microsoft/MSVBASE
MSVBASE is a system that efficiently supports complex queries of both approximate similarity search and relational operators. It integrates high-dimensional vector indices into PostgreSQL, a relational database to facilitate complex approximate similarity queries.
MSVBASE helps you efficiently query large datasets containing both traditional numerical/text data and high-dimensional vector data. You input your existing scalar and vector data, and it allows you to find items that are both similar (e.g., matching a product image) and meet specific criteria (e.g., within a certain price range). This is ideal for database administrators or data engineers building systems that need fast, combined searches.
103 stars. No commits in the last 6 months.
Use this if you need to perform complex searches that combine finding similar high-dimensional data (like embeddings for images, text, or products) with standard database filtering on scalar values, all within a familiar PostgreSQL environment.
Not ideal if your queries only involve simple keyword searches or exact matches on scalar data, or if you don't use PostgreSQL as your primary relational database.
Stars
103
Forks
13
Language
C++
License
MIT
Category
Last pushed
Nov 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/microsoft/MSVBASE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
tensorchord/VectorChord
Scalable, fast, and disk-friendly vector search in Postgres, the successor of pgvecto.rs.
tensorchord/vechord
Turn PostgreSQL into your search engine in a Pythonic way.
postgresml/postgresml
Postgres with GPUs for ML/AI apps.
soulteary/portable-docker-app
🎩 Magic in Pocket / 🪄 口袋里的“魔法”.
andreiramani/pgvector_pgsql_windows
pgvector - a PostgreSQL extension (native compiled in Microsoft Windows environment)