Blogsby GlyphOntology driven Dimensional Modeling
To understand how to answer world questions from data models, we don't need semantic layers, we need ontologies
7 of 392 posts
Wed Feb 251 post
Thu Feb 191 post
AI Memory: Understanding Modeling for Unstructured Data
For the data engineering crowd, here’s an explainer of how unstructured AI memory works, though the lens of what we know from working with structured data.
Tue Feb 171 post
Debugging Our Docs RAG, Part 2: Testing New Generation
By upgrading only the generative model, we achieved a 3x accuracy boost but hit a hard ceiling, proving that not only LLMs are needed for good retrieval.
Fri Feb 131 post
Tue Feb 101 post
The Last Mile is Solved by Slop
I didn't vibe-build a product. I wrote a messy scaffold that runs a pipeline, grabs the schema, and forces an agent to build a star schema. It works shockingly well.
Wed Feb 41 post
Finding the UFC GOAT: A Full Stack Pipeline with dlt, dbt and Metabase
Who's the UFC GOAT? Reshef Sharvit built an analytics pipeline using dlt, dbt & Metabase to find out. Automated ingestion meets deep SQL analysis. See the results here.
Tue Feb 31 post
3.7x Faster Pipelines: Benchmarking Arrow & ADBC vs. SQLAlchemy for EL
Moved 5M rows from DuckDB to MySQL 3.7x faster, reducing time from 344s to 92s by switching from SQLAlchemy’s row-by-row path to Arrow + ADBC’s columnar pipeline.