Generative AI Training for Developers Overview
This Introduction Generative AI (GenAI) training teaches developers how to build the next generation of intelligent applications. Through hands-on learning and real-world examples, participants master the core concepts of GenAI and large language models (LLMs), gaining the practical skills to develop scalable and innovative software solutions.
Location and Pricing
Accelebrate offers instructor-led enterprise training for groups of 3 or more online or at your site. Most Accelebrate classes can be flexibly scheduled for your group, including delivery in half-day segments across a week or set of weeks. To receive a customized proposal and price quote for private corporate training on-site or online, please contact us.
In addition, some courses are available as live, instructor-led training from one of our partners.
Objectives
- Define and describe the evolution of artificial intelligence, including traditional AI, machine learning, deep learning, and the emergence of generative AI.
- Master the core concepts of large language models (LLMs), including their architecture, training processes, and applications
- Use prompt engineering techniques to communicate with LLMs and elicit desired outputs effectively
- Access and utilize LLMs through APIs, integrating them into various applications and workflows
- Implement Retrieval Augmented Generation (RAG) to connect LLMs with external knowledge sources for enhanced performance
- Deploy LLMs securely and efficiently, considering factors like privacy, data governance, and cost optimization
- Evaluate the capabilities and limitations of LLMs and their potential impact across industries
Prerequisites
- Practical experience in Python (at least 6 months):
- Data Structures, Functions, Control Structures
- Exception Handling, File I/O, async, concurrency (recommended)
- Practical experience with these Python libraries: Pandas, NumPy, and scikit-learn
- Understanding of Machine Learning concepts - regression, clustering, classification
- ML Algorithms: Gradient Descent, Linear Regression
- Loss Functions and evaluation metrics
Outline
Expand All | Collapse All
Introduction to Generative AI
- What is Intelligence?
- Mechanisms of Intelligence
- What is Artificial Intelligence?
- How does AI work?
- Evolution of AI
- Applications of AI
- Traditional AI and Machine Learning
- Deep Learning: Neural Networks
- Emergence of Generative AI
- Transformer Models
Understanding Large Language Models
- What is a Language Model?
- Natural Language Processing (NLP)
- What are Large Language Models (LLMs)?
- Tokenization and Word Embeddings
- Case Study: GPT-3 Model
- Types and Applications of LLMs
- Training and Architectures of LLMs
- Power and Limitations of LLMs
Introduction to Prompt Engineering
- Basics of Prompting and Engineering
- Communicating with Large Language Models
- Effective Prompting Strategies
- Advanced Prompt Engineering Concepts
- Case-Study: GPT-o1
- Ensembling and Iterative Refinement
- Resources for Mastering Prompt Engineering
Accessing LLMs through API
- Closed Source vs. Open Source LLMs
- Accessing LLMs via API
- Utilizing LLM APIs in Applications
- Prompt Templates and Chaining
- Producing Structured Outputs
- Function Calling and LangChain
Introduction to Retrieval Augmented Generation
- Introduction and Advantages of RAG
- RAG Phases – Indexing, Retrieval, and Generation
- Integrating RAG with Knowledge Bases
- Vector Stores and Embeddings in RAG
- Using RAG for Document Summarization
- Managing Large Documents and Knowledge Bases
- Evaluating and Scaling RAG Systems
LLM Deployment
- Security and Privacy in LLM Deployment
- Data Governance and Compliance
- Deploying LLMs for Edge Computing
- Deploying LLMs with Auto-Scaling Capabilities
- Cost Management in LLM Deployment
Conclusion
Training Materials
All Generative AI training students receive comprehensive courseware.
Software Requirements
All attendees must have a modern web browser and an Internet connection.
