A sample app showing how to use Smart Components, pgvector and OpenAI to generate vector embeddings and implement semantic search in .NET.
Vector embeddings can be generated locally by using Local Embeddings or by using OpenAI API. The generated embeddings are stored in a PostgreSQL database and queried with Entity Framework Core and pgvector-dotnet
- The Illustrated Word2vec
- Vector Embeddings Explained
- Distance Metrics in Vector Search
- Why is Vector Search so fast?
- Vectors are the new JSON in PostgreSQL
- Vectors are the new JSON (PGConf.EU 2023 Recording)
- Postgres is all you need, even for vectors
- Vector Indexes in Postgres using pgvector: IVFFlat vs HNSW
- Understanding vector search and HNSW index with pgvector
- Using Vector Databases for Multimodal Embeddings and Search - Zain Hasan - NDC London 2024