DuckDB and Hugging Face workshop turns 2.1M Amazon reviews into an API in one afternoon
JeremyCMorgan · x · 2026-11-19
The DuckDB User Group's first Amsterdam workshop, co-hosted with Hugging Face, walked attendees through building a full pipeline in one afternoon: find products whose ratings are falling across 2.1 million Amazon Reviews 2023 entries, then explain why.
- Local-first workflow: a 22 MB sample was converted into two Parquet tables (reviews and products) by a seconds-fast ingest script; SQL files covered rating distributions, month-by-month product tracking, six-month rating-drop rankings, and surfacing the most helpful 1-2 star reviews.
- Full-scale run: the same ingest script ran as a Hugging Face Job over all 2.1 million reviews inside HF's network, writing Parquet to a Storage Bucket — on $0.01/hour hardware, finishing during a coffee break.
- Orchestration & shipping: Gradio's gr.Workflow chained five Python functions as canvas nodes, and every attendee left with a Hugging Face Space callable as an API.
More from coding & agent
- Switch Buddy builds a full dev team from one prompt: coder, reviewer, debugger in shared rooms — cneuralnetwork · 2026-11-19
- Unverified: Google's rumored Gemini Neon wows with one-shot working Olivetti typewriter — dreamwieber · 2026-11-19
- Zed dev: Gemini 4 Neon solves in one round what 3 frontier models couldn't crack in 9 — vivnat · 2026-11-19
- AUSM: open-source local-first context layer for context-aware macOS apps — HaijunXia · 2026-11-19
- Early tester: Neon 'abnormally good' even before release, watching the model build is stunning — AI_Andrew · 2026-11-19
- System 1 models as harness tools with codemode are underrated, dev says — GabGarrett · 2026-11-19