A Python web app on Google Cloud's Vertex AI for generating images, video, music and speech with Gemini, Veo, Lyria and Chirp models.
GoogleCloudPlatform/vertex-ai-samples
Notebooks, code samples and sample apps showing how to build, deploy and manage ML and generative AI workflows on Google Cloud Vertex AI.
- Stars
- 795
- Forks
- 322
- Open issues
- 87
- Last commit
- yesterday
What is it?
This repository collects Jupyter notebooks, code samples, sample apps and AI agent skills for Google Cloud Vertex AI, Google's managed platform for building and using generative AI and machine learning models. It is organized into official notebooks for each Vertex AI service, such as AutoML, custom training, Feature Store, Model Registry, Explainable AI, and Pipelines, plus community-contributed notebooks and tutorials.
Many notebooks include links to open and run them directly in Colab, Colab Enterprise, or Vertex AI Workbench. Coverage includes the Model Garden catalog of first-party, open-source and third-party models, and a skills directory with guides for the Gen AI SDK, model deployment to endpoints, inference, and fine-tuning.
A Google Cloud project is required to run the samples. The code is provided for demonstration purposes and is not an officially supported Google product.
Key features
- 01Official notebooks for AutoML, custom training, Feature Store, Model Registry and Pipelines
- 02Model Garden examples covering Gemini, Gemma, Llama 3 and Claude 3
- 03Notebooks runnable in Colab, Colab Enterprise and Vertex AI Workbench
- 04Skills guides for the Gen AI SDK, model deployment, inference and fine-tuning
Use cases
- Learning how to train and serve ML models on Google Cloud
- Prototyping generative AI apps with the Gemini API on Vertex AI
- Building reproducible ML pipelines with Vertex AI Pipelines
- Exploring open and third-party models available through Model Garden
Quick start
- 1
Create or sign in to a Google Cloud project (a free trial is available)
- 2
Open a notebook from the repository in Colab, Colab Enterprise or Vertex AI Workbench and run it
Things to know
- Requires a Google Cloud project, and running the samples will incur Google Cloud costs.
- The README states this is not an officially supported Google product and the code is for demonstration only.
Topics
FAQ
- What is vertex-ai-samples?
- Notebooks, code samples and sample apps showing how to build, deploy and manage ML and generative AI workflows on Google Cloud Vertex AI. This repository collects Jupyter notebooks, code samples, sample apps and AI agent skills for Google Cloud Vertex AI, Google's managed platform for building and using generative AI and machine learning models. It is organized into official notebooks for each Vertex AI service, such as AutoML, custom training, Feature Store, Model Registry, Explainable AI, and Pipelines, plus community-contributed notebooks and tutorials.
- Is vertex-ai-samples free to use? What license does it have?
- vertex-ai-samples is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is vertex-ai-samples still maintained?
- Actively maintained. The last commit to vertex-ai-samples was on Nov 6, 2026.
- What can I use vertex-ai-samples for?
- Learning how to train and serve ML models on Google Cloud Prototyping generative AI apps with the Gemini API on Vertex AI Building reproducible ML pipelines with Vertex AI Pipelines Exploring open and third-party models available through Model Garden
- How do I install vertex-ai-samples?
- Create or sign in to a Google Cloud project (a free trial is available) Open a notebook from the repository in Colab, Colab Enterprise or Vertex AI Workbench and run it
- Where can I get vertex-ai-samples?
- The source code and installation instructions are on GitHub: https://github.com/GoogleCloudPlatform/vertex-ai-samples
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Google Cloud Advanced Solutions Lab course materials: notebooks, labs and code samples for ML and generative AI on Google Cloud.
A curated list of open source libraries for deploying, monitoring, versioning, scaling and securing production machine learning.
A free, self-paced 9-week online course covering MLOps: experiment tracking, orchestration, deployment, monitoring and best practices.
Course labs, reading materials and exercises for an MLOps and LLMOps course at Northeastern University, covering ML deployment and monitoring.
Builds machine learning models from a natural-language intent and a tabular dataset using a multi-agent workflow.