EnterpriseDB Corp. has announced enhancements to its EDB Postgres AI platform, focusing on hybrid features that streamline artificial intelligence development and processing. The company, which offers a commercial version of the widely-used open-source PostgreSQL database management system, emphasizes the growing trend of enterprises adopting hybrid models that integrate both public and private cloud resources for critical workloads. According to EDB’s research, 56% of enterprises are currently utilizing such hybrid infrastructures.
The newly introduced features facilitate rapid application deployment and management across diverse environments, all from a single control point. Jozef de Vries, the company’s chief product engineering officer, noted that many capabilities unveiled in the spring were initially exclusive to their cloud-hosted system. Now, EDB is extending its cloud-managed experience as packaged software, enabling seamless connectivity between on-premises and cloud databases.
AI acceleration
Among the notable updates is the introduction of an AI Accelerator, leveraging EDB’s Pipelines Extension and integrating pgvector, an open-source PostgreSQL extension designed for handling high-dimensional vector data. This combination empowers users to efficiently test and deploy generative AI applications, such as chatbots and recommendation engines, by automating the entire data pipeline within the PostgreSQL environment.
De Vries explained, “In a traditional Postgres plus pgvector setup, you have the ability to store vectorized embeddings indexed, but then when you do data retrieval or data capture, you have to reach outside of your Postgres ecosystem. We’re building out the capabilities within our AI accelerator extensions so you can do data capture and embedding generation, store those vector embeddings, index them, and facilitate the retrieval all through the P-SQL interface. Developers don’t have to leave the environment they’ve been accustomed to working with.”
Additionally, the new multimodel data management features promise near real-time online analytical processing capabilities, boasting 18 times greater cost efficiency and 30 times faster performance compared to baseline PostgreSQL. De Vries highlighted that multimodel data management accentuates the various data types that PostgreSQL inherently supports, such as structured data, relational data, JSON, and time-series data. This shift aims to reduce reliance on multiple specialty databases for different data types.
Furthermore, an Analytics Accelerator has been introduced, enabling users to query columnar data stored in external object storage using SQL. This feature also supports tiered tables functions, which utilize logical replication to efficiently move frequently accessed data into another storage tier on a cluster without compromising performance.
