Embeddings & vector databases
Turn text into coordinates in meaning-space, then search by closeness — the index that makes semantic search and RAG work.
In one line
An embedding model maps text (or images, audio) to a long vector of numbers such that similar meaning lands nearby — so "heart attack" and "myocardial infarction" become neighbours even though they share no words.
How it works
Each chunk of content is embedded once and stored. A query is embedded the same way, and the database returns the nearest vectors by cosine or dot-product distance. At scale, exact comparison is too slow, so indexes like HNSW make approximate nearest-neighbour search fast. Vector storage is either a dedicated engine (Qdrant, Pinecone, Milvus) or an extension in the database you already run — pgvector in Postgres, which is exactly what this platform uses: every Kosha entry carries an embedding column from day one.
Where it shows up in digital health
Semantic search over clinical guidelines ("post-op fever workup" finds documents that never use those words); patient-similarity research; terminology candidate matching in NLP pipelines; and the retrieval half of every RAG assistant, Vaidya included.