AI and ML in PostgreSQL - You will see how to use PostgreSQL as a practical environment for AI and ML solutions, so you can choose the right architecture, extensions, and use cases for your own projects.
Working with embeddings - You will learn how to install and use pgvector, store embeddings in PostgreSQL, and compare them with similarity metrics to build semantic search and recommendation features.
Python inside database functions - You will learn how to connect PostgreSQL with Python and run ML logic from database functions, so you can automate classification, data processing, and selected analytical tasks.
SQL data preparation - You will practice SQL-based data transformations and exporting datasets to training files, which will help you prepare model input data without building separate, complex pipelines.
AI service integration - You will learn how to connect PostgreSQL with OpenAI, Azure AI, and Hugging Face APIs, allowing you to call external models from database workflows and extend apps with text analysis.
Vector database in practice - You will understand how to use PostgreSQL as a vector database, enabling semantic similarity, contextual search, and AI-ready data handling for modern intelligent applications.
Support ticket case study - Using a support workflow example, you will see how to combine relational data, embeddings, and AI models to classify tickets faster, find similar cases, and support team operations.
Building an AI agent - You will examine how an AI agent for symptom analysis is designed, helping you understand the integration of data, models, and application logic in a realistic implementation scenario.
PostgreSQL knowledge - You should be comfortable writing basic SQL queries in PostgreSQL and understand tables, relationships, and data operations, so you can focus on the AI and ML parts.
Basic Python skills - You should know Python fundamentals, including running scripts, working with libraries, and understanding simple syntax, because part of the training uses Python with PostgreSQL.
Data and API basics - You should understand how data exchange works in formats like JSON and know the basics of API calls, so you can work more easily with AI-as-a-Service integrations.
Basics of data analysis - You should understand core data preparation concepts such as filtering, aggregation, and transformation, because these operations will be used in the SQL exercises.
