GPTfy Glossary
Embeddings
Numeric vector representations of text that capture semantic meaning — the foundation of semantic search, RAG, and most modern NLP applications.
An embedding is a list of numbers (typically 384, 768, 1536, or 3072 dimensions) that represents a piece of text in a high-dimensional space. Texts with similar meanings end up near each other in this space, regardless of exact word overlap — "purchased shoes online" and "ordered sneakers from a website" produce nearby embeddings.
Embeddings power semantic search: instead of matching keywords, search becomes "find vectors near this query vector." In Salesforce contexts, this is how RAG systems retrieve relevant Knowledge Articles, prior Case resolutions, or related Opportunities — by comparing the embedding of a new question to a vector database of embedded company content.
Common embedding models: OpenAI's text-embedding-3-small/large, Cohere's embed, open-source alternatives like sentence-transformers. The choice affects search quality, cost, and infrastructure (some embeddings can run on-device, others require API calls).
See Embeddings in GPTfy
Book a 30-minute demo with a GPTfy engineer to see how this works in a Salesforce org like yours.
Book a demo