26 SEP,2024

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Enhancing data streaming with real-time data
and generative AI
Masudur Rahaman Sayem Partha Sarathi Sahoo
Senior Streaming Solutions Architect Senior Technical Account Manager, Analytics
AWS AWS

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
The evolution of data processing

Rise of real-time
Big data revolution data processing Generative AI-
Batch processing powered data
dominance 2000s 2010s processing

1980s Now

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
 What is generative AI?

• Creates new content and ideas

• Powered by large models that are pretrained
on vast amounts of data
and commonly referred to as foundation
models (FMs)
• Large language model (LLM)

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Large language models (LLMs) are pre-trained vast text
data

Data quality is the biggest challenges in realizing

the potential of generative AI

No inherent ability to access data

Trained with data

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
 Real-time data is a differentiator

Generic Generative AI that knows

generative AI your business and your
customer using real time
data

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
 Continuously collect, store, process, and
deliver data in real-time. Data and models
are no longer static

FMs trained on point-in-time data, and

Why streaming can be inaccurate unless new data is
added
data with
generative AI? Generate faster insights to respond to
customer demands’ and make more
accurate decisions

FMs are good for answering questions

but need to be retrained for domain
specific tasks

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Data streaming and streaming processing with AI

User profile/history/cache

Consumer
application/events/
actions, data lake

Streaming Stream
Streaming
data processing
storage
sources

Generative AI End user

Vector embeddings enabled
application

Inference , vector embeddings

Generative AI model (LLM)

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
 Data streaming and streaming processing with AI

Amazon Amazon Amazon

MemoryDB DynamoDB DocumentDB

Streaming data sources Streaming storage Stream processing

Consumer application/events/ actions User profile/history

Amazon Managed Data Lake

Amazon Amazon
Aurora Service for Amazon
MSK S3
Apache Flink SNS

Amazon Redshift
Amazon
DynamoDB AWS Glue
Amazon
Kinesis
Data Streams End user
AWS Generative AI
Other clients Amazon Amazon enabled
Lambda
OpenSearch Aurora application
Service
Amazon MemoryDB

Inference , vector embeddings Vector embeddings

Amazon Amazon
Bedrock SageMaker

Generative AI model (LLM)

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Sample use cases &
architecture patterns

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Streaming data with generative AI
• Real-time text generation

• Anomaly detection

• Predictive analytics

• Personalized recommendations

• Automated content generation

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Generative AI-powered anomaly
detection: Spotting anomalies in real-time

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Analyzing network flow logs with generative AI
Generative ai-powered anomaly detection: spotting anomalies in real-time

Amazon VPC

Amazon Bedrock

Asynchronous call
to Amazon
SageMaker model
Flow logs endpoint Write generated
Amazon SageMaker AWS Lambda smart alert to SNS Amazon SNS
Network Write anomalous topic
flow logs to events to Kafka
Kafka Topic Topic

Amazon S3 AWS Lambda Amazon MSK Amazon Managed Amazon MSK

Service
for Apache Flink

Amazon S3
Amazon Data
Firehose

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Analyzing network flow logs with generative AI

Amazon VPC

Flow logs
Network
flow logs to
Kafka Topic

Amazon S3 AWS Lambda Amazon MSK

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Analyzing network flow logs with generative AI

Amazon VPC Flink Applications

Studio Notebook
(Java, Scala,
(SQL, Python,
Python
Scala)
+embedded SQL)

Flow logs
Network
flow logs to
Kafka Topic

Amazon S3 AWS Lambda Amazon MSK Amazon Managed

Service
for Apache Flink

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Use Managed Apache Flink notebook to explore
streaming data

xxxxxxxxxxxx

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Use Managed Apache Flink notebook to explore
streaming data

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Analyzing network flow logs with generative AI

Amazon VPC

Asynchronous
call to Amazon
SageMaker
model
Flow logs endpoint Amazon SageMaker
Network
Write anomalous
flow logs to
events to Kafka
Kafka Topic
Topic

Amazon S3 AWS Lambda Amazon MSK Amazon Managed Amazon MSK

Service
for Apache Flink

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Run Apache Flink application

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Flink dashboard

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Flink dashboard

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Query and validate data
Incoming network log record

Processed record with anomaly

86.166.106.57 - - [2024-07-08 07:49:41.265217] "DELETE visit/pick/sort/outside.php?userid=80dd6a19-606d-4475-a488-

9a1482cc682a UNION ALL SELECT CONCAT(0x7171787671,0xSQLinjectionPayl,0x71707a7871),NULL,NULL-- HTTP/1.1" 500
805 "-" "Mozilla/5.0 (Android 4.2.1; Mobile; rv:19.0) Gecko/19.0 Firefox/19.0"

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Analyzing network flow logs with generative AI

Amazon VPC

Amazon Bedrock

Asynchronous call
to Amazon
SageMaker model
Flow logs endpoint Write generated Email alert to
Amazon SageMaker AWS Lambda smart alert to SNS Amazon SNS
the users
Network Write anomalous topic
flow logs to events to Kafka
Kafka Topic Topic

Amazon S3 AWS Lambda Amazon MSK Amazon Managed Amazon MSK

Service
for Apache Flink

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Bedrock to build generative AI Application

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Select model to experiment

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Configure the Lambda

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Configure the Lambda

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Configure the Lambda

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Email alert

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Analyzing network flow logs with generative AI

Amazon VPC

Amazon Bedrock

Asynchronous call
to Amazon
SageMaker model
Flow logs endpoint Write generated Email alert to
Amazon SageMaker AWS Lambda smart alert to SNS Amazon SNS
the users
Network Write anomalous topic
flow logs to events to Kafka
Kafka Topic Topic

Amazon S3 AWS Lambda Amazon MSK Amazon Managed Amazon MSK

Service
for Apache Flink

Amazon S3
Amazon Data
Firehose

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Key takeaways

Combining streaming data and generative AI unlocks powerful

capabilities

AWS streaming data services enable real-time data processing and

seamless integration with generative AI models

Amazon Kinesis, Apache Kafka, and Apache Flink provide

capabilities to continuously capture, store, process, and deliver
data in real-time

Explore workshops and resources to implement in your environment

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Get hands on
Analyzing network flow logs with generative AI Build a real-time streaming generative AI application using Amazon Bedrock,
Amazon Managed Service for Apache Flink and Amazon Kinesis Data Streams

https://aws.amazon.com/blogs/big-data/build-a-real-time-streaming-
https://catalog.workshops.aws/spot-anomalies-flink-lab/en-US generative-ai-application-using-amazon-bedrock-amazon-managed-
service-for-apache-flink-and-amazon-kinesis-data-streams/

Proactively addressing customer concern in real-time with generative

Exploring real-time streaming for generative AI applications
AI, Flink, Kafka and Kinesis

https://aws.amazon.com/blogs/big-data/exploring-real-time-streaming-
https://catalog.workshops.aws/realtime-genai/en-US
for-generative-ai-applications/

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Visit the Migrate. Modernize. Build. resource hub
Dive deeper into these resources:

• 6 steps to success with generative AI

• Understanding the costs of generative AI
• 5 ways a secure cloud infrastructure drives innovation
• 10 ways to optimize costs and innovate with AWS
• Containers and serverless recommendation guide https://tinyurl.com/migrate-modernize-build

• Running Windows workloads on AWS: Your questions answered

• Top 10 reasons to choose AWS for SAP

… and more!

Visit resource hub

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AWS Training and Certification
Access 600+ free digital courses with AWS Skill Builder

Focus on the cloud skills and services that are most relevant to you across
30+ AWS solutions, including digital self-paced learning plans and ramp-up
guides

• Build your future in the AWS Cloud at your own pace

https://skillbuilder.aws/
• Advance your skills and knowledge with learning plans
• Validate your cloud expertise with AWS Certification

Learn your way skillbuilder.aws »

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Why work with an AWS Partner
AWS Partners are uniquely positioned to help your organization at any stage of your
cloud adoption journey, providing

• Innovation – innovative and cost-effective scalable cloud solutions and

capabilities for your organization — helping you keep pace with cutting edge
technology changes

• Expertise – strategic experts and experienced builders, providing

groundbreaking, relevant and reliable solutions to help your business grow Connect with an AWS Partner

• Global Reach – Choose from a global community of trusted AWS Partners

across software, hardware, and services

Connect with an AWS partner

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Thank you for attending AWS Innovate – Migrate. Modernize. Build.

We hope you found it interesting! A kind reminder to complete the survey.

Let us know what you thought of today’s event and how we can improve the event
experience for you in the future.

[email protected]

twitter.com/AWSCloud

facebook.com/AmazonWebServices

youtube.com/user/AmazonWebServices

linkedin.com/company/amazon-web-services

twitch.tv/aws

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Thank you!

© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2024, Amazon Web Services, Inc. or its affiliates. All rights reserved.