Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 14 hours
Course Outline
Introduction to Multimodal LLMs in Vertex AI
- Overview of multimodal capabilities within Vertex AI
- Gemini models and their supported modalities
- Applications in enterprise and research contexts
Establishing the Development Environment
- Configuring Vertex AI for multimodal workflows
- Handling datasets across different modalities
- Practical lab: Environment setup and dataset preparation
Long Context Windows and Advanced Reasoning
- Comprehending long-context workflows
- Applications in planning and decision-making
- Practical lab: Implementing long-context analysis
Cross-Modal Workflow Architecture
- Synthesizing text, audio, and image analysis
- Chaining multimodal steps within pipelines
- Practical lab: Designing a multimodal pipeline
Managing Gemini API Parameters
- Setting up multimodal inputs and outputs
- Enhancing inference speed and efficiency
- Practical lab: Tuning Gemini API parameters
Advanced Applications and Integrations
- Developing interactive multimodal agents and assistants
- Integrating external APIs and tools
- Practical lab: Building a multimodal application
Evaluation and Iteration
- Assessing multimodal performance
- Metrics for accuracy, alignment, and drift
- Practical lab: Evaluating multimodal workflows
Summary and Next Steps
Requirements
- Proficiency in Python programming
- Experience in developing machine learning models
- Familiarity with multimodal data types (text, audio, image)
Target Audience
- AI researchers
- Advanced developers
- ML scientists
