Supavector QueryLayer

QueryLayer documentation for AI query infrastructure and vector retrieval

Learn how to create an index, sync knowledge sources, call the /v1/memories APIs, and build AI query infrastructure workflows that work with LangChain or your own backend.

What this page covers

  • Covers Index creation, search, ask, boolean_ask, chat, write, sync, and Query portal routes.
  • Useful for developers building AI query infrastructure, vector retrieval, RAG, and grounded answer flows.
  • Explains how to move beyond a raw vector database by adding source sync, direct writes, Query portals, and testing.

Common questions

Can Supavector work with LangChain?

Yes. Supavector can sit behind LangChain or your own runtime as the retrieval and durable query layer while your application keeps its own orchestration and UX.

When should I add full QueryLayer workflows?

Use full QueryLayer workflows when retrieval alone is not enough and you need source sync, grounded answers, index-scoped APIs, Query portals, and durable memory operations together.