SlideShare a Scribd company logo
UPDATE THIS PRESENTATION HEADER IN SLIDE MASTER
AWS UG Torino
Meetup 2024 #3
1 8 / 06 / 2 0 2 4
UPDATE THIS PRESENTATION HEADER IN SLIDE MASTER
AWS USER GROUP TORINO
ENTRA NEL GRUPPO WHATSAPP!
UPDATE THIS PRESENTATION HEADER IN SLIDE MASTER
© 2024, Amazon Web Services, Inc. or its affiliates. Allrights reserved. Amazon Confidential and Trademark.
Calendario 2024:
AWS UG TORINO MEETUP:
• 19/02/2024 ✓
• 16/04/2024 ✓
• 18/06/2024 oggi
• 02/10/2024
• 19/11/2024
UPDATE THIS PRESENTATION HEADER IN SLIDE MASTER
Rinfresco &
Networking
Agenda di oggi
AWS UG Torino Meetup 2024 #3
Carlo Peluso
AI Agents on AWS: Deep-
dive on Amazon Bedrock
Agents
Davide De Sio
Serverless e DevOps per
migliorare la DevXP
UPDATE THIS PRESENTATION HEADER IN SLIDE MASTER
© 2024, Amazon Web Services, Inc. or its affiliates. Allrights reserved. Amazon Confidential and Trademark.
Davide De Sio
Serverless e DevOps per
migliorare la DevXP
AW S UG TO R IN O M E E TU P 2 0 2 4 # 3
Superpower REST API DX
with Serverless and
DevOps Best Practices on
AWS
Come ridurre la complessità dell’infrastruttura con
AWS e migliorare la DevExperience attraverso pratiche
DevOps
Elev a
Srl
Chi Sono
Davide De Sio
Development Tech Lead @Eleva
AWS Solutions Architect (Professional)
Senior Full Stack Developer
“The essence of the serverless trend is the absence
of the server concept during software development.”
Tomasz Janczuk, VP at Auth0
Serverless Enthusiast
AWS UG Lead - Pavia
Use Case 1
Mobile Backend
Use Case 2
Single Page Application
Perché Serverless?
Cosa mi aspetto?
Voglio che l’architettura
scali in automatico (auto-scaling)
Voglio che gli sviluppatori
si concentrino nello scrivere
la business logic
Non voglio pagare
quando non utilizzo risorse (idle)
Voglio che il team di sviluppo si concentri su quello che conta
davvero, potendo far affidamento su una piattaforma di
sviluppo che massimizzi la Developer Experience e la renda
semplice, piacevole, ripetibile e manutenibile.
AWS User Group Torino 2024 #3 - 18/06/2024
Infrastructure as code
Infrastruttura dichiarata come codice
Documentation as code
Documentazione dichiarata come codice
Automated Testing
Test automatici basati sulla documentazione
CI/CD
Pipelines di distribuzione automatizzate
DR
Procedure di Disaster Recovery
Versioning
Versionamento del singolo micro-servizio
API Architecture
Pratiche DevOps
Security By Design
Best practices di sicurezza
Monitoring
Monitoraggio continuo
Provisioning (senza overhead)
Esposizione tramite Amazon API Gateway, Amazon Cloudfront
e Amazon Route 53
Esecuzione su funzioni serverless tramite AWS Lambda
CI/CD
Release tramite strumenti di infrastracture as code
(AWS Cloudformation/SAM/CDK/Serverless Framework)
Esecuzione del rilascio e dei test su pipeline per CI/CD
(AWS Codepipeline e AWS Codebuild) a partire da commit su
branch finalizzati al versionamento e al rilascio di repo Git
API Architecture
Key points
API Architecture
Key points
Doc first / Doc generation
Documentazione come codice secondo standard Open API V3 (via Serverless
Framework)
Generazione della documentazione su pagine statiche (via Redocly) storicizzate
su Amazon S3 e integrazione nella pipeline di distribuzione
Automated Testing
Implementazione di test che validano le API in base alle specifiche Open API V3
generate
Security first e monitoring
Messa in sicurezza con Managed Services
AWS IAM / VPC / WAF / Guard Duty
Monitoraggio tramite AWS X-Ray e Cloudwatch
(dashboard e allarmi)
Show me
the (infra) code!
CloudFormation per estensioni (security -
cognito)
Documentazione integrata
(doc-as-code)
Serverless files
Infrastructure as Code
Plugin per monitoraggio
(slic-watch)
Plugin per local environment
(serverless-offline)
CloudFormation per architettura
a supporto e CI/CD come codice
(buildspec) su CodePipeline e
CodeBuild
Talk is cheap
Show me the code
Serverless Skeletons
Open Source
Node.js PHP Python
Textract: Example Use Case
EU-Driving Licences OCR
AWS User Group Torino 2024 #3 - 18/06/2024
AWS User Group Torino 2024 #3 - 18/06/2024
Bonus
«Non tutte le ciambelle vengono col buco»
https://www.primevideotech.com/video-streaming/scaling-up-the-prime-video-audio-video-monitoring-
service-and-reducing-costs-by-90
Bonus
«Don't get locked up into avoiding lock-in»
https://martinfowler.com/articles/oss-lockin.html
• Vendor Lock-In
• Product Lock-in
• Version lock-in
• Architecture lock-in
• Platform lock-in
• Skills lock-in
• Legal lock-in
• Mental Lock-in
UPDATE THIS PRESENTATION HEADER IN SLIDE MASTER
© 2024, Amazon Web Services, Inc. or its affiliates. Allrights reserved. Amazon Confidential and Trademark.
Carlo Peluso
AI Agents on AWS: Deep-
dive on Amazon Bedrock
Agents
AW S UG TO R IN O M E E TU P 2 0 24 # 3
AI AGENTS ON
AMAZON BEDROCK
Carlo Peluso | Solutions Architect @ Storm Reply
INTRODUCTION
ABOUT ME
2018 – Started working as Backend Engineer
2020 – Bachelor’s Degree in Computer Science Engineering
2022 – Master’s Degree in Data Science and Engineering
2022 – Started working as Solutions Architect @ Storm Reply
2022 – Q1 Publication on Transformers for Healthcare
INTRODUCTION
TODAY’S TOPIC: AI AGENTS
WHAT
are AI agents?
WHY
AI agents
are useful?
HOW
AI agents
can be
implemented?
ARTIFICIAL INTELLIGENCE
FROM SHALLOW ARCHITECTURES TO LARGE LANGUAGE MODELS
Increasing number of hidden layers…
NEURAL NETWORKS & CNNs
AlexNet, ResNet, …
TRANSFORMERS & LLMs
BERT, Claude, Mistral, GPT-3, …
SHALLOW ARCHITECTURES
Support Vector Machines, Decision Trees, …
DEEP NEURAL NETWORKS
TRAINING COMPLEXITIES
HIGH NUMBER OF
HIDDEN LAYERS
LOTS OF DATA AND
HIGHLY PERFORMANT
COMPUTATIONAL
RESOURCES
BILLIONS OF
TRAINING
PARAMETERS
IMPLY REQUIRE
CAN WE
EXPLOIT PRE-TRAINED AI MODELS
FOR DATA SPECIFIC FROM OUR DOMAIN?
EXPLOIT PRE-TRAINED AI MODELS
FINETUNING
PRE-TRAINED MODELS CAN BE FINETUNED
(i.e., SMOOTHLY RETRAINED)
ON DATA FROM AN UNKNOWN DOMAIN
STILL…
WITH GENERATIVE AI MODELS
WE CAN USE A MORE
STRAIGHTFORWARD APPROACH!
EXPLOIT PRE-TRAINED AI MODELS
IN-CONTEXT LEARNING
COLLECT UNKNOWN DOMAIN DATA
WITHIN A KNOWLEDGE BASE
INPUT CONTEXT INFORMATION
FROM THE KNOWLEDGE BASE
TO THE GENERATIVE AI MODEL
EXPLOIT PRE-TRAINED AI MODELS
IN-CONTEXT LEARNING
THE GENERATIVE AI MODEL CAN
COMPENSATE THE
MISSING DOMAIN KNOWLEDGE
BY EXPLOITING
IN-CONTEXT INFORMATION
Qual è
la capitale
della Grecia?
IN-CONTEXT LEARNING
EXAMPLE
La capitale della Francia è Parigi.
La capitale dell’Italia è Roma.
La capitale della Spagna è Madrid.
La capitale della Grecia è Atene.
La capitale
della Grecia
è Atene.
Semantic search
Provide in-context information to the LLM
1
2
3
4
1
2
3
4
The user asks a question.
The question is used to retrieve from the knowledge base
the documents semantically closer to the question.
The documents retrieved are fed to the LLM, alongside the original
question and a system prompt (that describes how the LLM should
respond).
The LLM, based on the context provided and the system prompt,
answers the question.
SEAMLESSLY BUILD AND MAINTAIN
VECTOR DATABASES USING
DOCUMENTS FROM YOUR DOMAIN
EASILY INTEGRATE LEADING LLMs,
DELEGATING INFRASTRUCTURE
MANAGEMENT
GENERATIVE AI ON AWS
AMAZON BEDROCK
FOUNDATION MODELS
KNOWLEDGE BASES
AMAZON BEDROCK
KNOWLEDGE BASES
AMAZON BEDROCK
KNOWLEDGE BASES
Textual documents, PDFs,
CSVs, JSON, …
AMAZON S3
AMAZON
RDS
AMAZON
OPENSEARCH
Text to vector representations
IN-CONTEXT LEARNING
EXAMPLE USING AMAZON BEDROCK
La capitale della Francia è Parigi.
La capitale dell’Italia è Roma.
La capitale della Spagna è Madrid.
La capitale della Grecia è Atene.
AMAZON BEDROCK
KNOWLEDGE BASES
AMAZON BEDROCK
FOUNDATION MODELS
Qual è
la capitale
della Grecia?
1
1 The user asks a question.
IN-CONTEXT LEARNING
EXAMPLE USING AMAZON BEDROCK
La capitale della Francia è Parigi.
La capitale dell’Italia è Roma.
La capitale della Spagna è Madrid.
La capitale della Grecia è Atene.
AMAZON BEDROCK
KNOWLEDGE BASES
AMAZON BEDROCK
FOUNDATION MODELS
Qual è
la capitale
della Grecia?
API call: knowledgeBase.retrieve(question)
1
2
1
2
The user asks a question.
The question is used to retrieve from the knowledge base
the documents semantically closer to the question.
IN-CONTEXT LEARNING
EXAMPLE USING AMAZON BEDROCK
La capitale della Francia è Parigi.
La capitale dell’Italia è Roma.
La capitale della Spagna è Madrid.
La capitale della Grecia è Atene.
AMAZON BEDROCK
KNOWLEDGE BASES
AMAZON BEDROCK
FOUNDATION MODELS
Qual è
la capitale
della Grecia?
API call: knowledgeBase.retrieve(question)
API call: bedrock.invoke_model(context)
1
2
3
1
2
3
The user asks a question.
The question is used to retrieve from the knowledge base
the documents semantically closer to the question.
The documents retrieved are fed to the LLM, alongside the original
question and a system prompt (that describes how the LLM should
respond).
IN-CONTEXT LEARNING
EXAMPLE USING AMAZON BEDROCK
La capitale della Francia è Parigi.
La capitale dell’Italia è Roma.
La capitale della Spagna è Madrid.
La capitale della Grecia è Atene.
AMAZON BEDROCK
KNOWLEDGE BASES
AMAZON BEDROCK
FOUNDATION MODELS
Qual è
la capitale
della Grecia?
La capitale
della Grecia
è Atene.
API call: knowledgeBase.retrieve(question)
API call: bedrock.invoke_model(context)
1
2
3
4
1
2
3
4
The user asks a question.
The question is used to retrieve from the knowledge base
the documents semantically closer to the question.
The documents retrieved are fed to the LLM, alongside the original
question and a system prompt (that describes how the LLM should
respond).
The LLM, based on the context provided and the system prompt,
answers the question.
STILL,
RETRIEVE AND GENERATE
APPLICATIONS ARE SOMEHOW
“STATIC”
FOUNDATION MODELS
ORCHESTRATE TASKS BY
EXPLOTING A KNOWLEDGE BASE
AND
DYNAMICALLY INVOKING APIs
AI AGENTS
AI AGENTS ON AMAZON BEDROCK
ACTION GROUPS
DEFINE ACTIONS THAT THE AGENT CAN PERFORM
AI AGENTS ON AMAZON BEDROCK
ACTION GROUPS
LAMBDA FUNCTIONS
DEFINE HOW THE AGENT HANDLES
THE PARAMETERS IT RECEIVES
OPENAPI SCHEMAS
DEFINE THE PARAMETERS THE
AGENT MUST EXTRACT FOR THE
ACTION TO BE EXECUTED
AI AGENTS ON AMAZON BEDROCK
ACTION GROUPS
AI AGENTS
WORKFLOW
AI AGENT IS INPUT VALID?
PREPROCESSING
PROMPT
1
1 The agent verifies that the user input is not malicious.
AI AGENTS
WORKFLOW
AI AGENT IS INPUT VALID?
SEARCH WITHIN THE
KNOWLEDGE BASE
CALL AN API
ORCHESTRATION
PROMPT
WHICH ACTION
SHOULD I TAKE?
PREPROCESSING
PROMPT
1 2
1
2
The agent verifies that the user input is not malicious.
The agent creates an orchestration prompt using:
• User’s input
• Conversation history
• Information about knowledge bases and available APIs
• Instructions provided by the system developer
AI AGENTS
WORKFLOW
AI AGENT IS INPUT VALID?
PERFORM ACTION
SEARCH WITHIN THE
KNOWLEDGE BASE
CALL AN API
RESPONSE
ORCHESTRATION
PROMPT
WHICH ACTION
SHOULD I TAKE?
PREPROCESSING
PROMPT
1 2
3
1
2
3
The agent verifies that the user input is not malicious.
The agent creates an orchestration prompt using:
• User’s input
• Conversation history
• Information about knowledge bases and available APIs
• Instructions provided by the system developer
The Foundation Model choose which action should be taken.
AI AGENTS
WORKFLOW
AI AGENT IS INPUT VALID?
PERFORM ACTION
SEARCH WITHIN THE
KNOWLEDGE BASE
CALL AN API
RESPONSE
ORCHESTRATION
PROMPT
WHICH ACTION
SHOULD I TAKE?
OBSERVATION
PREPROCESSING
PROMPT
1 2
3
4
1
2
3
4
The agent verifies that the user input is not malicious.
The agent creates an orchestration prompt using:
• User’s input
• Conversation history
• Information about knowledge bases and available APIs
• Instructions provided by the system developer
The Foundation Model choose which action should be taken.
The action’s output is an observation that is used to enrich
the orchestration prompt.
AI AGENTS
WORKFLOW
AI AGENT IS INPUT VALID?
PERFORM ACTION
SEARCH WITHIN THE
KNOWLEDGE BASE
CALL AN API
RESPONSE
ORCHESTRATION
PROMPT
WHICH ACTION
SHOULD I TAKE?
OBSERVATION
PREPROCESSING
PROMPT
1 2
3
4
5
1
2
3
4
5
The agent verifies that the user input is not malicious.
The agent creates an orchestration prompt using:
• User’s input
• Conversation history
• Information about knowledge bases and available APIs
• Instructions provided by the system developer
The Foundation Model choose which action should be taken.
The action’s output is an observation that is used to enrich
the orchestration prompt.
Looping and refinement until the Agent has all the necessary
informations to answer.
TRACING
DETAIL THE STEPS ORCHESTRATED
BY THE AGENT, HELPING TO
FOLLOW THE AGENT’S REASONING
PROCESS
GUARDRAILS
IMPLEMENT SAFEGUARDS FOR
GENERATIVE AI APPLICATIONS
AI AGENTS ON AMAZON BEDROCK
GUARDRAILS & TRACING
ACTION GROUP
IMPLEMENT AN API FOR
RETRIEVING THE QUANTITY
OF AVAILABLE PUPPETS
KNOWLEDGE BASE
CONTAINS DESCRIPTIONS
ABOUT POKEMON PUPPETS
AI AGENTS ON AMAZON BEDROCK
USE-CASE
POKEMON PUPPETS INVENTORY ASSISTANT
ACTION GROUPS
ARE BASED ON
LAMBDA FUNTIONS
KNOWLEDGE BASE
IS HOSTED ON
AMAZON OPENSEARCH
FOUNDATION
MODEL
IS CLAUDE 2.1
AI AGENTS ON AMAZON BEDROCK
USE-CASE
UPDATE THIS PRESENTATION HEADER IN SLIDE MASTER
PROSSIMO APPUNTAMENTO
AWS UG Torino Meetup 2024 #4
CALL FOR SPEAKERS
02/10/2024 – 18.30
Toolbox Coworking
Via Agostino da Montefeltro, 2, Torino
Si possono presentare propri progetti, case study,
best practice e altro.

More Related Content

Similar to AWS User Group Torino 2024 #3 - 18/06/2024

AWS and Symantec: Cyber Defense at Scale (SEC311-S) - AWS re:Invent 2018
AWS and Symantec: Cyber Defense at Scale (SEC311-S) - AWS re:Invent 2018AWS and Symantec: Cyber Defense at Scale (SEC311-S) - AWS re:Invent 2018
AWS and Symantec: Cyber Defense at Scale (SEC311-S) - AWS re:Invent 2018
Amazon Web Services
 
Driving Innovation with Serverless Applications (GPSBUS212) - AWS re:Invent 2018
Driving Innovation with Serverless Applications (GPSBUS212) - AWS re:Invent 2018Driving Innovation with Serverless Applications (GPSBUS212) - AWS re:Invent 2018
Driving Innovation with Serverless Applications (GPSBUS212) - AWS re:Invent 2018
Amazon Web Services
 
Meetup Sécurité - AWS - Recap Reinforce 2019
Meetup Sécurité - AWS - Recap Reinforce 2019Meetup Sécurité - AWS - Recap Reinforce 2019
Meetup Sécurité - AWS - Recap Reinforce 2019
Devoteam Revolve
 
Using ML with Amazon SageMaker & GuardDuty to identify anomalous traffic - SE...
Using ML with Amazon SageMaker & GuardDuty to identify anomalous traffic - SE...Using ML with Amazon SageMaker & GuardDuty to identify anomalous traffic - SE...
Using ML with Amazon SageMaker & GuardDuty to identify anomalous traffic - SE...
Amazon Web Services
 
Aws 101 garage+
Aws 101 garage+Aws 101 garage+
Aws 101 garage+
Bruce Chen
 
AWS reInvent 2023 recaps from Chicago AWS user group
AWS reInvent 2023 recaps from Chicago AWS user groupAWS reInvent 2023 recaps from Chicago AWS user group
AWS reInvent 2023 recaps from Chicago AWS user group
AWS Chicago
 
透過最新的 AWS 服務在 2019 年為您的業務轉型 (Level 200)
透過最新的 AWS 服務在 2019 年為您的業務轉型 (Level 200)透過最新的 AWS 服務在 2019 年為您的業務轉型 (Level 200)
透過最新的 AWS 服務在 2019 年為您的業務轉型 (Level 200)
Amazon Web Services
 
Using Data Science & Serverless Python to find apartment in Toronto
Using Data Science & Serverless Python to find apartment in TorontoUsing Data Science & Serverless Python to find apartment in Toronto
Using Data Science & Serverless Python to find apartment in Toronto
Daniel Zivkovic
 
Continuous Deployment @ AWS Re:Invent
Continuous Deployment @ AWS Re:InventContinuous Deployment @ AWS Re:Invent
Continuous Deployment @ AWS Re:Invent
John Schneider
 
Continuous Integration and Deployment Best Practices on AWS (ARC307) | AWS re...
Continuous Integration and Deployment Best Practices on AWS (ARC307) | AWS re...Continuous Integration and Deployment Best Practices on AWS (ARC307) | AWS re...
Continuous Integration and Deployment Best Practices on AWS (ARC307) | AWS re...
Amazon Web Services
 
[AWS Dev Day] 앱 현대화 | DevOps 개발자가 되기 위한 쿠버네티스 핵심 활용 예제 알아보기 - 정영준 AWS 솔루션즈 아키...
[AWS Dev Day] 앱 현대화 | DevOps 개발자가 되기 위한 쿠버네티스 핵심 활용 예제 알아보기 - 정영준 AWS 솔루션즈 아키...[AWS Dev Day] 앱 현대화 | DevOps 개발자가 되기 위한 쿠버네티스 핵심 활용 예제 알아보기 - 정영준 AWS 솔루션즈 아키...
[AWS Dev Day] 앱 현대화 | DevOps 개발자가 되기 위한 쿠버네티스 핵심 활용 예제 알아보기 - 정영준 AWS 솔루션즈 아키...
Amazon Web Services Korea
 
Re-Invent 23 recap @ AWS UserGroup meetup
Re-Invent 23 recap @ AWS UserGroup meetupRe-Invent 23 recap @ AWS UserGroup meetup
Re-Invent 23 recap @ AWS UserGroup meetup
AbhiniveshJain1
 
DevSecOps 的規模化實踐 (Level: 300-400)
DevSecOps 的規模化實踐 (Level: 300-400)DevSecOps 的規模化實踐 (Level: 300-400)
DevSecOps 的規模化實踐 (Level: 300-400)
Amazon Web Services
 
Threat Detection and Remediation Workshop
Threat Detection and Remediation WorkshopThreat Detection and Remediation Workshop
Threat Detection and Remediation Workshop
Amazon Web Services
 
Fraud Detection with Amazon SageMaker
Fraud Detection with Amazon SageMakerFraud Detection with Amazon SageMaker
Fraud Detection with Amazon SageMaker
Amazon Web Services
 
AWS ReInvent 2023 Recap: AWS User GroupKolkata
AWS ReInvent 2023 Recap: AWS User GroupKolkataAWS ReInvent 2023 Recap: AWS User GroupKolkata
AWS ReInvent 2023 Recap: AWS User GroupKolkata
Aritra Nag
 
AWS reInvent 2023 re:Cap services Slide deck
AWS reInvent 2023 re:Cap services Slide deckAWS reInvent 2023 re:Cap services Slide deck
AWS reInvent 2023 re:Cap services Slide deck
Sammy Cheung
 
Getting started with streaming analytics: Deep Dive
Getting started with streaming analytics: Deep DiveGetting started with streaming analytics: Deep Dive
Getting started with streaming analytics: Deep Dive
javier ramirez
 
Amazon SageMaker Deep Dive - Meetup AWS Toulouse at D2SI
Amazon SageMaker Deep Dive - Meetup AWS Toulouse at D2SIAmazon SageMaker Deep Dive - Meetup AWS Toulouse at D2SI
Amazon SageMaker Deep Dive - Meetup AWS Toulouse at D2SI
Amazon Web Services
 
IaC: Tools of the trade
IaC: Tools of the tradeIaC: Tools of the trade
IaC: Tools of the trade
Michael Pearce
 

Similar to AWS User Group Torino 2024 #3 - 18/06/2024 (20)

AWS and Symantec: Cyber Defense at Scale (SEC311-S) - AWS re:Invent 2018
AWS and Symantec: Cyber Defense at Scale (SEC311-S) - AWS re:Invent 2018AWS and Symantec: Cyber Defense at Scale (SEC311-S) - AWS re:Invent 2018
AWS and Symantec: Cyber Defense at Scale (SEC311-S) - AWS re:Invent 2018
 
Driving Innovation with Serverless Applications (GPSBUS212) - AWS re:Invent 2018
Driving Innovation with Serverless Applications (GPSBUS212) - AWS re:Invent 2018Driving Innovation with Serverless Applications (GPSBUS212) - AWS re:Invent 2018
Driving Innovation with Serverless Applications (GPSBUS212) - AWS re:Invent 2018
 
Meetup Sécurité - AWS - Recap Reinforce 2019
Meetup Sécurité - AWS - Recap Reinforce 2019Meetup Sécurité - AWS - Recap Reinforce 2019
Meetup Sécurité - AWS - Recap Reinforce 2019
 
Using ML with Amazon SageMaker & GuardDuty to identify anomalous traffic - SE...
Using ML with Amazon SageMaker & GuardDuty to identify anomalous traffic - SE...Using ML with Amazon SageMaker & GuardDuty to identify anomalous traffic - SE...
Using ML with Amazon SageMaker & GuardDuty to identify anomalous traffic - SE...
 
Aws 101 garage+
Aws 101 garage+Aws 101 garage+
Aws 101 garage+
 
AWS reInvent 2023 recaps from Chicago AWS user group
AWS reInvent 2023 recaps from Chicago AWS user groupAWS reInvent 2023 recaps from Chicago AWS user group
AWS reInvent 2023 recaps from Chicago AWS user group
 
透過最新的 AWS 服務在 2019 年為您的業務轉型 (Level 200)
透過最新的 AWS 服務在 2019 年為您的業務轉型 (Level 200)透過最新的 AWS 服務在 2019 年為您的業務轉型 (Level 200)
透過最新的 AWS 服務在 2019 年為您的業務轉型 (Level 200)
 
Using Data Science & Serverless Python to find apartment in Toronto
Using Data Science & Serverless Python to find apartment in TorontoUsing Data Science & Serverless Python to find apartment in Toronto
Using Data Science & Serverless Python to find apartment in Toronto
 
Continuous Deployment @ AWS Re:Invent
Continuous Deployment @ AWS Re:InventContinuous Deployment @ AWS Re:Invent
Continuous Deployment @ AWS Re:Invent
 
Continuous Integration and Deployment Best Practices on AWS (ARC307) | AWS re...
Continuous Integration and Deployment Best Practices on AWS (ARC307) | AWS re...Continuous Integration and Deployment Best Practices on AWS (ARC307) | AWS re...
Continuous Integration and Deployment Best Practices on AWS (ARC307) | AWS re...
 
[AWS Dev Day] 앱 현대화 | DevOps 개발자가 되기 위한 쿠버네티스 핵심 활용 예제 알아보기 - 정영준 AWS 솔루션즈 아키...
[AWS Dev Day] 앱 현대화 | DevOps 개발자가 되기 위한 쿠버네티스 핵심 활용 예제 알아보기 - 정영준 AWS 솔루션즈 아키...[AWS Dev Day] 앱 현대화 | DevOps 개발자가 되기 위한 쿠버네티스 핵심 활용 예제 알아보기 - 정영준 AWS 솔루션즈 아키...
[AWS Dev Day] 앱 현대화 | DevOps 개발자가 되기 위한 쿠버네티스 핵심 활용 예제 알아보기 - 정영준 AWS 솔루션즈 아키...
 
Re-Invent 23 recap @ AWS UserGroup meetup
Re-Invent 23 recap @ AWS UserGroup meetupRe-Invent 23 recap @ AWS UserGroup meetup
Re-Invent 23 recap @ AWS UserGroup meetup
 
DevSecOps 的規模化實踐 (Level: 300-400)
DevSecOps 的規模化實踐 (Level: 300-400)DevSecOps 的規模化實踐 (Level: 300-400)
DevSecOps 的規模化實踐 (Level: 300-400)
 
Threat Detection and Remediation Workshop
Threat Detection and Remediation WorkshopThreat Detection and Remediation Workshop
Threat Detection and Remediation Workshop
 
Fraud Detection with Amazon SageMaker
Fraud Detection with Amazon SageMakerFraud Detection with Amazon SageMaker
Fraud Detection with Amazon SageMaker
 
AWS ReInvent 2023 Recap: AWS User GroupKolkata
AWS ReInvent 2023 Recap: AWS User GroupKolkataAWS ReInvent 2023 Recap: AWS User GroupKolkata
AWS ReInvent 2023 Recap: AWS User GroupKolkata
 
AWS reInvent 2023 re:Cap services Slide deck
AWS reInvent 2023 re:Cap services Slide deckAWS reInvent 2023 re:Cap services Slide deck
AWS reInvent 2023 re:Cap services Slide deck
 
Getting started with streaming analytics: Deep Dive
Getting started with streaming analytics: Deep DiveGetting started with streaming analytics: Deep Dive
Getting started with streaming analytics: Deep Dive
 
Amazon SageMaker Deep Dive - Meetup AWS Toulouse at D2SI
Amazon SageMaker Deep Dive - Meetup AWS Toulouse at D2SIAmazon SageMaker Deep Dive - Meetup AWS Toulouse at D2SI
Amazon SageMaker Deep Dive - Meetup AWS Toulouse at D2SI
 
IaC: Tools of the trade
IaC: Tools of the tradeIaC: Tools of the trade
IaC: Tools of the trade
 

Recently uploaded

stackconf 2024 | Generative AI Security — A Practical Guide to Securing Your ...
stackconf 2024 | Generative AI Security — A Practical Guide to Securing Your ...stackconf 2024 | Generative AI Security — A Practical Guide to Securing Your ...
stackconf 2024 | Generative AI Security — A Practical Guide to Securing Your ...
NETWAYS
 
Lucknow Girls Call Fazullaganj 08630512678 Provide Best And Top Girl Service ...
Lucknow Girls Call Fazullaganj 08630512678 Provide Best And Top Girl Service ...Lucknow Girls Call Fazullaganj 08630512678 Provide Best And Top Girl Service ...
Lucknow Girls Call Fazullaganj 08630512678 Provide Best And Top Girl Service ...
bangaloreakshitakaus
 
MINI PROJECT REPORT about the multidiseases.pdf
MINI PROJECT REPORT about the multidiseases.pdfMINI PROJECT REPORT about the multidiseases.pdf
MINI PROJECT REPORT about the multidiseases.pdf
BECHAADITYA
 
UMiami biyezheng degree offer diploma Transcript
UMiami biyezheng degree offer diploma TranscriptUMiami biyezheng degree offer diploma Transcript
UMiami biyezheng degree offer diploma Transcript
xmevus
 
Call India - AmanTel on the App Store.ppt
Call India - AmanTel on the App Store.pptCall India - AmanTel on the App Store.ppt
Call India - AmanTel on the App Store.ppt
Best International calling app on the market
 
Cornell biyezheng degree offer diploma Transcript
Cornell biyezheng degree offer diploma TranscriptCornell biyezheng degree offer diploma Transcript
Cornell biyezheng degree offer diploma Transcript
xmevus
 
Risks & Business Risks Reduce - investment.pdf
Risks & Business Risks Reduce  - investment.pdfRisks & Business Risks Reduce  - investment.pdf
Risks & Business Risks Reduce - investment.pdf
Home
 
Biography of the late Mrs. Stella Atsupui Eddah.pdf
Biography of the late Mrs. Stella Atsupui Eddah.pdfBiography of the late Mrs. Stella Atsupui Eddah.pdf
Biography of the late Mrs. Stella Atsupui Eddah.pdf
AbdulSadickZutah
 
VIP Shimla Girls Call Shimla 0X0000000X Doorstep High-Profile Girl Service Ca...
VIP Shimla Girls Call Shimla 0X0000000X Doorstep High-Profile Girl Service Ca...VIP Shimla Girls Call Shimla 0X0000000X Doorstep High-Profile Girl Service Ca...
VIP Shimla Girls Call Shimla 0X0000000X Doorstep High-Profile Girl Service Ca...
sukaniyasunnu
 
Communication Skills F.pptx for corporate employee
Communication Skills F.pptx for corporate employeeCommunication Skills F.pptx for corporate employee
Communication Skills F.pptx for corporate employee
artemacademy2
 
calcaneal fracture seminar by dr vishu.pptx
calcaneal fracture seminar by dr vishu.pptxcalcaneal fracture seminar by dr vishu.pptx
calcaneal fracture seminar by dr vishu.pptx
Skmch
 
Girls Call Bandra East 9910780858 Provide Best And Top Girl Service And No1 i...
Girls Call Bandra East 9910780858 Provide Best And Top Girl Service And No1 i...Girls Call Bandra East 9910780858 Provide Best And Top Girl Service And No1 i...
Girls Call Bandra East 9910780858 Provide Best And Top Girl Service And No1 i...
margaretblush
 
Hyderabad Girls Call Hyderabad 0X0000000X Unlimited Short Providing Girls Ser...
Hyderabad Girls Call Hyderabad 0X0000000X Unlimited Short Providing Girls Ser...Hyderabad Girls Call Hyderabad 0X0000000X Unlimited Short Providing Girls Ser...
Hyderabad Girls Call Hyderabad 0X0000000X Unlimited Short Providing Girls Ser...
rashmikasinghdelhiro
 
Dehradun Girls Call Dehradun 0X0000000X Unlimited Short Providing Girls Servi...
Dehradun Girls Call Dehradun 0X0000000X Unlimited Short Providing Girls Servi...Dehradun Girls Call Dehradun 0X0000000X Unlimited Short Providing Girls Servi...
Dehradun Girls Call Dehradun 0X0000000X Unlimited Short Providing Girls Servi...
sankisogandhi
 
VIP Nashik Girls Call Nashik 0X0000000X Doorstep High-Profile Girl Service Ca...
VIP Nashik Girls Call Nashik 0X0000000X Doorstep High-Profile Girl Service Ca...VIP Nashik Girls Call Nashik 0X0000000X Doorstep High-Profile Girl Service Ca...
VIP Nashik Girls Call Nashik 0X0000000X Doorstep High-Profile Girl Service Ca...
saroohilakhatariroy
 
Lucknow Girls Call Aliganj 08630512678 Provide Best And Top Girl Service And ...
Lucknow Girls Call Aliganj 08630512678 Provide Best And Top Girl Service And ...Lucknow Girls Call Aliganj 08630512678 Provide Best And Top Girl Service And ...
Lucknow Girls Call Aliganj 08630512678 Provide Best And Top Girl Service And ...
arnavkumar9870
 
Varanasi Girls Call Varanasi 0X0000000X Payment On Delevery Cash Hot Premium ...
Varanasi Girls Call Varanasi 0X0000000X Payment On Delevery Cash Hot Premium ...Varanasi Girls Call Varanasi 0X0000000X Payment On Delevery Cash Hot Premium ...
Varanasi Girls Call Varanasi 0X0000000X Payment On Delevery Cash Hot Premium ...
parichopra4
 
Marketing Articles and ppt on how to do marketing ..Challenges faced during M...
Marketing Articles and ppt on how to do marketing ..Challenges faced during M...Marketing Articles and ppt on how to do marketing ..Challenges faced during M...
Marketing Articles and ppt on how to do marketing ..Challenges faced during M...
ankitamarik05
 
2024-07-07 Transformed 06 (shared slides).pptx
2024-07-07 Transformed 06 (shared slides).pptx2024-07-07 Transformed 06 (shared slides).pptx
2024-07-07 Transformed 06 (shared slides).pptx
Dale Wells
 
Lucknow @Girls @ℂall Gomti Nagar 08630512678 @Girls @ℂall Service
Lucknow @Girls @ℂall  Gomti Nagar 08630512678  @Girls @ℂall ServiceLucknow @Girls @ℂall  Gomti Nagar 08630512678  @Girls @ℂall Service
Lucknow @Girls @ℂall Gomti Nagar 08630512678 @Girls @ℂall Service
veenita788
 

Recently uploaded (20)

stackconf 2024 | Generative AI Security — A Practical Guide to Securing Your ...
stackconf 2024 | Generative AI Security — A Practical Guide to Securing Your ...stackconf 2024 | Generative AI Security — A Practical Guide to Securing Your ...
stackconf 2024 | Generative AI Security — A Practical Guide to Securing Your ...
 
Lucknow Girls Call Fazullaganj 08630512678 Provide Best And Top Girl Service ...
Lucknow Girls Call Fazullaganj 08630512678 Provide Best And Top Girl Service ...Lucknow Girls Call Fazullaganj 08630512678 Provide Best And Top Girl Service ...
Lucknow Girls Call Fazullaganj 08630512678 Provide Best And Top Girl Service ...
 
MINI PROJECT REPORT about the multidiseases.pdf
MINI PROJECT REPORT about the multidiseases.pdfMINI PROJECT REPORT about the multidiseases.pdf
MINI PROJECT REPORT about the multidiseases.pdf
 
UMiami biyezheng degree offer diploma Transcript
UMiami biyezheng degree offer diploma TranscriptUMiami biyezheng degree offer diploma Transcript
UMiami biyezheng degree offer diploma Transcript
 
Call India - AmanTel on the App Store.ppt
Call India - AmanTel on the App Store.pptCall India - AmanTel on the App Store.ppt
Call India - AmanTel on the App Store.ppt
 
Cornell biyezheng degree offer diploma Transcript
Cornell biyezheng degree offer diploma TranscriptCornell biyezheng degree offer diploma Transcript
Cornell biyezheng degree offer diploma Transcript
 
Risks & Business Risks Reduce - investment.pdf
Risks & Business Risks Reduce  - investment.pdfRisks & Business Risks Reduce  - investment.pdf
Risks & Business Risks Reduce - investment.pdf
 
Biography of the late Mrs. Stella Atsupui Eddah.pdf
Biography of the late Mrs. Stella Atsupui Eddah.pdfBiography of the late Mrs. Stella Atsupui Eddah.pdf
Biography of the late Mrs. Stella Atsupui Eddah.pdf
 
VIP Shimla Girls Call Shimla 0X0000000X Doorstep High-Profile Girl Service Ca...
VIP Shimla Girls Call Shimla 0X0000000X Doorstep High-Profile Girl Service Ca...VIP Shimla Girls Call Shimla 0X0000000X Doorstep High-Profile Girl Service Ca...
VIP Shimla Girls Call Shimla 0X0000000X Doorstep High-Profile Girl Service Ca...
 
Communication Skills F.pptx for corporate employee
Communication Skills F.pptx for corporate employeeCommunication Skills F.pptx for corporate employee
Communication Skills F.pptx for corporate employee
 
calcaneal fracture seminar by dr vishu.pptx
calcaneal fracture seminar by dr vishu.pptxcalcaneal fracture seminar by dr vishu.pptx
calcaneal fracture seminar by dr vishu.pptx
 
Girls Call Bandra East 9910780858 Provide Best And Top Girl Service And No1 i...
Girls Call Bandra East 9910780858 Provide Best And Top Girl Service And No1 i...Girls Call Bandra East 9910780858 Provide Best And Top Girl Service And No1 i...
Girls Call Bandra East 9910780858 Provide Best And Top Girl Service And No1 i...
 
Hyderabad Girls Call Hyderabad 0X0000000X Unlimited Short Providing Girls Ser...
Hyderabad Girls Call Hyderabad 0X0000000X Unlimited Short Providing Girls Ser...Hyderabad Girls Call Hyderabad 0X0000000X Unlimited Short Providing Girls Ser...
Hyderabad Girls Call Hyderabad 0X0000000X Unlimited Short Providing Girls Ser...
 
Dehradun Girls Call Dehradun 0X0000000X Unlimited Short Providing Girls Servi...
Dehradun Girls Call Dehradun 0X0000000X Unlimited Short Providing Girls Servi...Dehradun Girls Call Dehradun 0X0000000X Unlimited Short Providing Girls Servi...
Dehradun Girls Call Dehradun 0X0000000X Unlimited Short Providing Girls Servi...
 
VIP Nashik Girls Call Nashik 0X0000000X Doorstep High-Profile Girl Service Ca...
VIP Nashik Girls Call Nashik 0X0000000X Doorstep High-Profile Girl Service Ca...VIP Nashik Girls Call Nashik 0X0000000X Doorstep High-Profile Girl Service Ca...
VIP Nashik Girls Call Nashik 0X0000000X Doorstep High-Profile Girl Service Ca...
 
Lucknow Girls Call Aliganj 08630512678 Provide Best And Top Girl Service And ...
Lucknow Girls Call Aliganj 08630512678 Provide Best And Top Girl Service And ...Lucknow Girls Call Aliganj 08630512678 Provide Best And Top Girl Service And ...
Lucknow Girls Call Aliganj 08630512678 Provide Best And Top Girl Service And ...
 
Varanasi Girls Call Varanasi 0X0000000X Payment On Delevery Cash Hot Premium ...
Varanasi Girls Call Varanasi 0X0000000X Payment On Delevery Cash Hot Premium ...Varanasi Girls Call Varanasi 0X0000000X Payment On Delevery Cash Hot Premium ...
Varanasi Girls Call Varanasi 0X0000000X Payment On Delevery Cash Hot Premium ...
 
Marketing Articles and ppt on how to do marketing ..Challenges faced during M...
Marketing Articles and ppt on how to do marketing ..Challenges faced during M...Marketing Articles and ppt on how to do marketing ..Challenges faced during M...
Marketing Articles and ppt on how to do marketing ..Challenges faced during M...
 
2024-07-07 Transformed 06 (shared slides).pptx
2024-07-07 Transformed 06 (shared slides).pptx2024-07-07 Transformed 06 (shared slides).pptx
2024-07-07 Transformed 06 (shared slides).pptx
 
Lucknow @Girls @ℂall Gomti Nagar 08630512678 @Girls @ℂall Service
Lucknow @Girls @ℂall  Gomti Nagar 08630512678  @Girls @ℂall ServiceLucknow @Girls @ℂall  Gomti Nagar 08630512678  @Girls @ℂall Service
Lucknow @Girls @ℂall Gomti Nagar 08630512678 @Girls @ℂall Service
 

AWS User Group Torino 2024 #3 - 18/06/2024

  • 1. UPDATE THIS PRESENTATION HEADER IN SLIDE MASTER AWS UG Torino Meetup 2024 #3 1 8 / 06 / 2 0 2 4
  • 2. UPDATE THIS PRESENTATION HEADER IN SLIDE MASTER AWS USER GROUP TORINO ENTRA NEL GRUPPO WHATSAPP!
  • 3. UPDATE THIS PRESENTATION HEADER IN SLIDE MASTER © 2024, Amazon Web Services, Inc. or its affiliates. Allrights reserved. Amazon Confidential and Trademark. Calendario 2024: AWS UG TORINO MEETUP: • 19/02/2024 ✓ • 16/04/2024 ✓ • 18/06/2024 oggi • 02/10/2024 • 19/11/2024
  • 4. UPDATE THIS PRESENTATION HEADER IN SLIDE MASTER Rinfresco & Networking Agenda di oggi AWS UG Torino Meetup 2024 #3 Carlo Peluso AI Agents on AWS: Deep- dive on Amazon Bedrock Agents Davide De Sio Serverless e DevOps per migliorare la DevXP
  • 5. UPDATE THIS PRESENTATION HEADER IN SLIDE MASTER © 2024, Amazon Web Services, Inc. or its affiliates. Allrights reserved. Amazon Confidential and Trademark. Davide De Sio Serverless e DevOps per migliorare la DevXP AW S UG TO R IN O M E E TU P 2 0 2 4 # 3
  • 6. Superpower REST API DX with Serverless and DevOps Best Practices on AWS Come ridurre la complessità dell’infrastruttura con AWS e migliorare la DevExperience attraverso pratiche DevOps Elev a Srl
  • 7. Chi Sono Davide De Sio Development Tech Lead @Eleva AWS Solutions Architect (Professional) Senior Full Stack Developer “The essence of the serverless trend is the absence of the server concept during software development.” Tomasz Janczuk, VP at Auth0 Serverless Enthusiast AWS UG Lead - Pavia
  • 9. Use Case 2 Single Page Application
  • 10. Perché Serverless? Cosa mi aspetto? Voglio che l’architettura scali in automatico (auto-scaling) Voglio che gli sviluppatori si concentrino nello scrivere la business logic Non voglio pagare quando non utilizzo risorse (idle) Voglio che il team di sviluppo si concentri su quello che conta davvero, potendo far affidamento su una piattaforma di sviluppo che massimizzi la Developer Experience e la renda semplice, piacevole, ripetibile e manutenibile.
  • 12. Infrastructure as code Infrastruttura dichiarata come codice Documentation as code Documentazione dichiarata come codice Automated Testing Test automatici basati sulla documentazione CI/CD Pipelines di distribuzione automatizzate DR Procedure di Disaster Recovery Versioning Versionamento del singolo micro-servizio API Architecture Pratiche DevOps Security By Design Best practices di sicurezza Monitoring Monitoraggio continuo
  • 13. Provisioning (senza overhead) Esposizione tramite Amazon API Gateway, Amazon Cloudfront e Amazon Route 53 Esecuzione su funzioni serverless tramite AWS Lambda CI/CD Release tramite strumenti di infrastracture as code (AWS Cloudformation/SAM/CDK/Serverless Framework) Esecuzione del rilascio e dei test su pipeline per CI/CD (AWS Codepipeline e AWS Codebuild) a partire da commit su branch finalizzati al versionamento e al rilascio di repo Git API Architecture Key points
  • 14. API Architecture Key points Doc first / Doc generation Documentazione come codice secondo standard Open API V3 (via Serverless Framework) Generazione della documentazione su pagine statiche (via Redocly) storicizzate su Amazon S3 e integrazione nella pipeline di distribuzione Automated Testing Implementazione di test che validano le API in base alle specifiche Open API V3 generate Security first e monitoring Messa in sicurezza con Managed Services AWS IAM / VPC / WAF / Guard Duty Monitoraggio tramite AWS X-Ray e Cloudwatch (dashboard e allarmi)
  • 15. Show me the (infra) code! CloudFormation per estensioni (security - cognito) Documentazione integrata (doc-as-code) Serverless files Infrastructure as Code Plugin per monitoraggio (slic-watch) Plugin per local environment (serverless-offline) CloudFormation per architettura a supporto e CI/CD come codice (buildspec) su CodePipeline e CodeBuild
  • 16. Talk is cheap Show me the code
  • 18. Textract: Example Use Case EU-Driving Licences OCR
  • 21. Bonus «Non tutte le ciambelle vengono col buco» https://www.primevideotech.com/video-streaming/scaling-up-the-prime-video-audio-video-monitoring- service-and-reducing-costs-by-90
  • 22. Bonus «Don't get locked up into avoiding lock-in» https://martinfowler.com/articles/oss-lockin.html • Vendor Lock-In • Product Lock-in • Version lock-in • Architecture lock-in • Platform lock-in • Skills lock-in • Legal lock-in • Mental Lock-in
  • 23. UPDATE THIS PRESENTATION HEADER IN SLIDE MASTER © 2024, Amazon Web Services, Inc. or its affiliates. Allrights reserved. Amazon Confidential and Trademark. Carlo Peluso AI Agents on AWS: Deep- dive on Amazon Bedrock Agents AW S UG TO R IN O M E E TU P 2 0 24 # 3
  • 24. AI AGENTS ON AMAZON BEDROCK Carlo Peluso | Solutions Architect @ Storm Reply
  • 25. INTRODUCTION ABOUT ME 2018 – Started working as Backend Engineer 2020 – Bachelor’s Degree in Computer Science Engineering 2022 – Master’s Degree in Data Science and Engineering 2022 – Started working as Solutions Architect @ Storm Reply 2022 – Q1 Publication on Transformers for Healthcare
  • 26. INTRODUCTION TODAY’S TOPIC: AI AGENTS WHAT are AI agents? WHY AI agents are useful? HOW AI agents can be implemented?
  • 27. ARTIFICIAL INTELLIGENCE FROM SHALLOW ARCHITECTURES TO LARGE LANGUAGE MODELS Increasing number of hidden layers… NEURAL NETWORKS & CNNs AlexNet, ResNet, … TRANSFORMERS & LLMs BERT, Claude, Mistral, GPT-3, … SHALLOW ARCHITECTURES Support Vector Machines, Decision Trees, …
  • 28. DEEP NEURAL NETWORKS TRAINING COMPLEXITIES HIGH NUMBER OF HIDDEN LAYERS LOTS OF DATA AND HIGHLY PERFORMANT COMPUTATIONAL RESOURCES BILLIONS OF TRAINING PARAMETERS IMPLY REQUIRE
  • 29. CAN WE EXPLOIT PRE-TRAINED AI MODELS FOR DATA SPECIFIC FROM OUR DOMAIN?
  • 30. EXPLOIT PRE-TRAINED AI MODELS FINETUNING PRE-TRAINED MODELS CAN BE FINETUNED (i.e., SMOOTHLY RETRAINED) ON DATA FROM AN UNKNOWN DOMAIN
  • 31. STILL… WITH GENERATIVE AI MODELS WE CAN USE A MORE STRAIGHTFORWARD APPROACH!
  • 32. EXPLOIT PRE-TRAINED AI MODELS IN-CONTEXT LEARNING COLLECT UNKNOWN DOMAIN DATA WITHIN A KNOWLEDGE BASE INPUT CONTEXT INFORMATION FROM THE KNOWLEDGE BASE TO THE GENERATIVE AI MODEL
  • 33. EXPLOIT PRE-TRAINED AI MODELS IN-CONTEXT LEARNING THE GENERATIVE AI MODEL CAN COMPENSATE THE MISSING DOMAIN KNOWLEDGE BY EXPLOITING IN-CONTEXT INFORMATION
  • 34. Qual è la capitale della Grecia? IN-CONTEXT LEARNING EXAMPLE La capitale della Francia è Parigi. La capitale dell’Italia è Roma. La capitale della Spagna è Madrid. La capitale della Grecia è Atene. La capitale della Grecia è Atene. Semantic search Provide in-context information to the LLM 1 2 3 4 1 2 3 4 The user asks a question. The question is used to retrieve from the knowledge base the documents semantically closer to the question. The documents retrieved are fed to the LLM, alongside the original question and a system prompt (that describes how the LLM should respond). The LLM, based on the context provided and the system prompt, answers the question.
  • 35. SEAMLESSLY BUILD AND MAINTAIN VECTOR DATABASES USING DOCUMENTS FROM YOUR DOMAIN EASILY INTEGRATE LEADING LLMs, DELEGATING INFRASTRUCTURE MANAGEMENT GENERATIVE AI ON AWS AMAZON BEDROCK FOUNDATION MODELS KNOWLEDGE BASES
  • 36. AMAZON BEDROCK KNOWLEDGE BASES AMAZON BEDROCK KNOWLEDGE BASES Textual documents, PDFs, CSVs, JSON, … AMAZON S3 AMAZON RDS AMAZON OPENSEARCH Text to vector representations
  • 37. IN-CONTEXT LEARNING EXAMPLE USING AMAZON BEDROCK La capitale della Francia è Parigi. La capitale dell’Italia è Roma. La capitale della Spagna è Madrid. La capitale della Grecia è Atene. AMAZON BEDROCK KNOWLEDGE BASES AMAZON BEDROCK FOUNDATION MODELS Qual è la capitale della Grecia? 1 1 The user asks a question.
  • 38. IN-CONTEXT LEARNING EXAMPLE USING AMAZON BEDROCK La capitale della Francia è Parigi. La capitale dell’Italia è Roma. La capitale della Spagna è Madrid. La capitale della Grecia è Atene. AMAZON BEDROCK KNOWLEDGE BASES AMAZON BEDROCK FOUNDATION MODELS Qual è la capitale della Grecia? API call: knowledgeBase.retrieve(question) 1 2 1 2 The user asks a question. The question is used to retrieve from the knowledge base the documents semantically closer to the question.
  • 39. IN-CONTEXT LEARNING EXAMPLE USING AMAZON BEDROCK La capitale della Francia è Parigi. La capitale dell’Italia è Roma. La capitale della Spagna è Madrid. La capitale della Grecia è Atene. AMAZON BEDROCK KNOWLEDGE BASES AMAZON BEDROCK FOUNDATION MODELS Qual è la capitale della Grecia? API call: knowledgeBase.retrieve(question) API call: bedrock.invoke_model(context) 1 2 3 1 2 3 The user asks a question. The question is used to retrieve from the knowledge base the documents semantically closer to the question. The documents retrieved are fed to the LLM, alongside the original question and a system prompt (that describes how the LLM should respond).
  • 40. IN-CONTEXT LEARNING EXAMPLE USING AMAZON BEDROCK La capitale della Francia è Parigi. La capitale dell’Italia è Roma. La capitale della Spagna è Madrid. La capitale della Grecia è Atene. AMAZON BEDROCK KNOWLEDGE BASES AMAZON BEDROCK FOUNDATION MODELS Qual è la capitale della Grecia? La capitale della Grecia è Atene. API call: knowledgeBase.retrieve(question) API call: bedrock.invoke_model(context) 1 2 3 4 1 2 3 4 The user asks a question. The question is used to retrieve from the knowledge base the documents semantically closer to the question. The documents retrieved are fed to the LLM, alongside the original question and a system prompt (that describes how the LLM should respond). The LLM, based on the context provided and the system prompt, answers the question.
  • 41. STILL, RETRIEVE AND GENERATE APPLICATIONS ARE SOMEHOW “STATIC”
  • 42. FOUNDATION MODELS ORCHESTRATE TASKS BY EXPLOTING A KNOWLEDGE BASE AND DYNAMICALLY INVOKING APIs AI AGENTS AI AGENTS ON AMAZON BEDROCK
  • 43. ACTION GROUPS DEFINE ACTIONS THAT THE AGENT CAN PERFORM AI AGENTS ON AMAZON BEDROCK ACTION GROUPS
  • 44. LAMBDA FUNCTIONS DEFINE HOW THE AGENT HANDLES THE PARAMETERS IT RECEIVES OPENAPI SCHEMAS DEFINE THE PARAMETERS THE AGENT MUST EXTRACT FOR THE ACTION TO BE EXECUTED AI AGENTS ON AMAZON BEDROCK ACTION GROUPS
  • 45. AI AGENTS WORKFLOW AI AGENT IS INPUT VALID? PREPROCESSING PROMPT 1 1 The agent verifies that the user input is not malicious.
  • 46. AI AGENTS WORKFLOW AI AGENT IS INPUT VALID? SEARCH WITHIN THE KNOWLEDGE BASE CALL AN API ORCHESTRATION PROMPT WHICH ACTION SHOULD I TAKE? PREPROCESSING PROMPT 1 2 1 2 The agent verifies that the user input is not malicious. The agent creates an orchestration prompt using: • User’s input • Conversation history • Information about knowledge bases and available APIs • Instructions provided by the system developer
  • 47. AI AGENTS WORKFLOW AI AGENT IS INPUT VALID? PERFORM ACTION SEARCH WITHIN THE KNOWLEDGE BASE CALL AN API RESPONSE ORCHESTRATION PROMPT WHICH ACTION SHOULD I TAKE? PREPROCESSING PROMPT 1 2 3 1 2 3 The agent verifies that the user input is not malicious. The agent creates an orchestration prompt using: • User’s input • Conversation history • Information about knowledge bases and available APIs • Instructions provided by the system developer The Foundation Model choose which action should be taken.
  • 48. AI AGENTS WORKFLOW AI AGENT IS INPUT VALID? PERFORM ACTION SEARCH WITHIN THE KNOWLEDGE BASE CALL AN API RESPONSE ORCHESTRATION PROMPT WHICH ACTION SHOULD I TAKE? OBSERVATION PREPROCESSING PROMPT 1 2 3 4 1 2 3 4 The agent verifies that the user input is not malicious. The agent creates an orchestration prompt using: • User’s input • Conversation history • Information about knowledge bases and available APIs • Instructions provided by the system developer The Foundation Model choose which action should be taken. The action’s output is an observation that is used to enrich the orchestration prompt.
  • 49. AI AGENTS WORKFLOW AI AGENT IS INPUT VALID? PERFORM ACTION SEARCH WITHIN THE KNOWLEDGE BASE CALL AN API RESPONSE ORCHESTRATION PROMPT WHICH ACTION SHOULD I TAKE? OBSERVATION PREPROCESSING PROMPT 1 2 3 4 5 1 2 3 4 5 The agent verifies that the user input is not malicious. The agent creates an orchestration prompt using: • User’s input • Conversation history • Information about knowledge bases and available APIs • Instructions provided by the system developer The Foundation Model choose which action should be taken. The action’s output is an observation that is used to enrich the orchestration prompt. Looping and refinement until the Agent has all the necessary informations to answer.
  • 50. TRACING DETAIL THE STEPS ORCHESTRATED BY THE AGENT, HELPING TO FOLLOW THE AGENT’S REASONING PROCESS GUARDRAILS IMPLEMENT SAFEGUARDS FOR GENERATIVE AI APPLICATIONS AI AGENTS ON AMAZON BEDROCK GUARDRAILS & TRACING
  • 51. ACTION GROUP IMPLEMENT AN API FOR RETRIEVING THE QUANTITY OF AVAILABLE PUPPETS KNOWLEDGE BASE CONTAINS DESCRIPTIONS ABOUT POKEMON PUPPETS AI AGENTS ON AMAZON BEDROCK USE-CASE POKEMON PUPPETS INVENTORY ASSISTANT
  • 52. ACTION GROUPS ARE BASED ON LAMBDA FUNTIONS KNOWLEDGE BASE IS HOSTED ON AMAZON OPENSEARCH FOUNDATION MODEL IS CLAUDE 2.1 AI AGENTS ON AMAZON BEDROCK USE-CASE
  • 53. UPDATE THIS PRESENTATION HEADER IN SLIDE MASTER PROSSIMO APPUNTAMENTO AWS UG Torino Meetup 2024 #4 CALL FOR SPEAKERS 02/10/2024 – 18.30 Toolbox Coworking Via Agostino da Montefeltro, 2, Torino Si possono presentare propri progetti, case study, best practice e altro.