AI model
OpenAI's large text embedding model, served via API. It returns 3,072-dimension vectors by default and is widely used for semantic search and retrieval.
Sayora's receptionist test found Jev gave the LLM a wrong page on 3% of 168 questions, against 33% for its embeddings. The figure is Sayora's own, from four small-business sites, and transfers only to sites built from single-topic pages.
Reality
Tiger Data says its pg_vectorsearch alpha answers at a 6 ms median and 95% recall on 100M vectors in its own tests. Its release notes say filtered queries can come back short of LIMIT, so we would keep pgvector HNSW in place for now.
Reality
A dev.to walkthrough replaces a managed vector store and a hosted embedding API with sqlite-vec and a local model on port 11434. Its schema declares float[768], so changing model dimension means re-embedding everything.
Reality
Mixedbread's embedding model is reported to edge text-embedding-3-large by half a point. The savings case rests on an arithmetic slip and pricing that does not exist yet.
Reality
Spring AI 2.0 moves schema enforcement to the provider, which trims input tokens on every healthy call. The retry path still bills the whole context again, in full.
Reality
Microsoft's agentic retrieval is now callable from any MCP client, so non-Microsoft agent stacks can stop rebuilding chunking, embedding and permissions. The edges are where the work moved.
Reality