This blog post discusses setting up a Retrieval Augmented Generation (RAG) system, highlighting its application in Generative AI projects. It explains RAG's role in addressing Large Language Models (LLMs) limitations, approaches to implementing RAG, and the critical Extract, Transform, Load (ETL) pipeline for data management. Additionally, it guides on data partitioning, transformation, and persistence to enhance retrieval and generation efficiency.
This blog post explores the benefits of using Testcontainers for database logic testing, highlighting the limitations of in-memory databases and offering insights into optimization techniques for real database testing. It provides a practical guide to integrating Testcontainers with xUnit, Dapper, and FluentAssertions, aiming for more accurate and reliable testing outcomes.
In this blog post, I share my journey from a tech enthusiast to a public speaker at Cloud Technology Townhall Tallinn 2024, highlighting the challenges and growth experienced along the way. Discover the importance of communication, collaboration, and the invaluable support of colleagues in transforming apprehension into accomplishment.
Understanding how the OpenTelemetry collector works by creating my first exporter
Stop referencing your OpenTelemetry exporters in your applications. In this article, we'll explore a great way to decouple them using the OpenTelemetry Collector
