PostgresML: Leveraging Postgres as a Vector Database for AI

With the growing importance of AI and machine learning in modern applications, data scientists and developers are constantly exploring new and efficient ways to store and analyze large amounts of data. While specialized vector databases like Pinecone exist, they are only a part of the solution and require a model provider like OpenAI to generate the embedding vectors. This often comes with a high price tag and requires data to be stored outside of your own datacenter. Enter PostgresML and pgvector - an approach to using Postgres as a complete vector database solution that can also generate the embedding vectors for AI applications.

In this talk, we will explore the benefits of using Postgres as a vector database for AI, including faster and cheaper processing, increased reliability, and greater accessibility. We will also discuss how PostgresML and pgvector can be leveraged to build AI applications that can analyze large volumes of structured and unstructured data. Additionally, we will highlight the advantages of keeping all your data within your own datacenter, while still benefiting from the capabilities of a specialized vector database.

Whether you are a data scientist or a developer, this talk will provide you with an understanding of how Postgres can be used as a vector database for AI and how it can be integrated into your existing application stack. Join us to learn how PostgresML and pgvector can enhance your AI capabilities, while keeping your data secure and accessible.


Date

Thursday Jun 15 / 10:35AM EDT ( 50 minutes )

Location

Dumbo / Navy Yard

Topics

AI/ML Architecture Database Platform Engineering

Share

From the same track

Session Search

Needle in a 930M Member Haystack: People Search AI @LinkedIn

Thursday Jun 15 / 11:50AM EDT

LinkedIn's search functionality is one of its oldest capabilities, allowing members to search for people they know, or to discover new connections.

Speaker image - Mathew Teoh

Mathew Teoh

Machine Learning @ LinkedIn

Session ML in Practice

Back to Basics: Scalable, Portable ML in Pure SQL

Thursday Jun 15 / 02:55PM EDT

Redshift has SageMaker. BigQuery begat BigML. Spark birthed Databricks. Every data warehouse is tightly coupled to a particular ML stack.

Speaker image - Evan Miller

Evan Miller

Principal Statistics Engineer @Eppo (Creator of Evan's Awesome A/B Tools)

Session AI/ML

Going Beyond the Case of Black Box AutoML

Thursday Jun 15 / 01:40PM EDT

Most AutoML tools are black-box tools. They offer no code/low code tools (UI/simple APIs) for practitioners to get started quickly. While this helps beginners, most experienced data scientists/ML practitioners often need more control.

Speaker image - Kiran Kate

Kiran Kate

Senior Technical Staff Member @IBM Research

Session

LLMs in the Real World: Structuring Text with Declarative NLP

Thursday Jun 15 / 04:10PM EDT

Building machine learning pipelines to extract structured data from unstructured text is a popular problem within an unpopular development lifecycle.

Speaker image - Adam Azzam

Adam Azzam

AI Product Lead @Prefect