Truffler: open-source Rails search replaces opaque embeddings with LLM-answered labels
kieranklaassen · x · 2026-09-26
Developer Kieran Klaassen open-sourced truffler, a Jev-powered search library for Rails that adds index-time labeling, query understanding, and streamed reranking on top of your existing keyword and embedding search.
The core idea is "non-black-box embeddings": instead of an embedding model spitting out 1,536 meaningless numbers, you ask an LLM questions about each document — e.g. iscustomer, urgent, aboutbilling, needsreply — and the answers become the vector. An email like "I got charged twice this month, pls fix asap" turns into an interpretable set of boolean/categorical labels.
The project was built via vibe coding and shows how semantic understanding can be grounded in explainable, searchable structured labels.
Related event: Replacing Black-Box Embeddings with LLM-Generated Interpretable Vectors(2 posts)→
More from coding & agent
- Reasonable Team Publishes TLA+ Tutorial: Not a Silver Bullet, AI Agents Could Change That — fhuszar · 2026-09-26
- Using Opus 5.5 to make a video explaining Algorithm W and Hindley-Milner type inference — ctjlewis · 2026-09-26
- Runway MCP brings Gen-4.5 video and image generation into Claude chats — runwayml · 2026-09-26
- One 'Harmless' Agent Permission Turned Into a Backdoor for Everyone — Adorable-Algae6903 · 2026-09-26
- DEV·TV: a single-HTML-file TV playing Hugging Face models and AI papers hits Product Hunt — TradingCardGirl · 2026-09-26
- MCP Wallet Agents Need Boring Permission Rules Before Going Agentic — Any-Sir-7622 · 2026-09-26