Module model2vec 

Model2Vec embedding provider.

Uses local Model2Vec static embeddings for instant embedding generation. This is the “fast tier” provider in the 2-tier architecture - generates embeddings in < 1ms for immediate semantic search.

Model2Vec uses pre-computed word vectors with averaging, not neural inference, which is why it’s 200-800x faster than transformer-based providers.

Structs

Model2VecProvider

Model2Vec embedding provider for fast embeddings.