GitHub - pgvector/pgvector: Open-source vector similarity search for Postgres

🚀 Looking to enhance your Postgres database with vector similarity search capabilities? Check out pgvector - an open-source tool supporting exact & approximate nearest neighbor search, various distance metrics, indexing options, and more! 💡💻 #AITool #Postgres #OpenSource

pgvector is an open-source vector similarity search tool for Postgres.
It supports exact and approximate nearest neighbor search, L2 distance, inner product, and cosine distance.
Installation can be done on Linux, Mac, and Windows with compilation and installation steps provided.
Usage involves creating tables with vector columns, inserting vectors, and querying nearest neighbors based on distance metrics.
Indexing options include HNSW and IVFFlat for different performance trade-offs.
Aggregates and functions are available for working with vectors.
Troubleshooting tips are provided for common issues like index usage, parallel scans, and index build times.
Performance optimization tips include using index types, setting parameters, and managing memory.
Various language libraries are listed for using pgvector from different programming languages.
Installation notes cover Postgres locations, missing headers, SDKs, portability, and additional installation methods.
Information on upgrading, version history, and contributing to the project is available.