Code and slides to accompany the online series of webinars: https://www.oreilly.com/live-events/gemini-api-with-vertexai-for-developers/0642572299484/ by Data For Science.
This webinar provides attendees with an excellent opportunity to explore Google's cutting-edge Generative AI capabilities, specifically focusing on the Gemini API within the Vertex AI framework on Google Cloud Platform. As AI development accelerates, understanding and implementing multimodal generative models have become essential for creating innovative and intelligent applications. The session will provide participants with the knowledge and hands-on skills to leverage generative AI across various modalities, including text generation for content creation and natural language processing, image synthesis for design and visual communication, video creation for automated production and immersive experiences, and audio generation for advancements in voice assistants and sound design.
The content is designed to provide developers with the necessary skills and knowledge to integrate powerful AI features into their projects. Whether building new applications or enhancing existing ones, the insights gained will enable the creation of more dynamic, interactive, and intelligent user experiences. By mastering the Gemini API within Vertex AI and the broader GCP ecosystem, developers will be positioned to harness the latest developments by one of the forefront leaders in this growing field.
- Generative AI
- Introduction to Gemini API
- Overview of Vertex AI
- Prompt Engineering for Text Models
- Text Generation with Gemini API
- Text Models for Information Extraction
- Exploring Gemini's Image and Video Understanding Capabilities
- Hands-on: Image Captioning and Visual Question Answering
- Integrating Multimodal Inputs for Advanced Applications
- Real-world Use Cases for Multimodal Generative AI
- Advanced MLOps Practices with Vertex AI
- Model Monitoring and Explainability on Vertex AI
- Deploying Gemini-powered Applications
- Scaling and Optimization for Production Environments
- Designing and Architecting Generative AI Systems
- Best Practices for Security and Data Privacy
- Install
uv(if needed):
curl -LsSf https://astral.sh/uv/install.sh | sh- Create an environment and install dependencies:
git clone https://github.com/DataForScience/GeminiAI.git
cd GeminiAI
uv venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
uv syncYou'll need accounts with the following services:
| Service | Used in | Where to get it |
|---|---|---|
| Google AI Studio | Modules 1, 3, 4, 5 | aistudio.google.com |
| Google Cloud | Modules 1, 4 | console.cloud.google.com (free tier available) |
Once you have your keys, set the following environment variables (or add them to a .env file):
GEMINI_API_KEY=...
GCP_PROJECT=your-gcp-project-id
jupyter notebookGeminiAI/
├── 1. Gemini Fundamentals.ipynb # Module 1: Gemini API basics
├── 2. Text Generation.ipynb # Module 2: Text generation
├── 3. Multimodal.ipynb # Module 3: Multimodal inputs
├── 4. Deployment.ipynb # Module 4: Deployment
├── 5. E2E Solutions.ipynb # Module 5: End-to-end solutions
├── slides/ # Slides
│ └── GeminiAI.pdf
├── data/ # Logos, author image, and sample assets
├── d4sci.mplstyle # Custom matplotlib style
├── pyproject.toml # Dependency manifest (for `uv sync`)
└── .env # API keys (create this file; do not commit)
- Start with Module 1 and run the notebooks in order (1 → 5).
- If you only want the deck, open
slides/GeminiAI.pdf.
| File | Topic |
|---|---|
1. Gemini Fundamentals.ipynb |
Gemini API and Vertex AI Fundamentals |
2. Text Generation.ipynb |
Gemini API for Text Generation |
3. Multimodal.ipynb |
Multimodal Applications with Gemini API |
4. Deployment.ipynb |
Vertex AI and Deployment Strategies |
5. E2E Solutions.ipynb |
End-to-End Generative AI Solutions |
Running through all notebooks end-to-end costs roughly $1–3 in API calls, depending on how much you re-run cells.
Reach out at info@data4sci.com or open an issue if something isn't working.
|
Web: www.data4sci.com |
