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 no separate vector service to stitch together. Every search is filtered to the account and chatbot being asked.
Similarity search returns a short list of candidate passages. CertifChat merges that list with the results of a Postgres full-text keyword search using reciprocal rank fusion, and passes only the top-ranked few to the model.
Read how they fit together in What is a RAG chatbot?.
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. Start on Starter: 7 days for a one-time $9.