5 ways to process images & PDFs with Gemini AI in n8n
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 22 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Google Gemini Chat Model. It also calls w3.org over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Define URLs And Prompts (Edit Fields (Set)): sets 1 field: urls
- Define Multiple Image URLs (Edit Fields (Set)): sets 1 field: urls
- Get PDF file (HTTP Request): calls w3.org
- Get image from unsplash (HTTP Request): calls an HTTP API
- Get image from unsplash (HTTP Request): calls an HTTP API
- Split Out: splits a list into separate items
- Split Out: splits a list into separate items
- Transform to base64 (pdf) (Extract from File): extracts data from a file (binary to propery)
- Transform to base64 (image) (Extract from File): extracts data from a file (binary to propery)
- AI Agent: runs an AI agent, with model: Google Gemini Chat Model
…plus 9 more steps. See the full node list below.
Services it uses
HTTP calls to: w3.org
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in AI Agent (v1.7), AI Agent2 (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Agent (v1.7), AI Agent2 (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (9)
- Manual Trigger
n8n-nodes-base.manualTrigger - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - AI Agent
@n8n/n8n-nodes-langchain.agent - HTTP Request
n8n-nodes-base.httpRequest - Split Out
n8n-nodes-base.splitOut - Extract from File
n8n-nodes-base.extractFromFile - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Edit Fields (Set)
n8n-nodes-base.set - Filter
n8n-nodes-base.filter
From the author
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…