Course Outline
Course Outline Training Proposal
Day 1 - Introduction to AI and Python for Data Workflows
• Overview of the artificial intelligence and machine learning landscape
• The role of AI in contemporary data engineering
• Python fundamentals review for AI applications
• Data manipulation using pandas and NumPy
• Introduction to APIs and JSON data processing
• Mini exercise: Loading and transforming datasets
Day 2 - Machine Learning Foundations for Practitioners
• Supervised and unsupervised learning concepts
• Feature engineering and data preparation methodologies
• Fundamentals of model training with scikit-learn
• Model evaluation and performance assessment metrics
• Introduction to model deployment principles
• Practical exercise: Building a basic predictive model
Day 3 - Introduction to LLMs and Prompt Engineering
• Understanding the operation of large language models
• Tokenization, context windows, and inherent limitations
• Prompt design principles and effective techniques
• Zero-shot and few-shot prompting strategies
• Prompt evaluation and iterative improvement methods
• Practical prompt engineering exercises
Day 4 - Building AI Applications with LLMs
• Utilising LLM APIs in Python
• Concepts of structured outputs and function calling
• Developing chat-based and task-oriented applications
• Introduction to retrieval-augmented generation
• Integrating LLMs with external data sources
• Mini project: Creating a simple AI assistant
Day 5 - Productionizing AI Solutions
• Designing scalable AI workflows
• Integrating AI into data pipelines
• Monitoring and enhancing model performance
• Cost optimisation and API management strategies
• Security and responsible AI considerations
• Final project: Developing an 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
