Episode

Pyversity with Thomas van Dongen - Weaviate Podcast #132!

Podcast
Weaviate Podcast
Published
Dec 8, 2025
Duration seconds
3631
Processing state
not_requested
Canonical source
https://podcasters.spotify.com/pod/show/weaviate/episodes/Pyversity-with-Thomas-van-Dongen---Weaviate-Podcast-132-e3c1a0o
Audio
https://anchor.fm/s/cffc3468/podcast/play/112289240/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2025-11-8%2F87ec0c57-39c3-10bf-5868-db52fc92dcbc.mp3
JSON
/v1/public/podcasts/weaviate-podcast-6288219/episodes/pyversity-with-thomas-van-dongen-weaviate-podcast-132
Markdown
/podcast/weaviate-podcast-6288219/pyversity-with-thomas-van-dongen-weaviate-podcast-132.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/weaviate-podcast-6288219/episodes/pyversity-with-thomas-van-dongen-weaviate-podcast-132/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/weaviate-podcast-6288219/pyversity-with-thomas-van-dongen-weaviate-podcast-132.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Thomas van Dongen is the head of AI engineering at Springer Nature and the creator of Pyversity! Pyversity is a fast, lightweight open-source Python library for diversifying retrieval results. Retrieval systems often return highly similar items. Pyversity efficiently re-ranks these results to encourage diversity, surfacing items that remain relevant but less redundant. It implements several popular diversification strategies such as MMR, MSD, DPP, and Cover with a clear, unified API.