Google's Generative AI offering is a suite of tools and services that help developers build and deploy generative AI applications. These applications can be used for a variety of purposes, such as, Improving search results.Automating content generation, and Personalizing user experiences. This learning path is designed for developers who want to learn about generative AI and how to use it to build their own applications. No prior experience with machine learning or natural language processing is required. This path builds on the concepts introduced in the Introduction to Generative AI Learning path introduction to Generative AI learning path. So if you are new to the Generative AI space, it's recommended that you start with that learning path before diving into more advanced content and hands-on labs.
This learning path will continue to be updated as we make new product announcements.
Complete the intermediate Explore Generative AI with the Gemini API in Vertex AI skill badge to demonstrate skills in the following: text generation, image and video analysis for enhanced content creation, and applying function calling techniques within the Gemini API....
Explore AI-powered search technologies, tools, and applications in this course. Learn semantic search utilizing vector embeddings, hybrid search combining semantic and keyword approaches, and retrieval-augmented generation (RAG) minimizing AI hallucinations as a grounded AI agent. Gain practical experience with Vertex...
This course explores Google Cloud technologies to create and generate embeddings. Embeddings are numerical representations of text, images, video and audio, and play a pivotal role in many tasks that involve the identification of similar items, like Google searches, online...
Complete the intermediate Inspect Rich Documents with Gemini Multimodality and Multimodal RAG skill badge to demonstrate skills in the following: using multimodal prompts to extract information from text and visual data, generating a video description, and retrieving extra information beyond...
Learn how Gemini can revolutionize your ability to develop applications! This course helps developers go beyond the basics and learn how to integrate Gemini into their workflows.
This course on Integrate Vertex AI Search and Conversation into Voice and Chat Apps is composed of a set of labs to give you a hands on experience to interacting with new Generative AI technologies. You will learn how to...
This course equips full-stack mobile and web developers with the skills to integrate generative AI features into their applications using LangChain. You'll learn how to leverage LangChain’s capabilities for backend flows and seamless model execution, all within the familiar environment...
Learn to use LangChain to call Google Cloud LLMs and Generative AI Services and Datastores to simplify complex applications' code.
All applications, including generative AI applications, should be deployed securely & have their performance monitored. In this course, you will explore a pattern for easily securing prototype generative AI applications for internal tool use or customer demos. Additionally, you will...
In this course, you'll use text embeddings for tasks like classification, outlier detection, text clustering and semantic search. You'll combine semantic search with the text generation capabilities of an LLM to build Retrieval Augmented Generation (RAG) solutions, such as for...
This course equips app developers with the skills to integrate generative AI features into their applications using Firebase Genkit. You learn how to leverage Firebase Genkit's capabilities for backend flows and seamless model execution, all using Node.js. The course guides...
Learn to build generative AI applications leveraging Firebase Genkit to call LLMs on Google Cloud and elsewhere, simplify complex applications' code and deploy your solution on Google Cloud.
An LLM-based application can process language in a way that resembles thought. But if you want to extend its capabilities to take actions by running other functions you have coded, you will need to use function calling. This can also...