Introduction to MultiModal RAG with Gemini on Google Cloud | Google Cloud | Lavi Nigam

Описание к видео Introduction to MultiModal RAG with Gemini on Google Cloud | Google Cloud | Lavi Nigam

RAG typically uses external data sources only based on text. With Gemini Pro Vision and multimodal embeddings, you can now perform multimodal RAG on text and images. In this session, you will gain hands-on experience by performing multimodal RAG on a financial document that contains both text and images (charts, diagrams).

Комментарии

Информация по комментариям в разработке

Похожие видео