Customizing Generative AI Models

Software

All attendees must have a modern web browser and an Internet connection.

Understanding Generative AI

• Defining Intelligence, Artificial Intelligence, and Generative AI
• Differentiating Generative AI from Traditional AI
• How Generative AI Works
• Tokenization (An entry point to Generative AI)
• Benefits and Challenges of Generative AI
• Popular GenAI Models and Frameworks
• LLM Settings and Parameters
• Prompt Engineering, RAG, Agentic AI, and other advanced concepts

Basics of Prompt Engineering

• Why prompt engineering?
• Techniques for Effective Direct Prompting (Zero-shot)
• Prompting with Examples (One-shot, Few-shot)
• Chain-of-Thought, Tree-of-Thoughts
• Evaluating and Refining Prompts
• Common Mistakes in Prompt Engineering

Building Simple LLM-Based Applications

• Application Design Building Blocks
• Accessing LLMs via APIs
• Prompt Templates
• Conversational Model of Completion
• Closed-Weight vs. Open-Weight Models
• Batch APIs for Cost Control

Evaluating Generative AI Models

• Generative AI Evaluation vs. Predictive AI Evaluation
• Generative AI Evaluation Metrics and Techniques
• Model Comparison and Benchmarking
• Building and Selecting Evaluation Datasets
• Evaluating Custom Criteria
• Chat-Specific Evaluation Metrics

Prompt Engineering for Customization

• Theory of Prompt Engineering
• Modifying Model Behavior with Prompts
• Evaluating the Effectiveness of Prompts
• Automatic Prompt Engineering
• Dynamic Prompt Generation
• Troubleshooting and Refining Prompts

Basics of Retrieval Augmented Generation

• What are embeddings?
• RAG Phases - Indexing, Retrieval, Generation
• Indexing - Preparation, Chunking, Enrichment, and Embeddings
• Working with Structured and Unstructured Documents
• Retrieval - Vector, Full-Text, and Fusion
• Filtering, Reranking, and Looping to Improve Retrieval
• Generation - Providing Context to LLM-Based

Parameter-Efficient Finetuning Techniques

• Parameter-Efficient Finetuning vs. Traditional Finetuning
• Prompt-based methods of Finetuning
• Low-Rank Adaptation Techniques
• IA3 and Other Techniques
• Selecting a PEFT Technique
• Evaluating PEFT Performance

Augmenting Data for PEFT

• Generating Synthetic Data for PEFT
• Leveraging Scaling Laws for Data Augmentation
• Considerations for Synthetic Data
• Balancing Synthetic and Real Data
• Evaluating the Quality of Synthetic Data
• Addressing Bias in Synthetic Data

Basics of Agentic AI with LangGraph

• LangGraph Concepts and Principles
• Common Agentic Patterns
• Multi-Agent Workflows
• Agent Communication and Coordination
• Error Handling in Agentic Systems
• Scaling Agentic AI Applications