Course Outline
Curriculum Outline Training Proposal
Day 1 - Foundations of AI and Python in Data Workflows
• Landscape overview of artificial intelligence and machine learning
• The significance of AI within contemporary data engineering
• Refresher on Python essentials for AI applications
• Data manipulation using pandas and NumPy
• Introduction to API interactions and JSON data processing
• Brief exercise: dataset loading and transformation
Day 2 - Machine Learning Essentials for Practitioners
• Concepts of supervised and unsupervised learning
• Feature engineering and data preprocessing methods
• Fundamentals of model training with scikit-learn
• Assessing model performance and evaluation metrics
• Overview of model deployment strategies
• Practical session: constructing a basic predictive model
Day 3 - LLMs and the Art of Prompt Engineering
• Comprehending large language models and their internal workings
• Tokenization, context windows, and system limitations
• Core principles and techniques for prompt design
• Zero-shot and few-shot prompting methodologies
• Strategies for prompt evaluation and iterative refinement
• Practical exercises in prompt engineering
Day 4- Developing AI Applications with LLMs
• Utilizing LLM APIs within Python
• Concepts of structured outputs and function calling
• Creating chat-based and task-oriented applications
• Introduction to retrieval augmented generation
• Linking LLMs with external data repositories
• Mini project: developing a basic AI assistant
Day 5 - Moving AI Solutions to Production
• Architecting scalable AI workflows
• Embedding AI into data pipelines
• Monitoring and enhancing model performance
• Strategies for cost efficiency and API management
• Security protocols and responsible AI practices
• Capstone project: building 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
