What is Semantic search?
Verified 5 August 2026
Both the query and every document are converted to vectors by the same model, and retrieval becomes a nearest-neighbour problem. Because the embedding captures meaning rather than spelling, a query for "car" retrieves a document about "automobiles", and — with a multilingual model — a document in German.
The failure mode is exact matching. An error code or a part number has no meaningful neighbourhood in embedding space, so semantic search returns things that are merely about errors. This is why production systems almost always run hybrid.
unlob puts all 101 supported languages in a single shared space, so an English query retrieves a relevant German passage with no translation step and no per-language index.
How unlob handles this: Search modes
Common questions
What is Semantic search?
Semantic search retrieves documents by meaning rather than by word overlap, using vector embeddings to place queries and documents in a shared space.
How does Semantic search work in practice?
The failure mode is exact matching. An error code or a part number has no meaningful neighbourhood in embedding space, so semantic search returns things that are merely about errors. This is why production systems almost always run hybrid.
See it working
The free tier is 10,000 requests a month with no card — enough to test any of this against your own queries.