Food Photo Analysis to Restaurant & Book Recommendations with GPT Vision and Google APIs
Ready for 3.0What this workflow does
This AI workflow has 18 nodes and runs on Google Drive events (file created). Along the way it connects Google Drive, OpenRouter Chat Model, Google Books and Slack. It also calls drive.google.com and places.googleapis.com over HTTP.
How it runs
Trigger: On Google Drive events (file created).
- Fetch Image (Drive) (HTTP Request): calls drive.google.com
- Dish Classifier (AI Agent): runs an AI agent, with model: LLM (Vision/JSON)
- Normalize Classification (Code): runs custom JavaScript code
- Set Origin & Radius (Edit Fields (Set)): sets 4 fields: originLabel, originLat, radiusM…
- Pass the API (Edit Fields (Set)): sets or maps fields
- Search Google Places (HTTP Request): calls places.googleapis.com (POST)
- Summarize Place List (Code): runs custom JavaScript code
- Select Best Place (AI) (AI Agent): runs an AI agent, with model: LLM (Selection)
- Format Best Place JSON (Code): runs custom JavaScript code
- Recommend Book (AI) (AI Agent): runs an AI agent, with model: LLM (Books)
…plus 4 more steps. See the full node list below.
Services it uses
HTTP calls to: drive.google.com, places.googleapis.com
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Rarely used nodes in this template: n8n-nodes-base.googleBooks
Nodes used (8)
- Google Drive Trigger
n8n-nodes-base.googleDriveTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - HTTP Request
n8n-nodes-base.httpRequest - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - Code
n8n-nodes-base.code - Edit Fields (Set)
n8n-nodes-base.set - Google Books
n8n-nodes-base.googleBooks - Slack
n8n-nodes-base.slack
From the author
AI Recommender: From Food Photo to Restaurant and Book (Google Books Integrated) What it does Analyzes a food photo with an AI vision model to extract dish name + category Searches nearby restaurants with Google Places and selects the single best (rating →…