Extract PDF Images & Analyze with GPT-4o in Google Drive

Automatically Extract Images from PDFs in Google Drive—and Analyze Them with GPT-4o

Stop screenshotting page by page. This n8n workflow instantly extracts embedded images from a PDF stored in Google Drive, analyzes each image with GPT-4o, and saves the results as a ready-to-use .txt file—fast, consistent, and less error-prone than manual image inspection.

What this workflow does

• Automatically extracts all images from the uploaded PDF (no manual intervention).
• Scans each PDF page to identify embedded images.
• Analyzes every extracted image using the GPT-4o model to generate descriptive insights and context for each image.
• Saves results to a plain text (.txt) file, including image URLs and the corresponding GPT-4o analysis for easy review, sharing, or downstream automation.

Use cases

• Turn PDF visuals into searchable knowledge by extracting figures, diagrams, or photos and generating image-level descriptions.
• Speed up research and content audits for teams reviewing document imagery without manual screenshots.
• Support document QA by quickly producing structured notes about what each embedded image contains.

Technical details

• Google Drive integration to work with uploaded PDFs and save outputs.
• Convert API usage to handle PDF conversion/image extraction (note: it may occasionally return a 503 Service Unavailable—the workflow may still succeed on retry).
• GPT-4o analysis for each extracted image.
• Workflow nodes include: set, code, split out, sticky note, Google Drive, and HTTP Request.
• Setup requires credentials for OpenAI, Convert API, and Google Drive when you first open the workflow.

This n8n automation workflow is built for practical PDF image extraction + GPT-4o insights, delivering results in seconds and eliminating the manual screenshot-to-notes workflow.