• Duration

    5.5 Hours

  • Level

    Beginner

  • Course Type

    Free Course

What you'll Learn

  • Understand Embeddings & Amazon Bedrock

  • Understand internals about Multimodal LLMs, CLIP, and BLIP-2

  • How to use Multimodal LLMs with Amazon Bedrock

  • How to use Amazon Nova Multimodal Model for Text, Image and Video Understanding

  • How to use Multimodal RAG with Amazon Nova and LangChain

  • How to use Amazon Bedrock Agents for building end-to-end applications

About the Instructor

Suman Debnath, Principal Developer Advocate (AI/ML), Amazon Web Services

Suman Debnath is a Principal Developer Advocate for Machine Learning at AWS, with a background in storage and performance engineering. He specializes in open-source ML tools like TensorFlow, PyTorch, and Spark, and has developed benchmarking tools for distributed storage systems. A seasoned speaker, he has presented at 100+ global events, including PyCon, PyData, and ODSC.
About the Instructor

Who Should Enroll?

  • Individuals looking to understand advanced AI tools and their applications in analytics and data-driven decision-making.

  • Beginners interested in AI, machine learning, and how innovative platforms like DeepSeek are reshaping the industry.

FAQ

  • What are text embeddings, and why are they important in AI?

    Text embeddings are vector representations of words, phrases, or entire documents that capture their semantic meaning. They are crucial in AI applications such as search, recommendation systems, chatbots, and Retrieval-Augmented Generation (RAG), enabling models to process and compare text efficiently.

  • How do multimodal models differ from traditional AI models?

    Multimodal models process and integrate multiple types of data, such as text, images, and audio, whereas traditional AI models typically focus on a single modality. These models enable applications like visual question answering (VQA), image captioning, and AI assistants capable of understanding both text and images.

  • What is the role of Amazon Nova in AI engineering?

    Amazon Nova is a multimodal large language model (LLM) developed by AWS that can process text and images simultaneously. It is designed for applications such as AI-powered customer support, content generation, and intelligent search, leveraging embeddings and RAG for enhanced accuracy.

  • What are the prerequisites for this course?

    A foundational understanding of machine learning and familiarity with AWS services are recommended to effectively engage with the course material.

  • How do embeddings and RAG work together in AI applications?

    Embeddings convert textual data into numerical vectors, which can then be used in RAG frameworks to retrieve relevant documents or facts before generating a response. This combination enhances AI systems by enabling real-time access to external knowledge, improving the factual accuracy of generated content.