Course Outline
Curriculum Structure Training Proposal
Day 1 - Foundations of AI and Python for Data Workflows
• An overview of the current artificial intelligence and machine learning ecosystem
• The significance of AI in contemporary data engineering
• A refresher on Python essentials for AI applications
•• Manipulating data with pandas and NumPy
•• An introduction to API interactions and JSON data management
•• Practical task involving the loading and transformation of datasets
Day 2 - Machine Learning Essentials for Practitioners
•• Core concepts of supervised and unsupervised learning
••• Techniques for feature engineering and data preparation
••• Foundational model training using scikit-learn
••• Assessing model performance and evaluation metrics
••• An introduction to the principles of model deployment
•••• Hands-on creation of a basic predictive model
Day 3 - Fundamentals of LLMs and Prompt Engineering
•••• Understanding the internal workings of large language models
••••• Key concepts including tokenization, context windows, and inherent limitations
•••••• Principles and methodologies for effective prompt design
•••••••• Strategies for zero-shot and few-shot prompting
••••••••• Approaches for evaluating and iterating on prompts
•••••••••• Practical exercises in prompt engineering
Day 4- Developing AI Applications with LLMs
••••••••••••••• Utilising LLM APIs within Python
••••••••••••••••• Concepts of structured outputs and function calling
••••••••••••••••••• Constructing chat-based and task-specific applications
••••••••••••••••••••• Introduction to Retrieval Augmented Generation (RAG)
••••••••••••••••••••••• Connecting LLMs to external data repositories
••••••••••••••••••••••••• Mini-project: Creating a basic AI assistant
Day 5 - Deploying AI Solutions for Production
••••••••••••••••••••••••••• Designing AI workflows that are scalable
••••••••••••••••••••••••••••• Embedding AI capabilities within data pipelines
••••••••••••••••••••••••••••••••••• Monitoring model health and enhancing performance
••••••••••••••••••••••••••••••••••••••••• Strategies for cost optimisation and efficient API usage
•••••••••••••••••••••••••••••••••••••••••••••• Considerations for security and responsible AI
•••••••••••••••••••••••••••••••••••••••••••••••••••••• Final project: Developing a comprehensive 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
