Skip to content

Vector database

πŸ“ Short definition

Database that stores numeric representations (vectors) of documents and finds those closest to a query by mathematical similarity.

πŸ“– Detailed definition

Each document is converted to a vector (embedding) by a specialized model. On search, the query is also embedded and the database returns documents whose vectors are closest (cosine similarity or dot product).

Common solutions in 2026: Qdrant, Milvus, Chroma (lightweight local), Weaviate. Most are open source and deployable on-prem.

Main limit in classic RAG: search is β€œblind”—it finds textually close passages but can miss complex semantic links or entity relationships. That is what GraphRAG tries to address.

πŸ’‘ Why it matters for on-prem AI

Central building block of standard RAG. Must be deployed locally to preserve data sovereignty.

⚠️ Common pitfalls

  • Returning too many hits (e.g. top-20) bloats the prompt and saturates the model context window.
  • Embedding quality is critical: a poor embedding model gives poor search results regardless of the database.
  • Cross-tenant data leakage β€” in a multi-user environment, a query can return documents from another tenant if no isolation filter (namespace, tenant_id in metadata) is applied on every search. ACLs at ingestion are not enough: the filter must be re-evaluated at query time. See LLM08 β€” Vector & Embedding Weaknesses.

πŸ“š Go deeper

  1. 🧩 RAG & Agents (full RAG pipeline and agentic alternatives)

πŸ”— See also

Give my opinion

Everything is optional: one answer is enough. This site sends nothing: you send it, the way you choose.

Your noteNo note
Your opinion is about
About what? (several choices possible)
What will be sent
Send by e-mail

Private, no account: opens your mail program with the message ready, for ia-on-prem@damien.becherini.fr.

Open a GitHub issue β†—

Public, with a GitHub account. You read the issue again before you publish it.

To paste it wherever you want.

Give at least a note, a subject or a message to be able to send.