Emoji search without embeddings: pgvector latency questions for a lightweight API
paul_cal · x · 2026-09-27
Developer maxleiter showed you don't need embeddings (Jev) for good emoji search, sharing an implementation. paulcal followed up on the engineering details: if the API uses pgvector, does it rely on saved embeddings, and what's the ms-per-request latency without cached vectors — a potential Jev alternative for some, though not all, use cases.
More from coding & agent
- Stop burning tokens: a Claude Code orchestrator prompt that routes tasks to cheaper models — TawohAwa · 2026-11-11
- Amazon paper: multi-agent setups burn 1.4-4.7x tokens for small gains; single agent is the default — rohanpaul_ai · 2026-11-11
- Dev shows off building a retro FPS entirely via Codex Mobile — 503 tests passing — Dimillian · 2026-11-11
- Explosion launches Ellf directory: 52 NLP templates plus multi-agent annotation workflow — _inesmontani · 2026-11-11
- Meme: 'Stochastic AI Agent Architecture' Is Just a Markov Chain in Disguise — PrasoonPratham · 2026-11-11
- OpenCode adds Gemini 4 Carbon and Claude Fable 5.2 support — dean_rie · 2026-11-11