NVIDIA has released the Nemotron ColEmbed V2 models, designed for efficient multimodal document retrieval. These models utilize a late-interaction embedding approach to improve accuracy in handling text, images, and structured visual data. They perform well on the ViDoRe V3 benchmark, making them suitable for applications like multimedia search engines and conversational AI.

Complete the intermediate course on implementing multimodal vector search with BigQuery, which takes 1 hour and 45 minutes. Participants will learn to use Gemini for SQL generation, conduct sentiment analysis, summarize text, generate embeddings, create a Retrieval Augmented Generation (RAG) pipeline, and perform multimodal vector searches.