pgEdge has announced its support for pgvector extension that adds an open-source vector similarity search capability to PostgreSQL. This integration will allow PostgreSQL users to harness power of AI (artificial intelligence) to do similarity searches and inference closer to end users, for results.
pgvector is an increasingly popular vector extension for PostgreSQL to store vector embeddings from AI models and to provide similarity search capabilities. This extension enhances PostgreSQL by introducing a vector data type named “vector,” along with three query operators designed for similarity searching Euclidean, negative inner product, and cosine distance. It also incorporates the “ivfflat” (inverted file with stored vectors) indexing mechanism, which increases approximate distance searches for vectors, thereby improving performance.
The pgvector extension is useful with applications involving natural language processing, including those built on OpenAI’s GPT models. However, rise of large language AI models (LLMs) has created a tremendous need to manage and search large-scale, high-dimensional data. “The solution to this challenge lies in vector databases, a powerful and increasingly popular embedding technology that enables faster and more accurate searches. Pairing pgvector with pgEdge’s distributed Postgres database providing multi-region replication, users get results more quickly and a broader range of applications can take advantage of the AI capabilities it offers.” says Phillip Merrick, co-founder and CEO of pgEdge.
“pgEdge combined with the pgvector extension is a powerful combination that puts inference and similarity search requests closer to the users giving them faster search results regardless of where they are located,” says Cemil Kor, head of product at Enquire AI.
Enquire AI is deploying distributed pgvector via pgEdge distributed PostgreSQL database. The pgvector extension is now available for both pgEdge cloud managed service offering, and self-hosted and self-managed pgEdge platform product.
For more information visit here.
