Description

How it works Many users have asked in the support forum about different methods to analyze images and PDF documents with Google Gemini AI in n8n. This workflow answers that question by demonstrating five different approaches: Single image with auto binary passthrough - The simplest approach using AI Agent's automatic binary handling Multiple images with predefined prompts - For customized analysis with different instructions per image Native n8n item-by-item processing - For handling multiple items using n8n's standard workflow paradigm PDF analysis via direct API - For document analysis and text extraction Image analysis via direct API - For direct control over API parameters Each method has advantages depending on your specific use case, data volume, and customization needs. Set up steps Setup time : ~5-10 minutes You'll need: A Google Gemini API key n8n with HTTP Request and AI Agent nodes Important: For the HTTP Request nodes making direct API calls to Gemini (Methods 3, 4, and 5), you'll need to set up Query Authentication with your Gemini API key. Add a parameter named "key" with your API key value in the Query Auth section of these nodes. I'll updated this if I find better ways. Also let me know if you know other ways. Eager to learn :)

Key Features

1) Demonstrates five different methods for processing images and PDFs with Gemini AI
2) Supports single image analysis with automatic binary passthrough for quick implementation
3) Enables custom prompts for analyzing multiple images
accommodating different analysis goals
4) Utilizes standard n8n item processing for multiple images with direct API control
5) Facilitates PDF analysis through base64 transformation and direct API calls
6) Offers advanced control over API parameters for users needing precise customization in image analysis.

Required Tools

MetaobjectListDrop