Vector Database & pgvector
A vector database is specialized storage optimized to index high-dimensional embeddings and execute sub-second approximate nearest neighbor (ANN) searches.
A vector database is a specialized database system built to store, index, and query high-dimensional vector embeddings using spatial similarity algorithms such as HNSW or IVFFlat.
How Vector Database works in practice
Traditional relational databases index strings and integers for exact equality (`=`) or ranges (`>`). Vector databases index geometric points in 768+ dimensions.
Using distance metrics like cosine distance or Euclidean distance, vector databases can search millions of embeddings in milliseconds to find nearest semantic neighbors.
How SiteMind implements Vector Database
SiteMind uses native PostgreSQL with the `pgvector` extension, eliminating external database hops and keeping vector storage, relational tables, and auth strictly isolated inside one secure system.
Test our AI tools in your browser (100% Free)
Estimate support savings, token counts, or test prompt injection security guardrails with our zero-cost sandboxes.
Related Technical Concepts
Vector Embeddings
Vector embeddings convert text into high-dimensional numerical lists that capture semantic meaning, enabling computers to compare concepts rather than keywords.
Cosine Similarity Thresholds
Cosine similarity measures the angle between two embedding vectors in multidimensional space to determine how closely their meanings match.
Hybrid Search (Dense + Sparse Retrieval)
Hybrid Search merges dense vector search with sparse keyword matching to deliver superior accuracy across both conceptual and exact-term queries.
Test it on your own website in under 2 minutes.
Enter your domain to index your pages and preview live answers.