n8n Workflow: Classify Emails & Extract Structured Data from Job Applications with GPT-4o

This n8n workflow automates the process of classifying incoming emails and extracting structured data from them, specifically designed for handling job applications. It leverages the power of Large Language Models (LLMs) to understand email content, classify it, and pull out key information.

What it does

This workflow streamlines the processing of incoming emails by:

1. Triggering on New Emails: Continuously monitors an IMAP email account for new messages.
2. Extracting File Content: Automatically extracts text content from any attached files (e.g., resumes, cover letters) found in the email.
3. Classifying Email Content: Uses an OpenAI Chat Model to classify the email's subject and body, determining if it's a job application or another type of email.
4. Extracting Structured Information: If classified as a job application, it utilizes an OpenAI Chat Model to extract structured data such as candidate name, contact information, desired role, and relevant skills from the email body and extracted file content.
5. No Operation (Placeholder): Includes a "No Operation" node, which can be extended to integrate with other services (e.g., adding data to a CRM, sending notifications, or storing in a database).

Prerequisites/Requirements

To use this workflow, you will need:

• n8n Instance: A running instance of n8n.
• IMAP Email Account: Access to an IMAP email server (e.g., Gmail, Outlook, custom mail server) to monitor for new emails. You will need the host, port, username, and password.
• OpenAI API Key: An API key for OpenAI to use the Chat Model for classification and information extraction. This workflow is specifically hinted to work with gpt-4o.

Setup/Usage

1. Import the Workflow:
   • Download the provided JSON file.
   • In your n8n instance, go to "Workflows" and click "New".
   • Click the "Import from JSON" button and paste the workflow JSON or upload the file.
2. Configure Credentials:
   • IMAP Email Trigger:
     • Click on the "Email Trigger (IMAP)" node.
     • Click "Create New Credential" for the IMAP account.
     • Enter your IMAP server details (Host, Port, Username, Password).
     • Test the connection to ensure it's working.
   • OpenAI Chat Model:
     • Click on the "OpenAI Chat Model" nodes (both the "Text Classifier" and "Information Extractor" use it).
     • Click "Create New Credential" for OpenAI.
     • Enter your OpenAI API Key.
     • Select the desired model (e.g., gpt-4o as suggested by the directory name, or gpt-3.5-turbo for cost efficiency).
3. Activate the Workflow:
   • Once all credentials are set up, click the "Activate" toggle in the top right corner of the workflow editor to start monitoring for new emails.
4. Customize (Optional):
   • Email Filtering: You can add a "Filter" node after the "Email Trigger" to only process emails from specific senders or with certain keywords in the subject.
   • Output Integration: Extend the "No Operation, do nothing" node (ID 26) to integrate with other services. For example, you could add nodes to:
     • Save extracted data to a Google Sheet, Notion database, or CRM.
     • Send a Slack or email notification with the extracted information.
     • Create a task in a project management tool.
   • Prompt Engineering: Adjust the prompts within the "Text Classifier" and "Information Extractor" nodes to fine-tune their behavior for your specific needs.