Mm-hmm.

You know, Postgres was right there, and, and it had that ex- that capability through the pgvector extension.

You know, and it's sort of grown somewhere from there.

Postgres in and of itself, you know, would not, maybe not be classified like the best AI database, and there have been various other, you know, databases that have come onto the scene, you know, very focused on AI.

I think it's more because the platform in itself is so adaptable, right? The extensions within Postgres really turn it into a, a multimodal, uh, platform.

And for a lot of developers, it gives them the functionality they need to build new apps or extend their-

Mm-hmm

... existing ones completely within Postgres.

So are we making that easier too?

So this is where AI pipelines in Horizon DB extend AI model management and AI functions even further.

Today, most generative AI apps rebuild the same steps, chunking, creating embeddings, backfilling data, often in fragile external pipelines.

With AI pipelines, all of this is built directly into Postgres.

So you can see here that I've created a pipeline using the create pipeline function in the AI extension.

This chunks the data in a database in real time as it's added.

It will then create embeddings for those chunks using the embedding model that the AI model management enabled for us, and these are ultimately stored in a table.

Why don't we move beyond the database itself and look at what we've done then to help with the building experience of Postgres workloads on Horizon DB?