Glossary
Embeddings
Numeric vectors that capture the meaning of text so similar passages sit close together.
An embedding is a list of numbers (a vector) that represents the meaning of a piece of text. An embedding model maps text so that passages with similar meaning produce vectors that are close together in space, even when they share no words. Embeddings are what make semantic search and RAG possible: you can find relevant content by comparing vectors rather than matching exact phrases.
When CertifChat ingests your content, it splits it into chunks and converts each chunk into an embedding, storing the vectors for fast similarity search. At query time, the visitor's question is embedded the same way and compared against those stored vectors to find the closest matches.
CertifChat uses a compact, cost-efficient embedding model and the OpenAI Batch API for bulk indexing, which keeps ingestion fast and inexpensive even for large sites.
See how this works in practice across CertifChat's features.
Related terms
- Retrieval-Augmented Generation (RAG)Grounding an LLM's answers in retrieved source documents instead of its training data alone.
- Vector DatabaseA store optimised for finding the embeddings most similar to a query vector.
- Semantic SearchSearching by meaning using embeddings, often combined with keyword search.
- ChunkingSplitting documents into passages small enough to embed and retrieve precisely.
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.