{"slug": "i-built-a-context-aware-rag-plant-assistant-for-magento-2-and-added-ai-photo", "title": "I Built a Context-Aware RAG Plant Assistant for Magento 2 — and Added AI Photo Analysis", "summary": "Johan, a developer running the multilingual Magento 2 plant store Introgreen, built two custom AI tools: Plantcoach, a context-aware RAG assistant that retrieves advice from the store's own plant knowledge library and adapts to the product page a visitor is viewing, and Plant Finder, a recommendation tool whose photo-analysis feature is in public beta. Both tools are custom-built for the five-language store and are now publicly available on its English site.", "body_md": "I've spent the past few months building two custom AI tools for **Introgreen**, my multilingual online plant store running on Magento 2.\n\nInstead of installing a generic chatbot extension, I wanted to develop something that understands which products visitors are viewing, retrieves relevant information from our own plant knowledge library and helps people choose suitable plants.\n\nThe result is **Plantcoach**, a context-aware RAG assistant, and **Plant Finder**, an AI-powered recommendation tool with photo analysis.\n\nBoth are now publicly available, with photo analysis still in beta.\n\nPlantcoach uses **Retrieval-Augmented Generation (RAG)** to retrieve relevant information from our own plant advice library instead of relying entirely on the model's general knowledge.\n\nThe library covers plant care, diseases, pests, growing conditions and plant selection for different environments.\n\nWhat makes it interesting is its integration with Magento 2.\n\nPlantcoach works through a dedicated page and as a chat popup on the homepage, category pages and product pages.\n\n**The assistant adapts to the page context.**\n\nFor example, when someone visits a Monstera product page and asks, \"Why are the leaves turning yellow?\", Plantcoach can use the current product context and retrieve relevant plant-specific advice.\n\nIt also combines plant knowledge with Magento product information, including plant characteristics and availability.\n\nThe challenge is providing useful advice without turning every conversation into a sales pitch.\n\nMy second tool, Plant Finder, recently gained a photo-analysis feature.\n\nVisitors can:\n\nA photograph alone cannot reliably determine everything. For example, it can't tell us how much natural light a room receives throughout the day.\n\nThat's why the tool combines image analysis with follow-up questions.\n\nThe photo feature is currently available as a **public beta**.\n\nOur Magento store operates in five languages: Dutch, German, English, French and Spanish.\n\nBuilding these tools has involved combining several different sources of information:\n\nOne challenge is handling different common names for the same plant across languages.\n\nAnother is ensuring recommendations remain relevant to both the user's situation and the actual product catalogue.\n\nThere's still plenty to improve, particularly around multilingual retrieval and recommendation quality.\n\nBoth tools are available on our English-language store.\n\n**Plantcoach — Context-Aware RAG Assistant**\n\n[https://introgreen.eu/plantcoach/](https://introgreen.eu/plantcoach/)\n\nAsk questions about plant care or try the contextual chat popup on a product page.\n\n**Plant Finder — AI Photo Analysis (Beta)**\n\n[https://introgreen.eu/plant-finder](https://introgreen.eu/plant-finder)\n\nUpload a photo and try the plant recommendations yourself.\n\nI'm particularly interested in hearing from other developers:\n\nBoth tools are custom-built for Introgreen, and I'm continuing to improve them.\n\nI'd love to hear your experiences with similar projects or suggestions for improvement.\n\nThanks for reading!\n\n**Johan**", "url": "https://wpnews.pro/news/i-built-a-context-aware-rag-plant-assistant-for-magento-2-and-added-ai-photo", "canonical_source": "https://dev.to/johanvdd/i-built-a-context-aware-rag-plant-assistant-for-magento-2-and-added-ai-photo-analysis-1147", "published_at": "2026-10-10 16:15:25+00:00", "updated_at": "2026-10-10 16:18:33.026749+00:00", "lang": "en", "topics": ["generative-ai", "ai-products", "ai-tools", "natural-language-processing"], "entities": ["Introgreen", "Magento 2", "Plantcoach", "Plant Finder", "Johan"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/i-built-a-context-aware-rag-plant-assistant-for-magento-2-and-added-ai-photo", "markdown": "https://wpnews.pro/news/i-built-a-context-aware-rag-plant-assistant-for-magento-2-and-added-ai-photo.md", "text": "https://wpnews.pro/news/i-built-a-context-aware-rag-plant-assistant-for-magento-2-and-added-ai-photo.txt", "jsonld": "https://wpnews.pro/news/i-built-a-context-aware-rag-plant-assistant-for-magento-2-and-added-ai-photo.jsonld"}}