Analyze Ingredient Photos using Telegram & Gemini AI Who’s it for Skincare enthusiasts who want to know if a product is safe. Food or supplement buyers checking ingredient safety. Parents reviewing kids’ products. Anyone wanting quick ingredient analysis before using/buying a product. How it works / What it does Telegram Input – User sends a photo of a product label or a text list of ingredients. Photo Handling – Workflow checks if the message contains a photo. If yes → retrieves the file, extracts ingredients using Google Gemini AI. If no → handles text/greetings/off-topic queries. Caption Branching With caption → Gives Use / Do Not Use recommendation + reason. Without caption → Gives Advantages, Disadvantages, Recommended For, Not Recommended For (3 points each). Response on Telegram – Sends a friendly, structured response back to the user. How to set up Import this workflow JSON into n8n. Create and connect a Telegram bot via BotFather → paste the API token in Telegram credentials. Add Google Gemini (PaLM) API credentials inside n8n. Activate the workflow and send your first product photo via Telegram! Requirements n8n instance (self-hosted or cloud). Telegram bot token. Google Gemini API credentials. How to customize the workflow Change AI Instructions – Update system messages to tweak tone (more technical, casual, or medical). Adjust Output Format – Edit Telegram response nodes for shorter/longer answers. Expand Analysis – Add extra categories (e.g., allergens, environmental impact). Multi-language Support – Modify prompts to output in the user’s preferred language. Add Database Logging – Connect to MySQL, PostgreSQL to save conversations (user queries + AI responses).