Fundamentals of Generative AI and Large Language Models
This section introduces the role of generative AI within modern AI platforms and examines the fundamental concepts behind large language models.
- Overview of generative AI and its role in modern AI platforms
- Understand large language models and transformer architectures
- Explore common enterprise use cases for generative AI
- Identify key challenges associated with deploying generative AI systems at scale
Using Azure Databricks for Generative AI Workloads
Explore how Azure Databricks supports the data processing and machine learning workflows required for generative AI applications.
- Introduction to Azure Databricks as a unified analytics platform
- Use Apache Spark for distributed AI workloads
- Manage data pipelines for generative AI applications
- Integrate Databricks with Azure AI services
Retrieval-Augmented Generation Architectures
This section examines how RAG can connect large language models with external sources of knowledge.
- Understand the principles of Retrieval-Augmented Generation
- Combine vector search with language models
- Design pipelines for contextual data retrieval
- Improve response accuracy and relevance by incorporating external knowledge sources
Multi-Stage and Agent-Style Reasoning Patterns
Explore multi-step and agent-based approaches for developing more sophisticated generative AI workflows.
- Understand multi-step reasoning within generative AI systems
- Design agent-based workflows using large language models
- Orchestrate tools and APIs within AI pipelines
- Improve decision-making through chained reasoning approaches
Fine-Tuning Large Language Models
Learn how large language models can be adapted for particular domains and specialised tasks.
- Overview of fine-tuning methods and approaches
- Prepare datasets for supervised fine-tuning
- Explore parameter-efficient tuning techniques
- Evaluate improvements achieved through fine-tuned models
Evaluating Generative AI Systems
This section focuses on measuring the performance and output quality of LLM-based solutions.
- Key evaluation metrics for large language models
- Automated and human-in-the-loop evaluation strategies
- Identify bias, hallucinations, and model drift
- Apply benchmarking and continual improvement practices
Responsible AI and Governance Considerations
Explore considerations for developing generative AI solutions in a responsible, ethical, and compliant manner.
- Responsible AI principles for generative systems
- Manage risk, bias, and ethical concerns
- Support compliance with organisational and regulatory standards
- Implement governance frameworks for AI solutions
Managing Generative AI Solutions with LLMOps
The final section examines how generative AI solutions can move from experimentation into production and be managed throughout their lifecycle.
- Introduction to Large Language Model Operations (LLMOps)
- Model versioning, monitoring, and lifecycle management
- Deploy generative AI applications into production environments
- Scale and maintain AI systems using Azure Databricks
