AIML001 Generative AI On AWS - Build and Scale Generative AI Applications With Foundation Models

I N D I A | M A Y 2 5 , 2 0 2 3
© 2023, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AIML001
Generative AI on AWS - Build and

scale generative AI applications
with foundation models
Praveen Jayakumar
Head of ML Solutions Architecture
AWS India
Question: What is generative artificial intelligence (AI)?
• Creates new content and ideas, including conversations,
stories, images, videos, and music
• Powered by large models that are pretrained on vast corpuses
of data and commonly referred to as foundation models (FMs)
BLOOM
Why foundation models?
Tasks Tasks
… … Text generation Text generation
… … Summarization Summarization
Labeled ML Information Unlabeled Foundation Information

data models extraction data model extraction
… … Q&A Q&A
… … Chatbot Chatbot
Train Deploy Pretrain Adapt
Flexibility
Secure
customization
The most cost-

Why AWS for effective
generative AI? infrastructure
The easiest way

to build with FMs
Generative AI-
powered solutions
Flexibility Choose from a wide
selection of FMs built by
AI21 Labs, Anthropic,
Secure
Stability AI, and Amazon to
customization
find the right model for your
use case.
The most cost-
The easiest way

to build with FMs
Generative AI-
powered solutions
Flexibility
Secure Customize FMs for your

customization business with just a few
labeled examples. Since all
data is encrypted and does
The most cost-
not leave your Amazon
Virtual Private Cloud (VPC),
generative AI? infrastructure you can trust that your data
will remain private and
The easiest way confidential.
to build with FMs
Generative AI-
powered solutions
Flexibility
Secure
customization
The most cost-

Get the best price
performance for generative
AI with infrastructure
powered by AWS-designed
The easiest way ML chips and NVIDIA GPUs.
to build with FMs Cost-effectively scale
infrastructure to train and
run FMs containing hundreds
Generative AI- of billions of parameters.
powered solutions
Flexibility
Secure
customization
The most cost-

Why AWS for effective Quickly integrate and deploy
generative AI? infrastructure FMs into your applications
and workloads running on
AWS using familiar controls
The easiest way
and integrations with the
to build with FMs
depth and breadth of AWS
capabilities and services like
Generative AI- Amazon SageMaker and
powered solutions Amazon S3.
Flexibility
Secure
customization
With generative AI built in,
The most cost- services such as Amazon
Why AWS for effective CodeWhisperer, an AI coding
generative AI? infrastructure companion, can help you
improve productivity. In
addition, you can deploy
The easiest way common generative AI use
to build with FMs cases like call summarization
and question answering using
AWS sample solutions that
Generative AI-
combine AWS AI services with
powered solutions
leading FMs.
Building with generative AI on AWS
Foundation models
available through
Amazon SageMaker
JumpStart
Proprietary Models in
Gated Preview only
Demo
Amazon Bedrock
The easiest way to build and scale
generative AI applications with
foundation models (FMs)
Amazon Bedrock key benefits
Accelerate Choose FMs from Privately customize Enhance your data Use AWS tools and
development of AI21 Labs, Anthropic, FMs using your protection using capabilities that you
generative AI Stability AI, and organization’s data comprehensive AWS are familiar with to
applications using Amazon to find the security capabilities deploy scalable,
FMs through an API, right FM for your use reliable, and secure
without managing case generative AI
infrastructure applications
Bedrock supports a wide range of
foundation models
FMs from Amazon FMs from AI21 Labs, Anthropic, and Stability AI
Titan Text Titan Jurassic-2 Claude Stable

Embeddings Diffusion
Amazon Titan
INNOVATE RESPONSIBLY WITH HIGH-
PERFORMING FOUNDATION MODELS
(FMs) FROM AMAZON
Benefits
• Built with 20+ years of Amazon
ML experience
• Automate language tasks such as
summarization and text generation with
Amazon Titan Text FM
Titan Text Titan Embeddings
• Enhance search accuracy and improve
focused on for enterprise tasks
personalized recommendations with
NLP tasks such as search and
Amazon Titan Embeddings FM
personalization
• Support responsible use of AI by reducing
inappropriate or harmful content
Foundation models from top AI startups
Jurassic-2 Claude Stable Diffusion

Multilingual LLMs for text LLM for conversational and text Generation of unique, realistic,
generation in Spanish, French, processing tasks high-quality images, art, logos,
German, Portuguese, Italian, and and designs
Dutch
Privately customize foundation models
using your organization’s data
Fine-tune
PURPOSE Maximizing accuracy for specific tasks
DATA NEED Small number of labeled examples
Amazon CodeWhisperer
Build applications faster and more securely
with an AI coding companion
CodeWhisperer
BUILD APPLICATIONS FASTER AND MORE SECURELY WITH YOUR AI CODING COMPANION
Code generation
AND AND
Go, Rust, PHP, Ruby, Kotlin, C, C++, CLion, GoLand, WebStorm, Rider,
Shell scripting, SQL, and Scala PhpStorm, RubyMine, and DataGrip
Code generation
• Get multiple code suggestions in seconds based
on natural language (English) description of
coding task and surrounding code
• Code generation can range from single-line
suggestions to full-function blocks
• Provides high-quality suggestions for popular
AWS services
• Generated code matches developer style and
patterns
Reference tracking
• Trained on billions of lines of code
• Flags code similar to open-source training

data
• Tracks accepted suggestions so that you can
provide appropriate attribution
• Enterprise controls to more easily
deactivate/filter code suggestions similar to
open-source training data
Security scanning
• Scan generated and developer-written

code to detect security vulnerabilities
• Receive vulnerability remediation
suggestions
• Scan for hard-to-find security
vulnerabilities
• Supports Python, Java, and JavaScript
Demo
Summary
• Amazon SageMaker Jumpstart – Foundation Model
• Amazon Bedrock
• Amazon CodeWhisperer
skillbuilder.aws
Your time is now

Build in-demand cloud skills your way
Thank you! Please complete the
session survey
Praveen Jayakumar
Head of ML Solutions Architecture
AWS India

AIML001 Generative AI On AWS - Build and Scale Generative AI Applications With Foundation Models

Uploaded by

Copyright:

Available Formats

You might also like

AIML001 Generative AI On AWS - Build and Scale Generative AI Applications With Foundation Models

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

AIML001 Generative AI On AWS - Build and Scale Generative AI Applications With Foundation Models

Uploaded by

Copyright:

Available Formats

I N D I A | M A Y 2 5 , 2 0 2 3

Generative AI on AWS - Build and

… … Text generation Text generation

Labeled ML Information Unlabeled Foundation Information

Train Deploy Pretrain Adapt

The most cost-

The easiest way

The easiest way

Secure Customize FMs for your

The most cost-

The most cost-

Titan Text Titan Jurassic-2 Claude Stable

Jurassic-2 Claude Stable Diffusion

PURPOSE Maximizing accuracy for specific tasks

DATA NEED Small number of labeled examples

• Trained on billions of lines of code

• Flags code similar to open-source training

• Scan generated and developer-written

• Amazon SageMaker Jumpstart – Foundation Model

Your time is now

You might also like