Extract and Summarize Web Content with OCI Generative AI

Introduction

There’s an insurmountable amount of content online. Summarizations can help with the daily firehose of information, and AI can be instrumental when turnaround time is important. This sample solution shows how you can use the Oracle Cloud Infrastructure (OCI) Generative AI service to help extract and summarize website content for quick and easy understanding and analysis.

Specifically, this example shows how to summarize the top 25 trending projects on GitHub for a given day. The text is read, analyzed, and summarized for publishing when time is of the essence and comprehension is vital.

Organizations can use this approach for content generation pipeline strategies, or individuals can use it to grow their social media following with organic and fresh content. While the example uses GitHub, the same methods can be applied to other text-based web pages.

Demo

Prerequisites and setup

1. Oracle Cloud account—sign-up page
2. Getting started with OCI Generative AI—docs
3. OCI SDK and command-line interface—configuration
4. OCI Generative AI—Python SDK
5. Python 3.10
6. Open source package manager—Conda

Getting started

• Detailed steps and sample code on GitHub

Additional resources

• Tutorial: Extract and Summarize Web Content with OCI Generative AI (11:43)