-
Notifications
You must be signed in to change notification settings - Fork 250
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Signed-off-by: Dj Walker-Morgan <[email protected]>
- Loading branch information
Showing
1 changed file
with
30 additions
and
2 deletions.
There are no files selected for viewing
32 changes: 30 additions & 2 deletions
32
advocacy_docs/edb-postgres-ai/ai-accelerator/pipelines/pgvector/index.mdx
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -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). |