Skip to main content

One post tagged with "Multimodal Models"

AI models capable of processing and understanding multiple data types, such as text, images, audio, and video. Covers models like CLIP, AWS Titan Multimodal, Gemini, and OpenAI's GPT-4 Vision, along with their applications in search, recommendation systems, and interactive AI agents.

View All Tags

Vectorizing multimodal e-commerce product data with AWS Titan: a practical guide

· 23 min read
Norah Sakal
Norah Sakal
AI Consultant & Developer

Vectorizing multimodal e-commerce product data with AWS Titan: a practical guide

Learn how to transform e-commerce product data into numerical vectors using AWS Titan.

This guide show you how to use a multimodal model to create embeddings from both text and images, enabling better search, recommendations, and data analysis.