Search and recommendation systems are nearly ubiquitous and form an integral component of modern enterprises. However, traditional search engines primarily rely on textual queries, supplemented by session and geographical data. In contrast, the advent of large language models (LLMs) like GPT-4o and Gemini has significantly enhanced the potential for multimodal search and recommendations. Multimodal systems create a shared embedding space for text, images, audio, and other modalities, enabling next-generation customer experiences. These advancements lead to more accurate and personalized recommendations, enhancing user satisfaction and engagement.