Mar 22
Loading video player...
Watch more from .local San Francisco → https://www.youtube.com/playlist?list=PL4RCxklHWZ9s7IrElTzddaZ2w5uupd6TQ Subscribe to MongoDB YouTube→ https://mdb.link/subscribe This workshop gives participants hands-on experience using Voyage AI's latest multimodal embedding model, together with MongoDB Atlas Vector Search to build semantic video retrieval systems. Attendees will generate embeddings from real video samples, store and index them in MongoDB, and run cross-modal queries such as text-to-video and video-to-video search. Through a guided demo and interactive notebook, participants will construct a complete video search pipeline and learn practical techniques for video segmentation, indexing, and deploying multimodal search in real applications. 00:00:00 Building Intelligent Video Search Pipelines 00:00:19 Scale and Use Cases for Video Retrieval 00:02:54 System Architecture with MongoDB Atlas 00:04:32 Hybrid Retrieval & Multimodal RAG 00:06:42 Solving the "Modality Gap" in AI Models 00:09:37 Voyage Multimodal 3.5 Architecture 00:11:15 Performance Benchmarks vs. Google & Amazon 00:12:16 Optimizing Costs: Quantization & Dimensionality 00:14:30 Video Processing & Semantic Segmentation Visit Mongodb.com → https://mdb.link/MongoDB Read the MongoDB Blog → https://mdb.link/Blog Read the Developer Blog → https://mdb.link/developerblog