PostgreSQL as a Vector Database: Part 1, Getting Started With pgvector

We all know PostgreSQL as a relational database for transactional workloads. But, at the same time, PostgreSQL can also be used as a vector database. It possesses all the essential capabilities needed for general-purpose AI applications.

In this hands-on, practical guide, we're starting with the basics. By building an AI app for Airbnb listings, we’ll learn how to store and work with vectorized data in PostgreSQL.

0:00 Postgres as a vector database
0:34 Architecture of a sample AI app
1:50 Application settings
2:30 Testing the Chat Completions API mode
4:14 Loading Airbnb data set and enabling pgvector
7:20 Implementing embedding generation logic
9:23 Generating embeddings with OpenAI
11:09 Implementing similarity search logic for Postgres
14:58 Displaying a list of Airbnb recommendations

Resources:
* The final version of the app:

Curious to learn even more about databases? Follow me here:

[debarghyadasgupta]

Can I achieve the same setup using a local Postgres and Azure OpenAI? Any guidance would be highly appreciated. I'm attempting this on Windows, so my Postgres is running on Windows. I'm interested in using Azure OpenAI embedding to achieve the same result. I watched your video where you demonstrated using an Azure Postgres instance to achieve this.

[MrApalazuelos]

Great material as always thank you 👏 can't wait for the next video 👍

[MrApalazuelos]

Is there a way to create the embeddings inside postgres?

[stasoline]

Great content with focus on production applications, looking forward to seeing the performance focused video next!

[Noufalsalim]

How much does it costs to embed all those description?

[eugenetapang]

Thank you Denis, absolutely perfection, everything in this Postgres playlist is so timely and exactly the elegant and purist vibe that is just Coding ASMR. Thanks buddy, you got a loyal listener here. Keep Rockin!

[PiyushJaiswal-buqp]

Hey you use which version of PostgreSQL?