GitHub: a good resources to use Gen AI from Google Vertex AI by Applied AI Engineering

github logo
github logo

Applied AI Engineering: Catalog

Generative AI on Vertex AI

This section contains code samples and hands-on labs demonstrating the use of Generative AI models and tools in Vertex AI.

Foundation ModelsEvaluationRAG & GroundingAgentsOthers
Gemini Prompting RecipesAdvanced PromptingFoundation model tuningVertex GenAI EvaluationGemini Evals PlaybookVertex AI SearchRetrieval Augmented GenerationAgentsVertex AI ExtensionsDeveloper Productivity with GenAI

Google Cloud AI/ML infrastructure

This section has reference guides and blueprints that compile best practices, and prescriptive guidance for running large-scale AI/ML workloads on Google Cloud AI/ML infrastructure.

Research Operationalization

This section has code samples demonstrating operationalization of latest research models or frameworks from Google DeepMind and Research teams on Google Cloud including Vertex AI.

Solutions Catalog

In addition to code samples in this repo, you may want to check out the following solutions published by Google Cloud Applied AI Engineering.

SolutionDescription

Open Data Q&A
The Open Data QnA python solution enables you to chat with your databases by leveraging LLM Agents on Google Cloud. The solution enables a conversational approach to interact with your data by implementing state-of-the-art NL2SQL / Text2SQL methods.

GenAI for Marketing
Showcasing Google Cloud’s generative AI for marketing scenarios via application frontend, backend, and detailed, step-by-step guidance for setting up and utilizing generative AI tools, including examples of their use in crafting marketing materials like blog posts and social media content, nl2sql analysis, and campaign personalization.

GenAI for Customer Experience Modernization
This solution shows how customers can have modern, engaging interactions with brands, and companies can improve the end user, agent, and customer experiences with a modern customer service platform on Google Cloud.

Creative Studio | Vertex AI
Creative Studio is a Vertex AI generative media example user experience to highlight the use of Imagen and other generative media APIs on Google Cloud.

RAG Playground
RAG Playground is a platform to experiment with RAG (Retrieval Augmented Generation) techniques. It integrates with LangChain and Vertex AI, allowing you to compare different retrieval methods and/or LLMs on your own datasets. This helps you build, refine, and evaluate RAG-based applications.

Generative AI on Vertex AI

This folder contains code samples and hands-on labs demonstrating the use of Generative AI models and tools in Vertex AI.

  • Tuning Foundational Models with Vertex AI: A comprehensive Jupyter notebook illustrating the step-by-step procedure for tuning foundational models (PaLM 2) with Google Cloud’s Vertex AI. Guides users through the entire setup and integration process – starting from environment setup, foundational model selection, to tuning it with Vertex AI.
  • Langchain Observability Code Snippet: A Langchain callback to aid with understanding/observing the exact LLM calls made by a Langchain agent. The callback is provided in a Jupyter notebook, which also includes a demonstration of the code snippet.
  • Advanced Prompting Training: A detailed notebook on prompt engineering, demonstrating and explaining chain of thought and ReAct (reasoning + acting) prompting. Chain of thought is a very low-effort way to improve prompt performance, and ReAct is the state-of-the-art for using LLMs to interact with external systems.
  • Vertex AI LLM Evaluation Services: We offer a comprehensive set of notebooks that demonstrate how to use Vertex AI LLM Evaluation Services in conjunction with other Vertex AI services. Additionally, we have provided notebooks that delve into the theory behind evaluation metrics.
  • Developer Productivity with GenAI: A collection of code samples to show builders and partners how to solve different developer tasks such as code generation, code explanation, unit test generation, comment generation, code debugging, code migration and talk to code and doc in software development life cycles to increase developer productivity with Codey APIs and other GCP services.
  • Natural Langauge to SQL queries: The notebook addresses the challenges inherent in converting natural language inputs into SQL queries, while providing demonstrations of effective strategies for generating SQL queries from natural language inputs.
  • Vertex AI Extensions Getting Started: A collection of notebooks for getting started using Vertex AI Extensions with the Code Interpreter and Vertex AI Search Extensions.
  • Vertex AI Search: A collection of notebooks, with varying levels of complexity, using Vertex AI Search. The notebooks are aimed to serve as building blocks which can be combined together to achieve higher levels goals.

You may also like...

Leave a Reply

Your email address will not be published. Required fields are marked *