Skip to content

Max Woolf personal blog

The best way to use text embeddings portably is with Parquet and Polars

minimaxir.com published 2025-02-2414 min read

Never store embeddings in a CSV!

Read on minimaxir.com → Discuss on HN (59) Archived copy

Points: 247
HN comments: 59
Submissions: 1
Cited by: 0 commenters

Databases & Data Software Engineering 2025

On Hacker News

Submitted	Title on HN	Points	Comments
Feb 24, 2025	The best way to use text embeddings portably is with Parquet and Polars by minimaxir	247	59

More from Max Woolf

All 40 posts →

Nano Banana can be prompt engineered for nuanced AI image generation

2025887 points236 commentscited by 4AI & Machine Learning details

Can LLMs write better code if you keep asking them to “write better code”?

2025812 points439 commentscited by 3AI & Machine Learning details

ChatGPT's API is so good and cheap, it makes most text generating AI obsolete

2023632 points428 comments AI & Machine Learning details

OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?

2026443 points437 comments AI & Machine Learning details

As an experienced LLM user, I don't use generative LLMs often

2025388 points207 comments AI & Machine Learning details

I Made Stable Diffusion XL Smarter by Finetuning It on Bad AI-Generated Images

2023331 points64 comments AI & Machine Learning details

Related posts from the same era

ICE using Palantir tool that feeds on Medicaid data

EFF Deeplinks20261,475 points969 comments details

Ingesting PDFs and why Gemini 2.0 changes everything

Sergey's Blog20251,303 points447 comments details

Tracking down the 16-year-old WAL-reset SQLite bug

Tailscale Blog20261,223 points239 commentscited by 3 details

GPT in 500 Lines of SQL

Explain Extended20241,111 points76 commentscited by 3 details

Postgres IDE in VS Code

Microsoft Tech Community20251,040 points407 comments details

PGSimCity - How PostgreSQL Works

nikolays.github.io2026930 points90 comments details