Glossary
Vector Database
A store optimised for finding the embeddings most similar to a query vector.
A vector database stores embeddings and retrieves them by similarity rather than by exact match. Given a query vector, it returns the stored vectors closest to it, which correspond to the passages most semantically related to the question. This is the retrieval engine behind semantic search and RAG.
CertifChat stores embeddings in Postgres using the pgvector extension, so vector search runs alongside the rest of the application data with full SQL access and row-level isolation per account. That keeps each business's content private and avoids stitching together a separate vector service.
Similarity search returns a small set of candidate passages, which are then reranked so only the most relevant few are passed to the model, typically the top three to five.
See how this works in practice across CertifChat's features.
Related terms
- EmbeddingsNumeric vectors that capture the meaning of text so similar passages sit close together.
- Retrieval-Augmented Generation (RAG)Grounding an LLM's answers in retrieved source documents instead of its training data alone.
- Semantic SearchSearching by meaning using embeddings, often combined with keyword search.
- Knowledge BaseThe collection of content an assistant draws on to answer questions.
Put your knowledge to work today
Connect your sources, drop one snippet on your site, and start deflecting tickets. We are opening CertifChat to a first group soon.