Weaviate shows how to turn a messy creative archive into semantic search without renaming files
philipvollet · x · 2026-09-09
Part 3 of Weaviate's Building Foundry series turns a badly named creative archive (finalFINALv7.svg territory) into a searchable library. The pipeline: a read-only scanner walks the folder → builds a manifest and descriptions → syncs to a Weaviate collection → supports keyword, semantic, or hybrid search → results link back to source assets, with nothing moved or renamed.
Each asset gains context from descriptions, tags, extracted text, and metadata. The test archive holds 23 assets from five projects. Searching "white rabbit in a grassy landscape" retrieves a reference image, a trailer clip, and related landscape assets even when filenames don't match. Teams remember moods and scenes; the archive only remembers filenames—this bridges that gap.
More from coding & agent
- Yoav Goldberg proposes a new agent eval: locating real GitHub artifacts via API — yoavgo · 2026-09-09
- OpenAI's Navier-Stokes proof reportedly used ~10,000 coordinating AI agents — mark_k · 2026-09-09
- Open-source Aurora: Go LLM gateway fork claims 55x LiteLLM speed and fixes OpenCode session lockout — entitybtw · 2026-09-09
- Can agents resolve vague human references like 'the change that broke token refresh'? — yoavgo · 2026-09-09
- Dev open-sources local prompt optimizer on DSPy+Ollama, boosting llama3.2 3B from 39% to 89% with GEPA — MortisAndTen · 2026-09-09
- Dev picks Amp over Codex for thread-focused agent UI — carlosdponx · 2026-09-09