Vector database: simple definition and costs

In brief

A vector database is a storage system designed to search data by semantic similarity rather than exact keyword: each document is turned into a numeric vector, and the search finds the closest ones. It's the technical building block that powers a RAG chatbot on your documents.

• The text is split into passages, converted into vectors (embeddings), then indexed.
• For every question, the question is converted into a vector and the closest passages are retrieved.
• Common options: pgvector (in PostgreSQL/Supabase), Cloudflare Vectorize, or dedicated databases.
• For SMB use, the cost is often included in your existing database: almost zero extra.

The problem, concretely

A classic keyword search fails as soon as the words differ: you search "notice compensation" but the contract says "termination indemnity". A vector database understands meaning: it finds the passage about the same topic, even with different words. That's what makes a chatbot on your documents genuinely useful.

How it works, simply

1. Indexing: your documents are split into passages, each turned into a numeric vector that captures its meaning. 2. Storage: the vectors are stored with their metadata (source, page). 3. Search: your question is turned into a vector, and the database returns the closest passages. 4. Answer: the model writes an answer only from these passages, with the source.

Which vector databases for an SMB

• pgvector: in your existing PostgreSQL (Supabase), free if the instance has headroom. The right default.
• Cloudflare Vectorize: at the edge, for high volume or global latency.
• Dedicated databases (Qdrant, Pinecone): relevant at very high volume, rarely needed for an SMB.

The choice depends on your existing stack: that's precisely what we decide together at the free audit.

Why it matters for you

A well-chosen vector database is the difference between a chatbot that "answers off the mark" and an assistant that cites the right clause. The complete pipeline (indexing, search, citations) is already built and runs in production on beforbuild.com: I adapt it to your documents, at a fixed price from €2,640 excl. tax, no subscription. Detail on the chatbot on your documents page.