https://nalar.dev/tags/embeddings/ Recent content in Embeddings on Nalar Hugo en-us Tue, 01 Sep 2026 00:00:00 +0700 https://nalar.dev/version-embeddings-for-safe-semantic-search/ Tue, 01 Sep 2026 00:00:00 +0700 https://nalar.dev/version-embeddings-for-safe-semantic-search/ <p>Semantic search systems often look simple from the outside: encode a document, store its vector, encode a query, and compare the vectors. The operational difficulty appears later, when the embedding model changes.</p> <p>Two models can produce vectors with the same dimension and still define completely different coordinate spaces. Mixing vectors from model A with query vectors from model B can silently destroy ranking quality without producing an obvious error.</p> <p>The safe approach is to treat an embedding model as a versioned data dependency, not a drop-in function.</p>