Vector Database

A vector database stores embeddings and helps search by meaning.

Simple idea: it is a database for semantic search.

Why It Matters

Normal databases are good for exact matches:

Find user where email = x

Vector databases are good for meaning-based matches:

Find documents similar to "AI data leakage risk"

How It Works

  1. Convert documents into Embeddings.
  2. Store the vectors with metadata.
  3. Convert the user question into an embedding.
  4. Search for nearby vectors.
  5. Return the most relevant chunks.
  6. Use those chunks in RAG.

Common Options

  • pgvector.
  • Qdrant.
  • Pinecone.
  • Weaviate.
  • Milvus.
  • Elasticsearch vector search.

What to Store

FieldExample
Text chunkParagraph from a policy doc
EmbeddingNumerical vector
SourceGDPR Guide.md
DateLast updated date
PermissionsWho can access it
ProductCookieYes, WebYes, WebToffee

Design Tips

  • Store metadata with every chunk.
  • Use access control for private docs.
  • Re-index when documents change.
  • Track retrieval quality.
  • Avoid sending sensitive data to external systems without review.

CookieYes Ideas

  • Privacy-law knowledge base.
  • Customer support search.
  • Cookie and tracker classification knowledge.
  • AI governance policy retrieval.

Mozilor Ideas

  • Accessibility remediation knowledge base.
  • WooCommerce agent playbooks.
  • Product documentation search.
  • Internal company research search.