Mar 22
Loading video player...
In this video, I'm building a multimodal RAG AI agent using Google's Gemini Embedding 2, their first embedding model that works with text, images, video, and audio. We'll set up a full AI shopping assistant that lets customers search products by typing a description or uploading an image, powered by vector search and Supabase pgvector. By the end, you'll have a working multimodal AI agent you can deploy online. --- 👉🏻 Hostinger's Cloud Hosting: https://www.hostg.xyz/SHIit 💰Extra Discounts (Use these Coupon Codes): Current LIMITED offer (valid till end of March 2026): YASHICA20 – 20% off on 12/24/48 month plans! After the limited offer ends: YASHICA15 – 15% off on 24 month plan YASHICA – 10% off on 12 month plan Applies to all hosting services. 🎁 Access the Prompt I used: https://yashica.gumroad.com/l/gemini-embedding-2 🔔 Subscribe for more Claude Code, AI automation, and agentic AI content! --- ✅ Get Custom AI Projects Built: Work with us: https://www.automatezai.com/ 📞 Need guidance - for example, technical help? Book a 1:1 call: https://calendly.com/automatezai/paid-ai-consultation-or-coaching-1-hour --- 😇 About me: Hi, I’m Yashica — an AI automation proclaimed nerd building AI solutions for businesses, advising 1:1, and sharing practical builds on YouTube. 💁🏼♀️ Connect with me: LinkedIn → https://www.linkedin.com/in/yashicajain9/ X → https://x.com/yashicajain_ 🎥 My mic, camera & gear: https://www.amazon.in/shop/yashicajain --- If this video helps, let me know in the comments 👇 #claudecode #RAG #gemini ⏱ Timestamps: 00:00 Gemini Embedding 2 Explained 01:20 Multimodal RAG: What Actually Changes 03:27 What We're Building 04:29 Ingestion & Query Pipeline Design 06:13 Prompting Claude Code to Build 10:33 Supabase MCP Setup & Data Ingestion 13:13 Testing Text-Based RAG Queries 18:28 Testing Image-Based Product Search