pgEdge, a distributed database for the network edge, has recently announced its incorporation of the pgvector extension.
According to the company, the integration propels AI-driven similarity searches to users’ proximity, enabling faster results.
pgvector is a vector extension for open-source PostgreSQL that enables storing vector embeddings from AI models and performing similarity searches. pgEdge says it enhances PostgreSQL’s performance and accelerates approximate distance searches for vectors.
Phillip Merrick, the co-founder and CEO of pgEdge says that embedding technology is gaining popularity and provides faster and more precise 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,” explains Merrick.
The pgvector extension is highly beneficial for natural language processing applications, especially those utilizing OpenAI’s GPT models. With the emergence of large language AI models (LLMs), there is a growing demand for efficient management and search of extensive, high-dimensional data.
Cemil Kor, the head of product at Enquire AI, lauds the integration, stating, “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.”
Enquire AI, a customer of pgEdge and the developer of AI-powered knowledge discovery products Pulse Marketplace and Lumina, is implementing distributed pgvector using the pgEdge Distributed PostgreSQL database.
The pgvector extension is now accessible for the pgEdge cloud-managed service offering and the self-hosted and self-managed pgEdge Platform
pgEdge Incorporation introduced its distributed edge database system, leveraging the PostgreSQL database earlier this year. Designed to enhance the performance of applications deployed at the network edge, the database provides reduced data latency and high availability for applications at the network edge and across cloud regions, the company says.
At the same time, pgEdge secured $9 million in a seed financing round, with Sands Capital and Grotech Ventures taking the lead.
AI models | network edge | PgEdge