Getting started with Pipelines

Getting started with Pipelines#

Where to start#

The best place to start is with the AI Accelerator Pipelines overview to get an understanding of what Pipelines is and how it works.

Installation#

Pipelines is included with the EDB Postgres AI - AI Accelerator suite of tools. To install Pipelines, follow the instructions in the AI Accelerator Installation Guide .

Using Pipelines#

After you have Pipelines installed, you can start using it to work with your data.

Log into your Postgres server and ensure the Pipelines extension is installed:

CREATE EXTENSION aidb CASCADE;

This example works solely with Postgres table data, so you don’t need to install the pgfs extension.

For the example, create a table to work with:

CREATE TABLE products (
   id SERIAL PRIMARY KEY,
   product_name TEXT NOT NULL,
   description TEXT,
   last_updated_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP
);
__OUTPUT__
CREATE TABLE

Then insert some data into it:

INSERT INTO products (product_name, description) VALUES
      (Hamburger, A delicious combination of bread and meat),
      (Cheesburger, Improving on a classic, the cheese brings favorite flavors),
      (Fish n Chips, The fish is a little greasy and the chips do not help),
      (Fries, Never sure about these on their own, needs seasoning),
      (Burrito, Always ready for this parcel of edible wonder),
      (Pizza, It is very much a staple, but the rolled dough with toppings does not inspire),
      (Sandwich, The blandest of offerings, the sandwich is predominantly boring bread),
      (Veggie Burger, The ultra-processed vegetable product in this is neither healthy nor delicious),
      (Kebab, Maybe one of the great edible treats, sliced lamb, salad and crisp pitta);
__OUTPUT__
INSERT 0 9

The result is a table with some data in it: food products and some very personal opinions about them.

!!!Note

This example uses simple, processed data. Pipelines can also handle multiple preprocessing steps via Pipelines reference - Preparers .

The core of Pipelines is the knowledge base. A knowledge base is a way to access the data in the table and use it in AI workflows.

Getting started with Pipelines#

See also#

In Pipelines models reference , you can learn how to create more models with Pipelines, including external models from OpenAI API-compatible services.

In Pipelines reference - Preparers , you can learn more about how to create preparers to perform preprocessing steps on your data before embeddings are calculated.

In Knowledge Bases , you can learn more about how to use knowledge bases with external data sources, local files, or S3 storage and how to use the knowledge base functions to get the data you need.

Contents