TwelveLabs uses Pinecone to efficiently store and search the vector embeddings produced by our embedding model, enabling fast, scalable retrieval across large video and text datasets.
We’re continuing to optimize our video models for NVIDIA GPU architectures to improve efficiency and accuracy across diverse video workloads. Together, we aim to make enterprise-grade video intelligence easier to build, operate, and scale.
By building on AWS, TwelveLabs ensures customers get enterprise-grade security, elasticity, and performance for video workloads. This partnership allows developers, enterprises, and partners to build the future of video intelligence with confidence.
