From 778c02cfdb6b6fbd75ff1358f5cb2421e00fa390 Mon Sep 17 00:00:00 2001 From: Dj Walker-Morgan Date: Tue, 26 Nov 2024 17:30:12 +0000 Subject: [PATCH] PGVector page filled out Signed-off-by: Dj Walker-Morgan --- .../pipelines/pgvector/index.mdx | 32 +++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) diff --git a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgvector/index.mdx b/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgvector/index.mdx index bc674779434..31e824e4c72 100644 --- a/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgvector/index.mdx +++ b/advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgvector/index.mdx @@ -1,12 +1,40 @@ --- title: "AI Accelerator - PGVector" navTitle: "PGVector" -description: "EDB PGVector is a Postgres extension that provides vector data types and functions to store and manipulate vector data." +description: "PGVector is a Postgres extension that provides vector data types and functions to store and manipulate vector data." +deepToC: true --- It's open source and we use it. +## What is PGVector + +PGvector is an extension for Postgres that enables efficient storage and similarity search of high-dimensional vector data, commonly used for machine learning models, recommendation systems, and natural language processing applications. + +### Part of the EDB Postgres AI platform + +EDB Postgres AI with pgvector delivers a flexible solution for enterprise AI, integrating seamlessly with existing Postgres environments. It outperforms standalone vector databases with 4.22X faster queries and eliminates data silos via integrations with 18X cost-efficient object storage. This unified platform accelerates AI deployment, simplifies management, and ensures up to 99.999% availability, enabling businesses to innovate rapidly and future-proof their data infrastructure without disrupting current operations. + +### Native Vector Data Type Support + +pgvector on EDB Postgres AI enables storage of AI/ML model embeddings as first-class data types, allowing efficient indexing and querying of large volumes of AI data stored in object storage, seamlessly integrated with traditional relational data. + +### Advanced 4.22X Vector Query + +Extends standard SQL with vector-specific operators and functions, enabling complex queries that combine vector operations, relational data, and full SQL capabilities, going far beyond simple similarity searches to support sophisticated AI-driven applications. + +### High-performance Indexing + +With real-time indexing, storage, and querying of AI data, pgvector enables efficient vector similarity search on embeddings from various LLMs, while leveraging Postgres transactionality for consistent handling of mixed workloads. + +### Integrated Vector Data Platform + +pgvector unifies vector database capabilities with EDB Postgres AI's mature enterprise features, ensuring high availability, robust backup/recovery, strong security, and ACID data integrity, all within a single vendor solution for comprehensive data management and AI workloads. + ## Installation -The extension is included with AI Accelerator's Pipelines and installed automatically when it is installed. +The extension is included with AI Accelerator's Pipelines and installed automatically when Pipelines is installed. + +## Further information +For more information on the pgvector extension, see the [pgvector repository](https://github.com/pgvector/pgvector).