This course covers building LLM-powered applications on Google Cloud. You learn how to access and use Gemini models through Vertex AI, design effective prompts, implement Retrieval Augmented Generation, and build agents that combine LLMs with tools and APIs.
Topics include Vertex AI Studio, Gemini API, prompt engineering, embeddings, vector search, RAG pipelines, and responsible AI practices. The course suits developers and ML engineers building the next generation of AI-powered applications on Google Cloud.
By the end of the course, you will be able to design and build LLM-powered applications and agents using Vertex AI and the Gemini model family.
