Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
In this 45-minute demo, Hrishikesh Yadav from Twelve Labs demonstrates a content recommendation application that leverages multimodal video understanding and vector search capabilities. Learn how to extract rich, multimodal embeddings from video content (including visuals, audio, scenes, and contextual information) using the Twelve Labs Embed API, and how to efficiently store and search these embeddings with Qdrant vector database for semantic retrieval. Discover how to build recommendation systems based on the actual content within videos rather than just metadata or tags. This presentation is ideal for developers building video AI applications, engineers exploring multimodal retrieval solutions, and anyone interested in more sophisticated video search capabilities beyond traditional methods. Access the complete project through the available live demo, accompanying blog post, and GitHub repository to implement similar functionality in your own applications.
