PinnedPublished inData Engineer ThingsFrom Scrolls to Similarity Search: Building a Movie Recommender with DuckDB VSSLearn how to use DuckDB’s Vector Similarity Search extension to create a recommendation engine using semantic search and Gemini embeddingsNov 29Nov 29
PinnedPublished inData Engineer ThingsStop Creating Multiple Airflow DAGs for Reloads and Parallel ProcessingModern Airflow and Dynamic Task Mapping to Transform Messy DAG Collections into Clean SolutionsNov 221Nov 221
PinnedPublished inData Engineer ThingsMinds and Machines — AI for Mental Health Support, Fine-Tuning LLMs with LoRA in PracticeExplore the potential of Large Language Models (LLMs) changing the future of mental healthcare and learn how to fine-tune LLMs by exampleMay 192May 192
PinnedPublished inTowards Data ScienceCreate an AI-Driven Movie Quiz with Gemini LLM, Python, FastAPI, Pydantic, RAG and moreDiscover the basics of using Gemini with Python via VertexAI, creating APIs, and the fundamentals of Retrieval-Augmented Generation (RAG)Apr 184Apr 184
PinnedPublished inTowards Data ScienceA Definitive Guide to Using BigQuery EfficientlyMake the most out of your BigQuery usage, burn data rather than money to create real value with some practical techniques.Mar 37Mar 37
Published inData Engineer ThingsThe AI Mirage — The Real Reason Your AI Projects Are FailingExplore the significance of having a skilled data team for AI projects, learn about the Small Data movement and no-code or low-code AI.Nov 41Nov 41
Published inData Engineer ThingsNetflix Maestro and Apache Airflow — Competitors or Companions in Workflow Orchestration?How Netflix Maestro and Apache Airflow complement each other. Delve into their features, strengths, and use cases.Jul 292Jul 292
Published inData Engineer ThingsCreate your own Gemini AI-chatbot with a twist using Python, Jinja2 and NiceGUIDiscover the basics of using Gemini with Python via VertexAI, creating a Web UI with NiceGUI and using Jinja2 to construct modular promptsApr 25Apr 25
Published inData Engineer ThingsEaster egg hunt with BigQuery and User-Defined Functions (UDFs)Discover the basics of extensibility with BigQuery User-Defined Functions (UDFs) with a little Easter egg hunt gameApr 1Apr 1
Published inTowards Data ScienceReal-time Twitch chat sentiment analysis with Apache FlinkLet’s learn about Apache Flink and sentiment analysis by building a real-time sentiment analysis streaming application for the Twitch chatMar 271Mar 271