Amazon has joined the generative AI race with its offering of Amazon Bedrock. With Bedrock, you get access to multiple models (from companies like AI21 Labs, Anthropic, Cohere, Stability AI, and Amazon itself with the Titan models), and you can also create custom models by fine-tuning on your own data. And as you would expect from Amazon, enterprise-level security, privacy, governance and monitoring are baked right in.
In this hands-on tutorial, I’ll show you how to get started using Bedrock, including how to access the models and use the three playgrounds (text, chat and image). Then we’ll move to the APIs, writing some simple Python code to send a prompt and view the response. Finally, I’ll show you how to get started with a custom model and fine-tuning.
?***CODE AND RESOURCES USED IN THE VIDEO***?
• The Python code used in the demo can be found here: https://docs.google.com/document/d/1tvyE8l8Sj4JaR9Il-m6_pYVrliQ7Uu9Hp-hJsGCDnfU/edit?usp=sharing
• Bedrock API reference: https://docs.aws.amazon.com/bedrock/latest/APIReference/welcome.html
• Bedrock pricing: https://aws.amazon.com/bedrock/pricing
?***MY AWS COURSES***?
If you’re interested in getting AWS certifications, check out these full courses. They include lots of hands-on demos, quizzes and full practice exams. Use FRIENDS10 for a 10% discount!
• AWS Certified Cloud Practitioner: https://academy.zerotomastery.io/a/aff_n20ghyn4/external?affcode=441520_lm7gzk-d
• AWS Certified Solutions Architect Associate: https://academy.zerotomastery.io/a/aff_464yrtnn/external?affcode=441520_lm7gzk-d
?***TIMESTAMPS***?
00:00 – A sneak peek at the Amazon Bedrock playgrounds, APIs and custom models
00:47 – Selecting a region where Amazon Bedrock is generally available
01:18 – What is Amazon Bedrock, and what models can I access?
01:53 – Demoing the AI Stylist application to showcase how Bedrock works, aistylist.awsplayer.com
03:14 – Why is it called Bedrock?
03:36 – How much does Amazon Bedrock cost? Pricing information
04:45 – How to get access to the Amazon Bedrock models
05:51 – What’s the differences between the Bedrock base models?
06:29 – Working with the Bedrock playgrounds for chat, text and images
09:29 – Using the Bedrock APIs
09:48 – Creating a Cloud9 environment to run the demo code
10:33 – Using the boto3 Python SDK to interact with the Bedrock models
13:15 – IMPORTANT!! Delete the Cloud9 environment if you created one (I’ll show you how)
13:31 – Getting started with fine-tuning and custom models