Build a Polite AI Chatbot Using n8n and Mistral-7B Model

What this workflow does

This workflow runs an AI chatbot that answers customer messages kindly and with emojis.

It solves the problem of spending too much time replying to common questions.

The chatbot uses the Mistral-7B-Instruct model to write polite and friendly replies.

This helps users get answers faster, saves time, and keeps customers happy.

Who should use this workflow

People who manage customer chats and want automatic helpful replies.

Small business owners or those with busy online stores will find it useful.

No deep AI or programming skills needed to run this with n8n.

Tools and services used

• n8n: Workflow automation software to connect nodes.
• Hugging Face: Hosts the Mistral-7B-Instruct AI model for text generation.
• Chat Trigger node: Receives incoming chat messages via webhook.
• Basic LLM Chain node: Adds a prompt that tells AI how to reply nicely with emojis.
• Hugging Face Inference Model node: Sends prompt to AI model and returns chat responses.

Inputs, Processing, and Output

Inputs

• Incoming chat messages captured by the Chat Trigger node via a webhook.

Processing Steps

• The Basic LLM Chain node applies a prompt that requests polite, emoji-rich responses.
• The Hugging Face Inference Model node uses the Mistral-7B-Instruct model to generate replies based on the prompt and chat input.
• Connections ensure messages flow from receiving, through the prompt and AI model, to generating replies.

Output

• Polite, friendly chat replies enriched with emojis, sent back to the user’s chat interface.
• Faster customer support with less manual typing and fewer errors.

Beginner step-by-step: How to use this workflow in n8n production

Import the workflow

1. Download the workflow file using the Download button on this page.
2. Open n8n editor and click Import from File to upload the downloaded workflow.

Configure credentials and settings

1. Add Hugging Face API Key in Settings > Credentials inside n8n.
2. Check nodes for any IDs, emails, channels, or folders and update them if the workflow connects to external systems.
3. Verify the prompt text in the Basic LLM Chain node. Copy and paste if needed:

=You are a helpful assistant. Please reply politely to the users. Use emojis and a text.

Test and activate

1. Run the workflow once manually to confirm inputs and outputs work correctly.
2. Use the webhook URL from the Chat Trigger node in your chat system.
3. After successful test, click Activate in n8n to run the chatbot constantly.

For users interested, consider self-host n8n for more control and privacy.

Common problems and fixes

Invalid API key or permission denied

Check if Hugging Face API Key is correct and active in n8n credentials.

Make sure the API key has access to the Mistral-7B-Instruct model.

Workflow doesn’t trigger on chat messages

Verify the webhook URL from the Chat Trigger node is correctly used.

Confirm the workflow is activated and receiving traffic.

Customization ideas

• Change the AI personality by editing the prompt text to make replies humorous or formal.
• Replace the model in Hugging Face node to use alternative language models you prefer.
• Adjust response length, creativity, and repetition by changing maxTokens, temperature, and frequencyPenalty values.

Summary of results

✓ Automates polite, emoji-friendly replies to customers.

✓ Saves time and reduces errors in answering common questions.

→ Chat users get quicker, friendlier support.

→ Offers easy customization and works fully inside n8n and Hugging Face.