Advanced Gemini for Developers
.MP4, AVC, 1152x720, 30 fps | English, AAC, 2 Ch | 1h 27m | 212 MB
Instructor: Lynn Langit

Creating applications grounded by powerful foundational modals can open new worlds for you and your users. In this course, learn to use Google Gemini applications patterns and tools to build large language model-based applications. These include patterns for prompt validation, effective retrieval-augmented generation (RAG), and fine tuning. Instructor Lynn Langit also shares comparisons of Gemini, Gemma, and other foundational LLMs for your application scenarios.

Learning objectives

• Understand the Google Gemini Agent Builder tool and its integration with cloud storage, BigQuery, and FHIR databases for building conversational generative AI applications.
  
• Explore the Vertex AI Studio for testing and evaluating language, vision, speech, and multimodal models, as well as the Model Garden for accessing pre-trained models from various sources.
  
• Learn about JumpStart solution patterns for developing end-to-end generative AI applications, including RAG (retrieval-augmented generation) with Cloud SQL, knowledge bases, RAG on GKE, and RAG on Vertex AI with evaluation.
  
• Gain insights into best practices for setting up a Google Cloud environment for Gemini development and learning.
  
• Understand the next steps in mastering the efficient design, development, testing, hosting, and deployment of machine learning models for Google Gemini applications.
  

Exercise Files on GitHub

More Info