Can LLMs make better decisions with documentation access? 25 LLMs tested across a 365-day WWTP simulation in 3 RAG modes — BARE, PASSIVE, and ACTIVE RAG.

This repo contains datasets used in trainings.

Systematic LLM behavioral analysis through domain-specific engineering benchmarks — 13 benchmarks, 22 models, 13 reports documenting how LLMs reason, fail, and produce convincing wrong answers

AI assistant that queries databases using natural language questions

An intelligent agent that uses multiple APIs through natural language - Learning project for AI agents

AI-powered data analysis assistant with planning and execution capabilities

Data Engineering Zoomcamp is a free 9-week course on building production-ready data pipelines. The next cohort starts in January 2026. Join the course here 👇🏼

This repo is for generating data from existing dataset to a file or producing dataset rows as message to kafka in a streaming manner.