SlideShare une entreprise Scribd logo
1  sur  9
AZURE OPEN AI
REAL USE CASE
MACHINE LEARNING PLATFORM ARCHITECTURE
Models: AKS
Batch predictions: SQL DB
Analytics
Power BI
Synapse
Business Apps
Responsible ML tools
Seamless studio experience
Notebooks Designer
Comprehensive MLOps
Unified management across clouds and on-premises
Serverless
Compute
Managed
Kubernetes
Azure Edge & Hybrid
Azure Arc-enabled
Kubernetes
Edge/IoT Devices
Reproducibility Automation Deployment Re-training
Security and Governance
Automated ML
Azure ML
Structured Data
Unstructured Data
All other ML scenarios;
NLP, Vision, IoT, etc.
Open
Datasets
Prepare Data Build & Train Manage & Monitor
Deploy
Data
Bricks
Generative AI
Prompt:
Write a tagline for an ice cream shop.
Response:
We serve up smiles with every scoop!
Prompt:
Table customers, columns = [CustomerId,
FirstName, LastName, Company, Address,
City, State, Country, PostalCode]
Create a SQL query for all customers in
Texas named Jane
query =
Response:
SELECT *
FROM customers
WHERE State = 'TX' AND FirstName =
'Jane'
Prompt: A white Siamese cat
Response:
GPT-3 Codex DALL·E
Inferencing
timeCost
Capability
Ada
• Simple classification
• Parsing and formatting text
Curie
• Answering questions
• Complex, nuanced classification
Davinci
• Summarizing for
specific audience
• Generating creative content
Babbage
• Semantic search ranking
• Moderately complex classification
Azure OpenAI Service models
Cushman-codex
Davinci-codex
Capability
Codex
GPT-3
OPENAI
Azure Cognitive Services –
Speech & OpenAI
Intelligent
Transcription
WebApp
Azure OpenAI
Service
Audio
Files
Q&A
DEMO
DEMO
THANK YOU

Contenu connexe

Similaire à weix-workshop.pptx

DataPalooza - A Music Festival themed ML + IoT Workshop
DataPalooza - A Music Festival themed ML + IoT WorkshopDataPalooza - A Music Festival themed ML + IoT Workshop
DataPalooza - A Music Festival themed ML + IoT Workshop
Amazon Web Services
 
Machine Learning & Amazon SageMaker
Machine Learning & Amazon SageMakerMachine Learning & Amazon SageMaker
Machine Learning & Amazon SageMaker
Amazon Web Services
 

Similaire à weix-workshop.pptx (20)

Sergii Baidachnyi ITEM 2018
Sergii Baidachnyi ITEM 2018Sergii Baidachnyi ITEM 2018
Sergii Baidachnyi ITEM 2018
 
ADL/U-SQL Introduction (SQLBits 2016)
ADL/U-SQL Introduction (SQLBits 2016)ADL/U-SQL Introduction (SQLBits 2016)
ADL/U-SQL Introduction (SQLBits 2016)
 
AI for an intelligent cloud and intelligent edge: Discover, deploy, and manag...
AI for an intelligent cloud and intelligent edge: Discover, deploy, and manag...AI for an intelligent cloud and intelligent edge: Discover, deploy, and manag...
AI for an intelligent cloud and intelligent edge: Discover, deploy, and manag...
 
SQL Server 2008 Data Mining
SQL Server 2008 Data MiningSQL Server 2008 Data Mining
SQL Server 2008 Data Mining
 
BI 2008 Simple
BI 2008 SimpleBI 2008 Simple
BI 2008 Simple
 
Cloud and azure and rock and roll
Cloud and azure and rock and rollCloud and azure and rock and roll
Cloud and azure and rock and roll
 
Machine Learning in azione con Amazon SageMaker
Machine Learning in azione con Amazon SageMakerMachine Learning in azione con Amazon SageMaker
Machine Learning in azione con Amazon SageMaker
 
GAIBT NewYork - Serverless Machine Learning.pptx
GAIBT NewYork - Serverless Machine Learning.pptxGAIBT NewYork - Serverless Machine Learning.pptx
GAIBT NewYork - Serverless Machine Learning.pptx
 
Datapalooza: A Music Festival Themed ML & IoT Workshop
Datapalooza: A Music Festival Themed ML & IoT WorkshopDatapalooza: A Music Festival Themed ML & IoT Workshop
Datapalooza: A Music Festival Themed ML & IoT Workshop
 
Modern Business Intelligence and Advanced Analytics
Modern Business Intelligence and Advanced AnalyticsModern Business Intelligence and Advanced Analytics
Modern Business Intelligence and Advanced Analytics
 
ChatGPT and not only: How to use the power of GPT-X models at scale
ChatGPT and not only: How to use the power of GPT-X models at scaleChatGPT and not only: How to use the power of GPT-X models at scale
ChatGPT and not only: How to use the power of GPT-X models at scale
 
Designing big data analytics solutions on azure
Designing big data analytics solutions on azureDesigning big data analytics solutions on azure
Designing big data analytics solutions on azure
 
Introduction to Azure Databricks
Introduction to Azure DatabricksIntroduction to Azure Databricks
Introduction to Azure Databricks
 
DataPalooza - A Music Festival themed ML + IoT Workshop
DataPalooza - A Music Festival themed ML + IoT WorkshopDataPalooza - A Music Festival themed ML + IoT Workshop
DataPalooza - A Music Festival themed ML + IoT Workshop
 
.Net development with Azure Machine Learning (AzureML) Nov 2014
.Net development with Azure Machine Learning (AzureML) Nov 2014.Net development with Azure Machine Learning (AzureML) Nov 2014
.Net development with Azure Machine Learning (AzureML) Nov 2014
 
Ai on the edge... and containers
Ai on the edge... and containersAi on the edge... and containers
Ai on the edge... and containers
 
Machine Learning & Amazon SageMaker
Machine Learning & Amazon SageMakerMachine Learning & Amazon SageMaker
Machine Learning & Amazon SageMaker
 
Azure Synapse 101 Webinar Presentation
Azure Synapse 101 Webinar PresentationAzure Synapse 101 Webinar Presentation
Azure Synapse 101 Webinar Presentation
 
Integrating technology to your startup
Integrating technology to your startupIntegrating technology to your startup
Integrating technology to your startup
 
Generating insights from IoT data using Amazon Machine Learning
Generating insights from IoT data using Amazon Machine LearningGenerating insights from IoT data using Amazon Machine Learning
Generating insights from IoT data using Amazon Machine Learning
 

Dernier

Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
Joaquim Jorge
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
vu2urc
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
giselly40
 

Dernier (20)

Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
Artificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and MythsArtificial Intelligence: Facts and Myths
Artificial Intelligence: Facts and Myths
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 

weix-workshop.pptx

  • 2. MACHINE LEARNING PLATFORM ARCHITECTURE Models: AKS Batch predictions: SQL DB Analytics Power BI Synapse Business Apps Responsible ML tools Seamless studio experience Notebooks Designer Comprehensive MLOps Unified management across clouds and on-premises Serverless Compute Managed Kubernetes Azure Edge & Hybrid Azure Arc-enabled Kubernetes Edge/IoT Devices Reproducibility Automation Deployment Re-training Security and Governance Automated ML Azure ML Structured Data Unstructured Data All other ML scenarios; NLP, Vision, IoT, etc. Open Datasets Prepare Data Build & Train Manage & Monitor Deploy Data Bricks
  • 3. Generative AI Prompt: Write a tagline for an ice cream shop. Response: We serve up smiles with every scoop! Prompt: Table customers, columns = [CustomerId, FirstName, LastName, Company, Address, City, State, Country, PostalCode] Create a SQL query for all customers in Texas named Jane query = Response: SELECT * FROM customers WHERE State = 'TX' AND FirstName = 'Jane' Prompt: A white Siamese cat Response: GPT-3 Codex DALL·E
  • 4. Inferencing timeCost Capability Ada • Simple classification • Parsing and formatting text Curie • Answering questions • Complex, nuanced classification Davinci • Summarizing for specific audience • Generating creative content Babbage • Semantic search ranking • Moderately complex classification Azure OpenAI Service models Cushman-codex Davinci-codex Capability Codex GPT-3
  • 5. OPENAI Azure Cognitive Services – Speech & OpenAI Intelligent Transcription WebApp Azure OpenAI Service Audio Files
  • 6. Q&A

Notes de l'éditeur

  1. AZURE ML can help us implement a Responsible MLOps process, for our entire ML lifecycle regardless of where our compute is running.  With built-in integration with Azure DevOps, developers can ensure model reproducibility, validation, deployment, and retraining.  Here, we can see that the platform architecture includes tools and services across the lifecycle – from data preparation to utilization that can be realized through deep integration with other Azure Data Services.   When the key components of a platform are Data, Model Building, Model Governance and Model Operations. Actually, Azure Machine Learning Platform empowers data scientists and developers with a wide range of capabilities to help with building, training, and deployment of machine learning models securely and at scale.  
  2. When GPT-3 is for text completion, and it is a set of models that can understand and generate natural language. it can also do interesting things with Classification and summarization, and we will get to some of these examples later.  The second is Codex that is actually a descendant of GPT-3 that can understand and generate code, including translating natural language to code. And there is a lot of interesting innovation in this space, for example take a given code and translate it to my SQL instead of SQL.  And DALL-E that is different from GPT 3 and Codex that can generate or manipulate images from natural language. And this becomes an interesting use especially for generating images on the fly. So instead of spending an hour to find prefect image for our power point presentation for example, we can generate image and do manipulation of images by providing further instructions for example to  change the background.