
TimescaleDB has introduced a new open-source extension for PostgreSQL, named pgvectorscale, which significantly enhances the performance and scalability of the database. This extension builds on pgvector and makes PostgreSQL 75% cheaper and 28 times faster compared to Pinecone, a specialized vector database. Pgvectorscale achieves 28x lower p95 latency and 16x higher query throughput on a benchmark dataset of 50 million Cohere embeddings with 768 dimensions each. The introduction of pgvectorscale positions PostgreSQL as a formidable option for AI applications, challenging the need for standalone vector databases. Additionally, TimescaleDB has also introduced pgai extensions, further boosting scalability and usability for AI applications. Both extensions are 100% open-source and freely available.



Timescale introduces pgvectorscale and pgai extensions for PostgreSQL, boosting scalability and usability for AI applications #AI #artificialintelligence #llm #machinelearning #pgai #pgvectorscale #PostgreSQL #Software #Timescale https://t.co/ECZVVX3KIp https://t.co/OBN0ISSLiu
When building AI applications, developers often wonder if they need a standalone vector database or if they can use a general-purpose database like PostgreSQL. 🤔 While dedicated vector databases seem to promise better performance, pgvectorscale challenges this by bringing… https://t.co/tG5YY4fq3l
🤩 Exciting new open source extensions from @TimescaleDB that make PostgreSQL the best database for AI applications. https://t.co/gwSlQGupkX