SlideShare a Scribd company logo
1 of 16
REST and Microservices based ML
deployment with Containers: From Data
Science experiments to Production ML
Nisha Talagala
CTO, ParallelM
2
Growing AI Investments; Few Deployed at Scale
Survey of 3073 AI-aware C-level
Executives
Source: โ€œArtificial Intelligence: The Next Digital Frontier?โ€, McKinsey Global Institute, June 2017
Out of 160 reviewed AI
use cases:
88% did not
progress
beyond the
experimental
stage
But successful early
AI adopters report:
Profit margins
3โ€“15%
higher than
industry
average
20%
AI in
Production
80%
Developing,
Experimenting,
Contemplating
https://parallelm.com/free-account
3
Development Is Only the Beginning
โ€ข Your model has great accuracy! Now what?
โ€ข Many systems available to help develop models
โ€ข โ€œSingle clickโ€ deployment has become clichรฉ
โ€ข Publicly available endpoint != Production
โ€ข Even vetted models can cause catastrophic errors (e.g.,
Knight Capital)
โ€ข Real-world context is constantly changing (e.g., search
results)
โ€ข Test conditions may not accurately represent overall goal
(e.g., resume filters)
https://parallelm.com/free-account
4
A Microservice approach to ML Deployment
MLApp
Business Application
Request Prediction
https://parallelm.com/free-account
5
MLApp
Business Application
Request Prediction
Example:
- Customer name,
- Prior purchases: cat
food, rugs, pet brush
- Search terms: toys
Example:
- Recommend:
- Cat toys
A Microservice approach to ML Deployment
https://parallelm.com/free-account
6
Endpoint != Production ML Service
โ€ข Performance โ€“ meet SLAs and avoid unhappy customers
โ€ข Resource efficiency โ€“ lower cost
โ€ข Scale out โ€“ adapt to load
โ€ข High availability
โ€ข Debuggability, Observability and Reproducibility
โ€ข Governance and Explainability
โ€ข All models and all languages
โ€ข Update models on the fly without restarting service
https://parallelm.com/free-account
7
What is inside the MLApp? Simple way to get started..
Business Application
Request Prediction
Example:
- Customer name,
- Prior purchases: cat
food, rugs, pet brush
- Search terms: toys
Example:
- Recommend:
- Cat toys
Trained Model from your favorite developer or AutoML tool
REST Inference Pipeline
https://parallelm.com/free-account
8
Business Application
Request Prediction
Example:
- Customer name,
- Prior purchases: cat food
, rugs, pet brush
- Search terms: toys
Example:
- Recommend:
- Cat toys
REST Inference Pipeline
Model Retraining pipeline
Policy Human approval
New model
What is inside the MLApp? Getting more fancy..
https://parallelm.com/free-account
9
Models, Retraining
Control, Statistics
Events, Alerts
Data Science
Platforms
Data Streams Data Lakes
MCenter
MCenter Server
Analytic
Engines
MCenter
Developer Connectors
What we do: MCenter
MCenterA
gent
MCenterA
gent
MCenterA
gent
MCenterA
gent
MCenter
Agent
MCenterA
gent
)CDSW(
10
MCenter Production Model Deployment
MCenter
Server
MCenter
Agent
Inference
Logic
Trained
Model
2 Launch an ML
Application
ML Compute
Platforms
Inference
Logic
Trained
Model
Serving
Endpoint
MCenter
Monitoring
Packaged as
Container
Deployed
Container
1 Upload Trained Model
(and optional
Inference Logic)
ServingEndpoint
3 Prediction
Request
4 Prediction
Response Business
Application
Data Scientist
Environment
https://parallelm.com/free-account
11
Deploying ML Models as a REST based service with
MCenter
โ€ข Train your model wherever you like
โ€ข Upload model into MCenter (you can do this manually or via a script)
โ€ข One step configure of a REST service
โ€ข Click โ€œLaunchโ€
โ€ข Get reports, update models, etc. from MCenter dashboards
https://parallelm.com/free-account
12
โ€ข ACME Prey Tracking Service: Wile E Coyote is tracking RoadRunner
โ€ข Road Runnerโ€™s cell phone stats are used to train a Scikit Learn Model
โ€ข Data Scientist uploads model and deploys easily via REST
โ€ข Data Scientist can use Mcenter to easily manage the Service
Demo
https://parallelm.com/free-account
13
Demo
MLApp
Business Application
(Acme Prey Tracker)
Request Prediction
https://parallelm.com/free-account
REST Inference Pipeline
Scikit Learn Model
Road Runner
cell phone
monitoring data
Road Runner
Status
14
Demo
https://parallelm.com/free-account
15
Summary
โ€ข We are at the beginnings of MLOps โ€“ production ML for real life
โ€ข With MCenter, anyone can deploy a production grade ML service and manage
full ML lifecycle
โ€ข Interested? Get a Free Account
https://parallelm.com/free-account
16
nisha.talagala@parallelm.com
https://parallelm.com/free-account

More Related Content

What's hot

Managing the Machine Learning Lifecycle with MLflow
Managing the Machine Learning Lifecycle with MLflowManaging the Machine Learning Lifecycle with MLflow
Managing the Machine Learning Lifecycle with MLflowDatabricks
ย 
Detecting Financial Fraud at Scale with Machine Learning
Detecting Financial Fraud at Scale with Machine LearningDetecting Financial Fraud at Scale with Machine Learning
Detecting Financial Fraud at Scale with Machine LearningDatabricks
ย 
NLP Text Recommendation System Journey to Automated Training
NLP Text Recommendation System Journey to Automated TrainingNLP Text Recommendation System Journey to Automated Training
NLP Text Recommendation System Journey to Automated TrainingDatabricks
ย 
Accelerating Production Machine Learning with MLflow with Matei Zaharia
Accelerating Production Machine Learning with MLflow with Matei ZahariaAccelerating Production Machine Learning with MLflow with Matei Zaharia
Accelerating Production Machine Learning with MLflow with Matei ZahariaDatabricks
ย 
Importance of ML Reproducibility & Applications with MLfLow
Importance of ML Reproducibility & Applications with MLfLowImportance of ML Reproducibility & Applications with MLfLow
Importance of ML Reproducibility & Applications with MLfLowDatabricks
ย 
High Performance Transfer Learning for Classifying Intent of Sales Engagement...
High Performance Transfer Learning for Classifying Intent of Sales Engagement...High Performance Transfer Learning for Classifying Intent of Sales Engagement...
High Performance Transfer Learning for Classifying Intent of Sales Engagement...Databricks
ย 
The Quest for an Open Source Data Science Platform
 The Quest for an Open Source Data Science Platform The Quest for an Open Source Data Science Platform
The Quest for an Open Source Data Science PlatformQAware GmbH
ย 
mlflow: Accelerating the End-to-End ML lifecycle
mlflow: Accelerating the End-to-End ML lifecyclemlflow: Accelerating the End-to-End ML lifecycle
mlflow: Accelerating the End-to-End ML lifecycleDatabricks
ย 
Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...
Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...
Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...Justin Basilico
ย 
Models in Minutes using AutoML
Models in Minutes using AutoMLModels in Minutes using AutoML
Models in Minutes using AutoMLBill Liu
ย 
Design Patterns for Machine Learning in Production - Sergei Izrailev, Chief D...
Design Patterns for Machine Learning in Production - Sergei Izrailev, Chief D...Design Patterns for Machine Learning in Production - Sergei Izrailev, Chief D...
Design Patterns for Machine Learning in Production - Sergei Izrailev, Chief D...Sri Ambati
ย 
Real-Time Fraud Detection at Scaleโ€”Integrating Real-Time Deep-Link Graph Anal...
Real-Time Fraud Detection at Scaleโ€”Integrating Real-Time Deep-Link Graph Anal...Real-Time Fraud Detection at Scaleโ€”Integrating Real-Time Deep-Link Graph Anal...
Real-Time Fraud Detection at Scaleโ€”Integrating Real-Time Deep-Link Graph Anal...Databricks
ย 
Real time machine learning
Real time machine learningReal time machine learning
Real time machine learningVinoth Kannan
ย 
Machine Learning with Apache Spark
Machine Learning with Apache SparkMachine Learning with Apache Spark
Machine Learning with Apache SparkIBM Cloud Data Services
ย 
Production ready big ml workflows from zero to hero daniel marcous @ waze
Production ready big ml workflows from zero to hero daniel marcous @ wazeProduction ready big ml workflows from zero to hero daniel marcous @ waze
Production ready big ml workflows from zero to hero daniel marcous @ wazeIdo Shilon
ย 
Leveraging Spark ML for Real-Time Credit Card Approvals with Anand Venugopal ...
Leveraging Spark ML for Real-Time Credit Card Approvals with Anand Venugopal ...Leveraging Spark ML for Real-Time Credit Card Approvals with Anand Venugopal ...
Leveraging Spark ML for Real-Time Credit Card Approvals with Anand Venugopal ...Databricks
ย 
Nasscom ml ops webinar
Nasscom ml ops webinarNasscom ml ops webinar
Nasscom ml ops webinarSameer Mahajan
ย 
Reproducible AI using MLflow and PyTorch
Reproducible AI using MLflow and PyTorchReproducible AI using MLflow and PyTorch
Reproducible AI using MLflow and PyTorchDatabricks
ย 
Porting R Models into Scala Spark
Porting R Models into Scala SparkPorting R Models into Scala Spark
Porting R Models into Scala Sparkcarl_pulley
ย 

What's hot (20)

Managing the Machine Learning Lifecycle with MLflow
Managing the Machine Learning Lifecycle with MLflowManaging the Machine Learning Lifecycle with MLflow
Managing the Machine Learning Lifecycle with MLflow
ย 
Detecting Financial Fraud at Scale with Machine Learning
Detecting Financial Fraud at Scale with Machine LearningDetecting Financial Fraud at Scale with Machine Learning
Detecting Financial Fraud at Scale with Machine Learning
ย 
NLP Text Recommendation System Journey to Automated Training
NLP Text Recommendation System Journey to Automated TrainingNLP Text Recommendation System Journey to Automated Training
NLP Text Recommendation System Journey to Automated Training
ย 
Accelerating Production Machine Learning with MLflow with Matei Zaharia
Accelerating Production Machine Learning with MLflow with Matei ZahariaAccelerating Production Machine Learning with MLflow with Matei Zaharia
Accelerating Production Machine Learning with MLflow with Matei Zaharia
ย 
Importance of ML Reproducibility & Applications with MLfLow
Importance of ML Reproducibility & Applications with MLfLowImportance of ML Reproducibility & Applications with MLfLow
Importance of ML Reproducibility & Applications with MLfLow
ย 
High Performance Transfer Learning for Classifying Intent of Sales Engagement...
High Performance Transfer Learning for Classifying Intent of Sales Engagement...High Performance Transfer Learning for Classifying Intent of Sales Engagement...
High Performance Transfer Learning for Classifying Intent of Sales Engagement...
ย 
The Quest for an Open Source Data Science Platform
 The Quest for an Open Source Data Science Platform The Quest for an Open Source Data Science Platform
The Quest for an Open Source Data Science Platform
ย 
mlflow: Accelerating the End-to-End ML lifecycle
mlflow: Accelerating the End-to-End ML lifecyclemlflow: Accelerating the End-to-End ML lifecycle
mlflow: Accelerating the End-to-End ML lifecycle
ย 
Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...
Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...
Is that a Time Machine? Some Design Patterns for Real World Machine Learning ...
ย 
Models in Minutes using AutoML
Models in Minutes using AutoMLModels in Minutes using AutoML
Models in Minutes using AutoML
ย 
MLOps at OLX
MLOps at OLXMLOps at OLX
MLOps at OLX
ย 
Design Patterns for Machine Learning in Production - Sergei Izrailev, Chief D...
Design Patterns for Machine Learning in Production - Sergei Izrailev, Chief D...Design Patterns for Machine Learning in Production - Sergei Izrailev, Chief D...
Design Patterns for Machine Learning in Production - Sergei Izrailev, Chief D...
ย 
Real-Time Fraud Detection at Scaleโ€”Integrating Real-Time Deep-Link Graph Anal...
Real-Time Fraud Detection at Scaleโ€”Integrating Real-Time Deep-Link Graph Anal...Real-Time Fraud Detection at Scaleโ€”Integrating Real-Time Deep-Link Graph Anal...
Real-Time Fraud Detection at Scaleโ€”Integrating Real-Time Deep-Link Graph Anal...
ย 
Real time machine learning
Real time machine learningReal time machine learning
Real time machine learning
ย 
Machine Learning with Apache Spark
Machine Learning with Apache SparkMachine Learning with Apache Spark
Machine Learning with Apache Spark
ย 
Production ready big ml workflows from zero to hero daniel marcous @ waze
Production ready big ml workflows from zero to hero daniel marcous @ wazeProduction ready big ml workflows from zero to hero daniel marcous @ waze
Production ready big ml workflows from zero to hero daniel marcous @ waze
ย 
Leveraging Spark ML for Real-Time Credit Card Approvals with Anand Venugopal ...
Leveraging Spark ML for Real-Time Credit Card Approvals with Anand Venugopal ...Leveraging Spark ML for Real-Time Credit Card Approvals with Anand Venugopal ...
Leveraging Spark ML for Real-Time Credit Card Approvals with Anand Venugopal ...
ย 
Nasscom ml ops webinar
Nasscom ml ops webinarNasscom ml ops webinar
Nasscom ml ops webinar
ย 
Reproducible AI using MLflow and PyTorch
Reproducible AI using MLflow and PyTorchReproducible AI using MLflow and PyTorch
Reproducible AI using MLflow and PyTorch
ย 
Porting R Models into Scala Spark
Porting R Models into Scala SparkPorting R Models into Scala Spark
Porting R Models into Scala Spark
ย 

Similar to Rest microservice ml_deployment_ntalagala_ai_conf_2019

The Machine Learning Audit. MIS ITAC 2017 Keynote
The Machine Learning Audit. MIS ITAC 2017 KeynoteThe Machine Learning Audit. MIS ITAC 2017 Keynote
The Machine Learning Audit. MIS ITAC 2017 KeynoteAndrew Clark
ย 
Practical AI use cases in Customer Service
Practical AI use cases in Customer ServicePractical AI use cases in Customer Service
Practical AI use cases in Customer ServiceDenys Holovatyi
ย 
Emerging engineering issues for building large scale AI systems By Srinivas P...
Emerging engineering issues for building large scale AI systems By Srinivas P...Emerging engineering issues for building large scale AI systems By Srinivas P...
Emerging engineering issues for building large scale AI systems By Srinivas P...Analytics India Magazine
ย 
Helping data scientists escape the seduction of the sandbox - Krish Swamy, We...
Helping data scientists escape the seduction of the sandbox - Krish Swamy, We...Helping data scientists escape the seduction of the sandbox - Krish Swamy, We...
Helping data scientists escape the seduction of the sandbox - Krish Swamy, We...Sri Ambati
ย 
IBM i & Data Science in the AI era.
IBM i & Data Science in the AI era.  IBM i & Data Science in the AI era.
IBM i & Data Science in the AI era. Benoit Marolleau
ย 
Machine Learning in Microsoft Azure
Machine Learning in Microsoft AzureMachine Learning in Microsoft Azure
Machine Learning in Microsoft AzureDmitry Petukhov
ย 
Big Data Analytics for Real Time Systems
Big Data Analytics for Real Time SystemsBig Data Analytics for Real Time Systems
Big Data Analytics for Real Time SystemsKamalika Dutta
ย 
Shiva Amiri, Chief Product Officer, RTDS Inc. at MLconf SEA - 5/01/15
Shiva Amiri, Chief Product Officer, RTDS Inc. at MLconf SEA - 5/01/15Shiva Amiri, Chief Product Officer, RTDS Inc. at MLconf SEA - 5/01/15
Shiva Amiri, Chief Product Officer, RTDS Inc. at MLconf SEA - 5/01/15MLconf
ย 
Ml master class cfa poland
Ml master class   cfa polandMl master class   cfa poland
Ml master class cfa polandQuantUniversity
ย 
IBM Meetup on November 1, 2018: Machine Learning made easy with Watson Studio
IBM Meetup on November 1, 2018: Machine Learning made easy with Watson StudioIBM Meetup on November 1, 2018: Machine Learning made easy with Watson Studio
IBM Meetup on November 1, 2018: Machine Learning made easy with Watson StudioSvetlana Levitan, PhD
ย 
MongoDB.local Austin 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB.local Austin 2018: Building Intelligent Apps with MongoDB & Google CloudMongoDB.local Austin 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB.local Austin 2018: Building Intelligent Apps with MongoDB & Google CloudMongoDB
ย 
How to make your data scientists happy
How to make your data scientists happy How to make your data scientists happy
How to make your data scientists happy Hussain Sultan
ย 
Qu for India - QuantUniversity FundRaiser
Qu for India  - QuantUniversity FundRaiserQu for India  - QuantUniversity FundRaiser
Qu for India - QuantUniversity FundRaiserQuantUniversity
ย 
CWIN17 san francisco-ai implementation-pub
CWIN17 san francisco-ai implementation-pubCWIN17 san francisco-ai implementation-pub
CWIN17 san francisco-ai implementation-pubCapgemini
ย 
Building the Ideal Stack for Machine Learning
Building the Ideal Stack for Machine LearningBuilding the Ideal Stack for Machine Learning
Building the Ideal Stack for Machine LearningSingleStore
ย 
Building Intelligent Apps with MongoDB and Google Cloud - Jane Fine
Building Intelligent Apps with MongoDB and Google Cloud - Jane FineBuilding Intelligent Apps with MongoDB and Google Cloud - Jane Fine
Building Intelligent Apps with MongoDB and Google Cloud - Jane FineMongoDB
ย 
ML and AI in Finance: Master Class
ML and AI in Finance: Master ClassML and AI in Finance: Master Class
ML and AI in Finance: Master ClassQuantUniversity
ย 
Machine Learning for Finance Master Class
Machine Learning for Finance Master Class Machine Learning for Finance Master Class
Machine Learning for Finance Master Class QuantUniversity
ย 
Disrupting Risk Management through Emerging Technologies
Disrupting Risk Management through Emerging TechnologiesDisrupting Risk Management through Emerging Technologies
Disrupting Risk Management through Emerging TechnologiesDatabricks
ย 

Similar to Rest microservice ml_deployment_ntalagala_ai_conf_2019 (20)

The Machine Learning Audit. MIS ITAC 2017 Keynote
The Machine Learning Audit. MIS ITAC 2017 KeynoteThe Machine Learning Audit. MIS ITAC 2017 Keynote
The Machine Learning Audit. MIS ITAC 2017 Keynote
ย 
Practical AI use cases in Customer Service
Practical AI use cases in Customer ServicePractical AI use cases in Customer Service
Practical AI use cases in Customer Service
ย 
Emerging engineering issues for building large scale AI systems By Srinivas P...
Emerging engineering issues for building large scale AI systems By Srinivas P...Emerging engineering issues for building large scale AI systems By Srinivas P...
Emerging engineering issues for building large scale AI systems By Srinivas P...
ย 
Helping data scientists escape the seduction of the sandbox - Krish Swamy, We...
Helping data scientists escape the seduction of the sandbox - Krish Swamy, We...Helping data scientists escape the seduction of the sandbox - Krish Swamy, We...
Helping data scientists escape the seduction of the sandbox - Krish Swamy, We...
ย 
IBM i & Data Science in the AI era.
IBM i & Data Science in the AI era.  IBM i & Data Science in the AI era.
IBM i & Data Science in the AI era.
ย 
Machine Learning in Microsoft Azure
Machine Learning in Microsoft AzureMachine Learning in Microsoft Azure
Machine Learning in Microsoft Azure
ย 
Big Data Analytics for Real Time Systems
Big Data Analytics for Real Time SystemsBig Data Analytics for Real Time Systems
Big Data Analytics for Real Time Systems
ย 
Shiva Amiri, Chief Product Officer, RTDS Inc. at MLconf SEA - 5/01/15
Shiva Amiri, Chief Product Officer, RTDS Inc. at MLconf SEA - 5/01/15Shiva Amiri, Chief Product Officer, RTDS Inc. at MLconf SEA - 5/01/15
Shiva Amiri, Chief Product Officer, RTDS Inc. at MLconf SEA - 5/01/15
ย 
Ml master class cfa poland
Ml master class   cfa polandMl master class   cfa poland
Ml master class cfa poland
ย 
IBM Meetup on November 1, 2018: Machine Learning made easy with Watson Studio
IBM Meetup on November 1, 2018: Machine Learning made easy with Watson StudioIBM Meetup on November 1, 2018: Machine Learning made easy with Watson Studio
IBM Meetup on November 1, 2018: Machine Learning made easy with Watson Studio
ย 
Ai in finance
Ai in financeAi in finance
Ai in finance
ย 
MongoDB.local Austin 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB.local Austin 2018: Building Intelligent Apps with MongoDB & Google CloudMongoDB.local Austin 2018: Building Intelligent Apps with MongoDB & Google Cloud
MongoDB.local Austin 2018: Building Intelligent Apps with MongoDB & Google Cloud
ย 
How to make your data scientists happy
How to make your data scientists happy How to make your data scientists happy
How to make your data scientists happy
ย 
Qu for India - QuantUniversity FundRaiser
Qu for India  - QuantUniversity FundRaiserQu for India  - QuantUniversity FundRaiser
Qu for India - QuantUniversity FundRaiser
ย 
CWIN17 san francisco-ai implementation-pub
CWIN17 san francisco-ai implementation-pubCWIN17 san francisco-ai implementation-pub
CWIN17 san francisco-ai implementation-pub
ย 
Building the Ideal Stack for Machine Learning
Building the Ideal Stack for Machine LearningBuilding the Ideal Stack for Machine Learning
Building the Ideal Stack for Machine Learning
ย 
Building Intelligent Apps with MongoDB and Google Cloud - Jane Fine
Building Intelligent Apps with MongoDB and Google Cloud - Jane FineBuilding Intelligent Apps with MongoDB and Google Cloud - Jane Fine
Building Intelligent Apps with MongoDB and Google Cloud - Jane Fine
ย 
ML and AI in Finance: Master Class
ML and AI in Finance: Master ClassML and AI in Finance: Master Class
ML and AI in Finance: Master Class
ย 
Machine Learning for Finance Master Class
Machine Learning for Finance Master Class Machine Learning for Finance Master Class
Machine Learning for Finance Master Class
ย 
Disrupting Risk Management through Emerging Technologies
Disrupting Risk Management through Emerging TechnologiesDisrupting Risk Management through Emerging Technologies
Disrupting Risk Management through Emerging Technologies
ย 

More from Nisha Talagala

Ml ops past_present_future
Ml ops past_present_futureMl ops past_present_future
Ml ops past_present_futureNisha Talagala
ย 
Global ai conf_final
Global ai conf_finalGlobal ai conf_final
Global ai conf_finalNisha Talagala
ย 
Pm.ais ummit 180917 final
Pm.ais ummit 180917 finalPm.ais ummit 180917 final
Pm.ais ummit 180917 finalNisha Talagala
ย 
Fms invited talk_2018 v5
Fms invited talk_2018 v5Fms invited talk_2018 v5
Fms invited talk_2018 v5Nisha Talagala
ย 
Parallel machines flinkforward2017
Parallel machines flinkforward2017Parallel machines flinkforward2017
Parallel machines flinkforward2017Nisha Talagala
ย 
Nisha talagala keynote_inflow_2016
Nisha talagala keynote_inflow_2016Nisha talagala keynote_inflow_2016
Nisha talagala keynote_inflow_2016Nisha Talagala
ย 

More from Nisha Talagala (7)

Ml ops past_present_future
Ml ops past_present_futureMl ops past_present_future
Ml ops past_present_future
ย 
Msst 2019 v4
Msst 2019 v4Msst 2019 v4
Msst 2019 v4
ย 
Global ai conf_final
Global ai conf_finalGlobal ai conf_final
Global ai conf_final
ย 
Pm.ais ummit 180917 final
Pm.ais ummit 180917 finalPm.ais ummit 180917 final
Pm.ais ummit 180917 final
ย 
Fms invited talk_2018 v5
Fms invited talk_2018 v5Fms invited talk_2018 v5
Fms invited talk_2018 v5
ย 
Parallel machines flinkforward2017
Parallel machines flinkforward2017Parallel machines flinkforward2017
Parallel machines flinkforward2017
ย 
Nisha talagala keynote_inflow_2016
Nisha talagala keynote_inflow_2016Nisha talagala keynote_inflow_2016
Nisha talagala keynote_inflow_2016
ย 

Recently uploaded

SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AISyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AIABDERRAOUF MEHENNI
ย 
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerHow To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerThousandEyes
ย 
Diamond Application Development Crafting Solutions with Precision
Diamond Application Development Crafting Solutions with PrecisionDiamond Application Development Crafting Solutions with Precision
Diamond Application Development Crafting Solutions with PrecisionSolGuruz
ย 
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Kakori Lucknow best sexual service Online โ˜‚๏ธ
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Kakori Lucknow best sexual service Online  โ˜‚๏ธCALL ON โžฅ8923113531 ๐Ÿ”Call Girls Kakori Lucknow best sexual service Online  โ˜‚๏ธ
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Kakori Lucknow best sexual service Online โ˜‚๏ธanilsa9823
ย 
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdfLearn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdfkalichargn70th171
ย 
TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providermohitmore19
ย 
Shapes for Sharing between Graph Data Spacesย - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spacesย - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data Spacesย - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spacesย - and Epistemic Querying of RDF-...Steffen Staab
ย 
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...panagenda
ย 
CHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICE9953056974 Low Rate Call Girls In Saket, Delhi NCR
ย 
call girls in Vaishali (Ghaziabad) ๐Ÿ” >เผ’8448380779 ๐Ÿ” genuine Escort Service ๐Ÿ”โœ”๏ธโœ”๏ธ
call girls in Vaishali (Ghaziabad) ๐Ÿ” >เผ’8448380779 ๐Ÿ” genuine Escort Service ๐Ÿ”โœ”๏ธโœ”๏ธcall girls in Vaishali (Ghaziabad) ๐Ÿ” >เผ’8448380779 ๐Ÿ” genuine Escort Service ๐Ÿ”โœ”๏ธโœ”๏ธ
call girls in Vaishali (Ghaziabad) ๐Ÿ” >เผ’8448380779 ๐Ÿ” genuine Escort Service ๐Ÿ”โœ”๏ธโœ”๏ธDelhi Call girls
ย 
Right Money Management App For Your Financial Goals
Right Money Management App For Your Financial GoalsRight Money Management App For Your Financial Goals
Right Money Management App For Your Financial GoalsJhone kinadey
ย 
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...harshavardhanraghave
ย 
Hand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptxHand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptxbodapatigopi8531
ย 
HR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comHR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comFatema Valibhai
ย 
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female service
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female serviceCALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female service
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female serviceanilsa9823
ย 
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...MyIntelliSource, Inc.
ย 
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...kellynguyen01
ย 
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...ICS
ย 
Optimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVOptimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVshikhaohhpro
ย 

Recently uploaded (20)

SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AISyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
ย 
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerHow To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
ย 
Diamond Application Development Crafting Solutions with Precision
Diamond Application Development Crafting Solutions with PrecisionDiamond Application Development Crafting Solutions with Precision
Diamond Application Development Crafting Solutions with Precision
ย 
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Kakori Lucknow best sexual service Online โ˜‚๏ธ
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Kakori Lucknow best sexual service Online  โ˜‚๏ธCALL ON โžฅ8923113531 ๐Ÿ”Call Girls Kakori Lucknow best sexual service Online  โ˜‚๏ธ
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Kakori Lucknow best sexual service Online โ˜‚๏ธ
ย 
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdfLearn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
ย 
Vip Call Girls Noida โžก๏ธ Delhi โžก๏ธ 9999965857 No Advance 24HRS Live
Vip Call Girls Noida โžก๏ธ Delhi โžก๏ธ 9999965857 No Advance 24HRS LiveVip Call Girls Noida โžก๏ธ Delhi โžก๏ธ 9999965857 No Advance 24HRS Live
Vip Call Girls Noida โžก๏ธ Delhi โžก๏ธ 9999965857 No Advance 24HRS Live
ย 
TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service provider
ย 
Shapes for Sharing between Graph Data Spacesย - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spacesย - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data Spacesย - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spacesย - and Epistemic Querying of RDF-...
ย 
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
ย 
CHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )๐Ÿ” 9953056974๐Ÿ”(=)/CALL GIRLS SERVICE
ย 
call girls in Vaishali (Ghaziabad) ๐Ÿ” >เผ’8448380779 ๐Ÿ” genuine Escort Service ๐Ÿ”โœ”๏ธโœ”๏ธ
call girls in Vaishali (Ghaziabad) ๐Ÿ” >เผ’8448380779 ๐Ÿ” genuine Escort Service ๐Ÿ”โœ”๏ธโœ”๏ธcall girls in Vaishali (Ghaziabad) ๐Ÿ” >เผ’8448380779 ๐Ÿ” genuine Escort Service ๐Ÿ”โœ”๏ธโœ”๏ธ
call girls in Vaishali (Ghaziabad) ๐Ÿ” >เผ’8448380779 ๐Ÿ” genuine Escort Service ๐Ÿ”โœ”๏ธโœ”๏ธ
ย 
Right Money Management App For Your Financial Goals
Right Money Management App For Your Financial GoalsRight Money Management App For Your Financial Goals
Right Money Management App For Your Financial Goals
ย 
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
Reassessing the Bedrock of Clinical Function Models: An Examination of Large ...
ย 
Hand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptxHand gesture recognition PROJECT PPT.pptx
Hand gesture recognition PROJECT PPT.pptx
ย 
HR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comHR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.com
ย 
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female service
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female serviceCALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female service
CALL ON โžฅ8923113531 ๐Ÿ”Call Girls Badshah Nagar Lucknow best Female service
ย 
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
ย 
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
ย 
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
ย 
Optimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTVOptimizing AI for immediate response in Smart CCTV
Optimizing AI for immediate response in Smart CCTV
ย 

Rest microservice ml_deployment_ntalagala_ai_conf_2019

  • 1. REST and Microservices based ML deployment with Containers: From Data Science experiments to Production ML Nisha Talagala CTO, ParallelM
  • 2. 2 Growing AI Investments; Few Deployed at Scale Survey of 3073 AI-aware C-level Executives Source: โ€œArtificial Intelligence: The Next Digital Frontier?โ€, McKinsey Global Institute, June 2017 Out of 160 reviewed AI use cases: 88% did not progress beyond the experimental stage But successful early AI adopters report: Profit margins 3โ€“15% higher than industry average 20% AI in Production 80% Developing, Experimenting, Contemplating https://parallelm.com/free-account
  • 3. 3 Development Is Only the Beginning โ€ข Your model has great accuracy! Now what? โ€ข Many systems available to help develop models โ€ข โ€œSingle clickโ€ deployment has become clichรฉ โ€ข Publicly available endpoint != Production โ€ข Even vetted models can cause catastrophic errors (e.g., Knight Capital) โ€ข Real-world context is constantly changing (e.g., search results) โ€ข Test conditions may not accurately represent overall goal (e.g., resume filters) https://parallelm.com/free-account
  • 4. 4 A Microservice approach to ML Deployment MLApp Business Application Request Prediction https://parallelm.com/free-account
  • 5. 5 MLApp Business Application Request Prediction Example: - Customer name, - Prior purchases: cat food, rugs, pet brush - Search terms: toys Example: - Recommend: - Cat toys A Microservice approach to ML Deployment https://parallelm.com/free-account
  • 6. 6 Endpoint != Production ML Service โ€ข Performance โ€“ meet SLAs and avoid unhappy customers โ€ข Resource efficiency โ€“ lower cost โ€ข Scale out โ€“ adapt to load โ€ข High availability โ€ข Debuggability, Observability and Reproducibility โ€ข Governance and Explainability โ€ข All models and all languages โ€ข Update models on the fly without restarting service https://parallelm.com/free-account
  • 7. 7 What is inside the MLApp? Simple way to get started.. Business Application Request Prediction Example: - Customer name, - Prior purchases: cat food, rugs, pet brush - Search terms: toys Example: - Recommend: - Cat toys Trained Model from your favorite developer or AutoML tool REST Inference Pipeline https://parallelm.com/free-account
  • 8. 8 Business Application Request Prediction Example: - Customer name, - Prior purchases: cat food , rugs, pet brush - Search terms: toys Example: - Recommend: - Cat toys REST Inference Pipeline Model Retraining pipeline Policy Human approval New model What is inside the MLApp? Getting more fancy.. https://parallelm.com/free-account
  • 9. 9 Models, Retraining Control, Statistics Events, Alerts Data Science Platforms Data Streams Data Lakes MCenter MCenter Server Analytic Engines MCenter Developer Connectors What we do: MCenter MCenterA gent MCenterA gent MCenterA gent MCenterA gent MCenter Agent MCenterA gent )CDSW(
  • 10. 10 MCenter Production Model Deployment MCenter Server MCenter Agent Inference Logic Trained Model 2 Launch an ML Application ML Compute Platforms Inference Logic Trained Model Serving Endpoint MCenter Monitoring Packaged as Container Deployed Container 1 Upload Trained Model (and optional Inference Logic) ServingEndpoint 3 Prediction Request 4 Prediction Response Business Application Data Scientist Environment https://parallelm.com/free-account
  • 11. 11 Deploying ML Models as a REST based service with MCenter โ€ข Train your model wherever you like โ€ข Upload model into MCenter (you can do this manually or via a script) โ€ข One step configure of a REST service โ€ข Click โ€œLaunchโ€ โ€ข Get reports, update models, etc. from MCenter dashboards https://parallelm.com/free-account
  • 12. 12 โ€ข ACME Prey Tracking Service: Wile E Coyote is tracking RoadRunner โ€ข Road Runnerโ€™s cell phone stats are used to train a Scikit Learn Model โ€ข Data Scientist uploads model and deploys easily via REST โ€ข Data Scientist can use Mcenter to easily manage the Service Demo https://parallelm.com/free-account
  • 13. 13 Demo MLApp Business Application (Acme Prey Tracker) Request Prediction https://parallelm.com/free-account REST Inference Pipeline Scikit Learn Model Road Runner cell phone monitoring data Road Runner Status
  • 15. 15 Summary โ€ข We are at the beginnings of MLOps โ€“ production ML for real life โ€ข With MCenter, anyone can deploy a production grade ML service and manage full ML lifecycle โ€ข Interested? Get a Free Account https://parallelm.com/free-account