Compare local Ollama Vision models for image analysis using Google Docs

by Joseph LePage ✓ · 5,410 views · created 2025-03-16 · Document Extraction, Multimodal AI

What this workflow does

This workflow has 13 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Google Drive and Google Docs.

How it runs

Trigger: Manually, when you click “Execute workflow”.

1. Google Doc Image Id (Edit Fields (Set)): sets 1 field: id
2. Download Image File from Google Drive (Google Drive): download
3. Get Base64 String (Extract from File): extracts data from a file (binary to propery)
4. List of Vision Models (Edit Fields (Set)): sets 1 field: models
5. Split List of Vision Models for Looping (Split Out): splits a list into separate items
6. Loop Over Ollama Models (Loop Over Items (Split in Batches)): loops over the items in batches
7. Create Result Objects (Edit Fields (Set)): sets 1 field: result
8. General Image Prompt (Edit Fields (Set)): sets 1 field: user_prompt
9. Save Image Descriptions to Google Docs (Google Docs): update
10. Create Request Body (Edit Fields (Set)): sets 1 field: body

…plus 2 more steps. See the full node list below.

Services it uses

Google DriveGoogle Docs

Before you upgrade to n8n 3.0

Nodes used (8)

• Manual Triggern8n-nodes-base.manualTrigger
• HTTP Requestn8n-nodes-base.httpRequest
• Edit Fields (Set)n8n-nodes-base.set
• Loop Over Items (Split in Batches)n8n-nodes-base.splitInBatches
• Extract from Filen8n-nodes-base.extractFromFile
• Google Driven8n-nodes-base.googleDrive
• Split Outn8n-nodes-base.splitOut
• Google Docsn8n-nodes-base.googleDocs

From the author

Compare Local Ollama Vision Models for Image Analysis using Google Docs Process images using locally hosted Ollama Vision Models to extract detailed descriptions, contextual insights, and structured data. Save results directly to Google Docs for efficient…

View the original on n8n.io → Check your own copy