Extract Business Card Data from Telegram to Google Sheets with OpenRouter AI Vision

This n8n workflow automates the process of extracting contact information from business card images sent via Telegram and saving it into a Google Sheet. It leverages OpenRouter AI's vision capabilities to intelligently parse the image content.

What it does

This workflow simplifies the task of digitizing business cards by:

1. Listening for Telegram Messages: Triggers when a new message is received in a configured Telegram bot.
2. Filtering for Images: Checks if the received message contains an image.
3. Extracting Text with AI Vision: If an image is present, it uses an OpenRouter AI Chat Model and an AI Agent to analyze the image and extract relevant business card data (e.g., name, company, title, email, phone).
4. Structuring AI Output: Parses the AI's response into a structured JSON format.
5. Saving to Google Sheets: Appends the extracted business card data as a new row in a specified Google Sheet.

Prerequisites/Requirements

To use this workflow, you will need:

• n8n Instance: A running n8n instance.
• Telegram Bot: A Telegram bot token and chat ID.
• OpenRouter API Key: An API key for OpenRouter to access its AI models.
• Google Sheets: A Google account with access to Google Sheets and a specific spreadsheet and sheet name where the data will be stored. The sheet should ideally have columns corresponding to the data you expect to extract (e.g., Name, Company, Title, Email, Phone).

Setup/Usage

1. Import the Workflow:

   • Copy the provided JSON code.
   • In your n8n instance, go to "Workflows" and click "New".
   • Click the three dots menu (...) and select "Import from JSON".
   • Paste the JSON code and click "Import".

2. Configure Credentials:

   • Telegram Trigger:
     • Click on the "Telegram Trigger" node.
     • Select or create a new Telegram API credential. You'll need your Telegram Bot Token.
   • OpenRouter Chat Model:
     • Click on the "OpenRouter Chat Model" node.
     • Select or create a new OpenRouter API credential. You'll need your OpenRouter API Key.
   • Google Sheets:
     • Click on the "Google Sheets" node.
     • Select or create a new Google Sheets API credential (OAuth 2.0 recommended). You'll need to grant n8n access to your Google Sheets.

3. Configure Nodes:

   • Telegram Trigger: Ensure the "Updates" field is set to photo or message to capture images.
   • AI Agent:
     • Review the prompt within the "AI Agent" node to ensure it aligns with the data you want to extract from business cards. You might want to refine it for specific fields or languages.
     • Ensure the "Tools" section is configured to use an image processing tool if available, or that the prompt clearly instructs the AI to describe the image content.
   • Structured Output Parser: Verify the schema defined in this node matches the expected JSON output from the AI Agent. This is crucial for correctly parsing the extracted data.
   • Google Sheets:
     • Specify the "Spreadsheet ID" of your target Google Sheet.
     • Specify the "Sheet Name" within that spreadsheet where the data will be added.
     • Map the output fields from the "Structured Output Parser" to the corresponding columns in your Google Sheet. For example, {{ $json.name }} to the "Name" column, {{ $json.company }} to "Company", etc.

4. Activate the Workflow:

   • Once all credentials and node settings are configured, click the "Activate" toggle in the top right corner of the n8n editor to enable the workflow.

Now, whenever you send a business card image to your configured Telegram bot, the workflow will process it, extract the contact details, and add them to your Google Sheet.