GITBOOK-96: No subject

Moloejoe · gitbook-bot · commit 0d6fd11633d2 · 2023-12-03T01:30:35.000Z
diff --git a/pgml-cms/docs/getting-started/README.md b/pgml-cms/docs/getting-started/README.md
@@ -1,3 +1,17 @@
+---
+description: Setup a database and connect your application to PostgresML
+---
+
 # Getting Started
 
-PostgresML is a machine learning extension for PostgreSQL that enables you to perform training and inference on text and tabular data using SQL queries. With PostgresML, you can seamlessly integrate machine learning models into your PostgreSQL database and harness the power of cutting-edge algorithms to process data efficiently.
+A PostgresML deployment consists of multiple components working in concert to provide a complete Machine Learning platform. We provide a fully managed solution in our cloud.
+
+* A PostgreSQL database, with pgml and pgvector extensions installed, including backups, metrics, logs, replicas and high availability configurations
+* A PgCat pooler proxy to provide secure access and model load balancing across tens of thousands of clients
+* A web application to manage deployed models and host SQL notebooks
+
+<figure><img src="../.gitbook/assets/architecture.png" alt=""><figcaption></figcaption></figure>
+
+By building PostgresML on top of a mature database, we get reliable backups for model inputs and proven scalability without reinventing the wheel, so that we can focus on providing access to the latest developments in open source machine learning and artificial intelligence.
+
+This guide will help you get started with a generous free account, that includes access to GPU accelerated models and 5GB of storage, or you can skip to our Developer Docs to see how to run PostgresML locally with our Docker image.
