Course Outline
Course Syllabus Training Plan
Day 1 - AI and Python Fundamentals for Data Operations
• Survey of the artificial intelligence and machine learning ecosystem
• The role of AI in contemporary data engineering
• Review of Python essentials for AI contexts
• Manipulating data with pandas and NumPy
• Basics of API interactions and JSON data processing
• Short task: Loading and converting datasets
Day 2 - Machine Learning Essentials for Practitioners
• Principles of supervised and unsupervised learning
• Techniques for feature engineering and data preprocessing
• Fundamentals of model training via scikit-learn
• Assessing model accuracy and performance indicators
• Overview of model deployment principles
• Practical task: Constructing a basic predictive model
Day 3 - Exploring LLMs and Prompt Design
• Analyzing large language models and their operational logic
• Tokenization, context limits, and constraints
• Core principles and methods for prompt design
• Zero-shot and few-shot prompting approaches
• Strategies for prompt assessment and iterative improvement
• Practical prompt design tasks
Day 4 - Developing AI Applications with LLMs
• Utilizing LLM APIs within Python
• Concepts of structured output and function invocation
• Creating chat-driven and task-oriented applications
• Overview of retrieval-augmented generation
• Linking LLMs with external data repositories
• Mini-project: Creating a basic AI assistant
Day 5 - Deploying AI Solutions at Scale
• Architecting scalable AI processes
• Embedding AI into data pipelines
• Monitoring and enhancing model performance
• Strategies for cost management and API usage
• Ethical AI and security considerations
• Capstone project: Developing a complete end-to-end AI solution
Testimonials (2)
The trainer was very available to answer all te kind of question I did
Caterina - Stamtech
Course - Developing APIs with Python and FastAPI
Trainer develops training based on participant's pace
