Spring AI 2.1 adds VectorStore.upsert for apps that bring their own embeddings
therealdanvega · x · 2026-10-30
Spring AI 2.1 RC1 introduces VectorStore.upsert and a similaritySearch overload that accept application-supplied vectors, letting apps index embeddings computed from images, video, or audio — or imported from batch APIs and other vector databases — without re-running the store's embedding model.
- Example: multimodal embeddings let a "green velvet armchair" text query match a product photo whose description lacks those details
- Video/audio: store segment embeddings with URL and timestamps in metadata so searches jump to the right moment
- Vectors validated for size and NaN before writes; upsert replaces by ID, so stable IDs make re-indexing safe
- Supported in RC1 by PGvector, Redis, Elasticsearch, Qdrant, and OpenSearch, with more stores planned before GA
- Caveat: query and stored vectors must come from compatible models
More from coding & agent
- Vercel's zeeg: We Now Spend Over $50k/Month on AI Security Review Tool Warden — zeeg · 2026-10-30
- YCAMPLIFIEDAMPLIF-amplified amplifies: Herdr is an open-source multiplexer for managing agents across machines — ycombinator · 2026-10-30
- UK Ministry of Justice uses Pydantic as executable contracts for judge-facing AI tools — samuelcolvin · 2026-10-30
- ComfyUI Updater adds one-click Core and Frontend updates with rollback from the Settings dialog — Inuya5haSama · 2026-10-30
- User claims Opus 5.5 built a complete game from one prompt in 1hr 26m, no engine — wes11223344 · 2026-10-30
- Vercel quietly launches "Agentic Infrastructure", positioning itself as the deploy target for coding agents — evilrabbit_ · 2026-10-30