use case.

Connect Multiple Databases: Add additional Notion Database nodes to give the AI access to multiple databases or pages within your workspace.

Add More Tools: Extend the AI agent with additional tools like web search, email sending, or integration with other services.

Workflow Structure

Chat Trigger → Smart AI Agent ← OpenAI Chat Model
                     ↓
         Set & Get Notion Database
                     ↑
           Remember Chat History

The Smart AI Agent orchestrates the conversation, deciding when to query Notion and how to use the retrieved content in responses. The memory buffer ensures natural conversation flow by maintaining context across interactions.

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - Sticky Note1

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 2 - Sticky Note2

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 3 - Sticky Note3

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 4 - Sticky Note

Type / Role
n8n-nodes-base.stickyNote - stickyNote
Config choices
Version 1

Block 5 - OpenAI Chat Model

Type / Role
@n8n/n8n-nodes-langchain.lmChatOpenAi - lmChatOpenAi
Config choices
Version 1.2

Block 6 - Start Chat Conversation

Type / Role
@n8n/n8n-nodes-langchain.chatTrigger - chatTrigger
Config choices
Version 1.1

Block 7 - Smart AI Agent

Type / Role
@n8n/n8n-nodes-langchain.agent - agent
Config choices
Version 1.7

Block 8 - Remember Chat History

Type / Role
@n8n/n8n-nodes-langchain.memoryBufferWindow - memoryBufferWindow
Config choices
Version 1.3

Block 9 - Set & Get Notion Database

Type / Role
n8n-nodes-base.notionTool - notionTool
Config choices
Version 2.2

3. Summary Table

Workflow Create a knowledge base chatbot with OpenAI and Notion for website embedding
Complexity intermediate
Nodes 9
Categories Support Chatbot, AI RAG
Author Gegenfeld
Published 26 Jul 2025

4. Reproducing the Workflow from Scratch

  1. 1. Download the workflow JSON

    Use the JSON export at /data/workflows/6500/6500.json as the source template for this automation.

  2. 2. Import the template into n8n

    Open n8n, import the downloaded JSON, and review each node before activating the workflow.

  3. 3. Configure credentials and variables

    Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.

  4. 4. Test with sample data

    Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.

  5. 5. Activate and monitor

    Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Frequently asked questions

What does Create a knowledge base chatbot with OpenAI and Notion for website embedding do?

This workflow creates an AI chatbot that uses your Notion database as a knowledge base and allows for website embedding (e.g., as a customer support chatbot). The AI agent can automatically query y...

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Support Chatbot, AI RAG use case.