SlideShare a Scribd company logo
Vespa - Tokyo Meetup
Kristian Aune | March 2018
Kristian Aune
Tech Product Manager Vespa
Worked in Vespa Team since 2000
Who? アメリカ最大の携帯電話会社
総従業員数: 15万人
Verizonでデジタルメディアを取
り扱う子会社
Vespa Team
26 developers in Trondheim, Norway
History:
● Fast Search & Transfer: 1998 (alltheweb.com)
● Overture: 2004
● Yahoo: 2004
● Oath: 2017
● Vespa Open Source: September 2017 - we want comitters from Japan ! 😊
Topics
What is Vespa
● History
● The Vespa Team
Vespa usage in Oath
● Select use cases
Vespa features (highlights)
● Ease of use
● Scalability
● Advanced Ranking (tensors)
Vespa
A platform for low latency computations over large, evolving data sets:
● Search and selection over structured and unstructured data
● Relevance scoring
● Query time organization and aggregation of matching data
● Real-time writes
Typical use cases: text search, personalization/recommendation/targeting, real-time
data display
Gemini Native Ads
Ads blend into streams “natively”
● Relevance
● Budget updates
● Diversity
● Match-phase
Taiwan & Hong Kong
E-commerce
Auctions and search
Streams:
Personalized Articles
Popular and personalized articles
● Relevance
● Newsroom
News Direct Display
Search Results
● Freshness
News Search
Image Search
Flickr
Search and navigation
● Machine learned models
● Public and personal
● Massive updates after model
training
Fantasy Sports
Backend for all player data
● Team rosters
● Results
● Vespa is cornerstone in serving
architecture
● Grid batch updates
● Extremely low-cost serving
Recommendations
Recommendation engine
● Videos
● Contacts
● Questions / answers
Question-to-Answer
Search Direct Display
From question to answer
● In Search, return answer!
User-generated
Content
Example news.yahoo.com
● Top / recent comments
Installing
● Rpm packages or Docker images
● All nodes have the same packages/image
● CentOS (Runs on mac and win inside Docker or VirtualBox)
● 1 config variable:
http://docs.vespa.ai/documentation/vespa-quick-start.html
http://docs.vespa.ai/documentation/vespa-quick-start-centos.html
http://docs.vespa.ai/documentation/vespa-quick-start-multinode-aws.html
echo "override VESPA_CONFIGSERVERS [config-server-hostnames]" >>
$VESPA_HOME/conf/vespa/default-env.txt
./hosts.xml
Ease of Use
./services.xml
<hosts>
<host name="host1.domain.name">
<alias>node1</alias>
</host>
<host name="host2.domain.name">
<alias>node2</alias>
</host>
<host name="host3.domain.name">
<alias>node3</alias>
</host>
</hosts>
<services version='1.0'>
<container id='default' version='1.0'>
<search/>
<document-api/>
<nodes>
<node hostalias=”node1”/>
</nodes>
</container>
<content id='music' version='1.0'>
<redundancy>2</redundancy>
<documents>
<document mode='index' type='music'/>
</documents>
<nodes>
<node hostalias=”node2” distribution-key=”1”/>
<node hostalias=”node3” distribution-key=”2”/>
</nodes>
</content>
</services>
Application
Packages
./searchdefinitions/music.sd
http://docs.vespa.ai/documentation/
search-definitions.html
search music {
document music {
field artist type string {
indexing: summary | index
}
field album type string {
indexing: summary | index
}
field track type string {
indexing: summary | index
}
field popularity type int {
indexing: summary | attribute
attribute: fast-search
}
}
rank-profile song inherits default {
first-phase {
expression {
0.7 * nativeRank(artist,album,track) +
0.3 * attribute(popularity)
}
}
}
}
Scalability
Vespa distributes data over
● A set of nodes
● With a certain replication factor
● In a set of groups
Nodes or distribution (config) change > Dynamic redistribution
No need to manually partition data - no shards!
Tensors
A data type in ranking expressions (in addition to double)
Makes it possible to deploy large and complex ML models to Vespa
Examples
● Deep neural nets
● FTRL (regression models with millions of parameters)
● Word2vec models
http://docs.vespa.ai/documentation/tensor-intro.html
What is a tensor?
Tensor: A multidimensional array which can be used for computation
Textual form: { {address}:double, .. } where address is {identifier:value},...
Examples
● 0-dimensional: A scalar {{}:0.1}
● 1-dimensional: A vector {{x:0}:0.1, {x:1}:0.2}
● 2-dimensional: A matrix {{x:0,y:0}:0.1, {x:0,y:1}:0.2}
Indexed tensor dimensions: Values addressed by numbers, continuous from 0
Mapped tensor dimensions: Values addressed by identifiers, sparse
TensorFlow import
Import machine learned ranking models trained with TensorFlow directly.
Add the files to the application package, and point to the model during ranking:
first-phase {
expression: sum(tensorflow("my_model/saved"))
}
http://docs.vespa.ai/documentation/tensorflow.html
TensorFlow import

More Related Content

What's hot

[OpenInfra Days Korea 2018] Day 2 - E5-1: "Invited Talk: Kubicorn - Building ...
[OpenInfra Days Korea 2018] Day 2 - E5-1: "Invited Talk: Kubicorn - Building ...[OpenInfra Days Korea 2018] Day 2 - E5-1: "Invited Talk: Kubicorn - Building ...
[OpenInfra Days Korea 2018] Day 2 - E5-1: "Invited Talk: Kubicorn - Building ...
OpenStack Korea Community
 
Building an external CPI for CloudStack
Building an external CPI for CloudStackBuilding an external CPI for CloudStack
Building an external CPI for CloudStack
Guillaume Berche
 
Cassandra: Now and the Future @ Yahoo! JAPAN
Cassandra: Now and the Future @ Yahoo! JAPANCassandra: Now and the Future @ Yahoo! JAPAN
Cassandra: Now and the Future @ Yahoo! JAPAN
Yahoo!デベロッパーネットワーク
 
Docker Summit 2016 - Kubernetes: Sweets and Bitters
Docker Summit 2016 - Kubernetes: Sweets and BittersDocker Summit 2016 - Kubernetes: Sweets and Bitters
Docker Summit 2016 - Kubernetes: Sweets and Bitters
smalltown
 
DevOps Practices: Configuration as Code
DevOps Practices:Configuration as CodeDevOps Practices:Configuration as Code
DevOps Practices: Configuration as Code
Doug Seven
 
OpenStack Trove Update - Juno, Kilo and Beyond
OpenStack Trove Update - Juno, Kilo and BeyondOpenStack Trove Update - Juno, Kilo and Beyond
OpenStack Trove Update - Juno, Kilo and Beyond
OpenStack_Online
 
Apache Tajo - BWC 2014
Apache Tajo - BWC 2014Apache Tajo - BWC 2014
Apache Tajo - BWC 2014
Gruter
 
Nise BOSH in Action
Nise BOSH in ActionNise BOSH in Action
Nise BOSH in Action
i_yudai
 
Kubernetes x PaaS – コンテナアプリケーションのNoOpsへの挑戦
Kubernetes x PaaS – コンテナアプリケーションのNoOpsへの挑戦Kubernetes x PaaS – コンテナアプリケーションのNoOpsへの挑戦
Kubernetes x PaaS – コンテナアプリケーションのNoOpsへの挑戦
Yoichi Kawasaki
 
Provisioning your Environment with Vagrant and Ansible
Provisioning your Environment with Vagrant and AnsibleProvisioning your Environment with Vagrant and Ansible
Provisioning your Environment with Vagrant and Ansible
Richard Gwozdz
 
Apache Bigtop: a crash course in deploying a Hadoop bigdata management platform
Apache Bigtop: a crash course in deploying a Hadoop bigdata management platformApache Bigtop: a crash course in deploying a Hadoop bigdata management platform
Apache Bigtop: a crash course in deploying a Hadoop bigdata management platform
rhatr
 
Dragon: A Distributed Object Storage at Yahoo! JAPAN (WebDB Forum 2017 / E...
   Dragon: A Distributed Object Storage at Yahoo! JAPAN (WebDB Forum 2017 / E...   Dragon: A Distributed Object Storage at Yahoo! JAPAN (WebDB Forum 2017 / E...
Dragon: A Distributed Object Storage at Yahoo! JAPAN (WebDB Forum 2017 / E...
Yahoo!デベロッパーネットワーク
 
Making sense of Apache Bigtop's role in ODPi and how it matters to Apache Apex
Making sense of Apache Bigtop's role in ODPi and how it matters to Apache ApexMaking sense of Apache Bigtop's role in ODPi and how it matters to Apache Apex
Making sense of Apache Bigtop's role in ODPi and how it matters to Apache Apex
Apache Apex
 
One-click Hadoop Cluster Deployment on OpenPOWER Systems
One-click Hadoop Cluster Deployment on OpenPOWER SystemsOne-click Hadoop Cluster Deployment on OpenPOWER Systems
One-click Hadoop Cluster Deployment on OpenPOWER Systems
Pradeep Kumar
 
Apache: Big Data North America 2017 参加報告 #streamctjp
Apache: Big Data North America 2017 参加報告  #streamctjpApache: Big Data North America 2017 参加報告  #streamctjp
Apache: Big Data North America 2017 参加報告 #streamctjp
Yahoo!デベロッパーネットワーク
 
Whats all the FaaS About
Whats all the FaaS AboutWhats all the FaaS About
Whats all the FaaS About
Haggai Philip Zagury
 
Git ops & Continuous Infrastructure with terra*
Git ops  & Continuous Infrastructure with terra*Git ops  & Continuous Infrastructure with terra*
Git ops & Continuous Infrastructure with terra*
Haggai Philip Zagury
 
London HUG 12/4
London HUG 12/4London HUG 12/4
Build an affordable Cloud Stroage
Build an affordable Cloud StroageBuild an affordable Cloud Stroage
Build an affordable Cloud Stroage
Alex Lau
 
Cloud Foundry Deployment Tools: BOSH vs Juju Charms
Cloud Foundry Deployment Tools:  BOSH vs Juju CharmsCloud Foundry Deployment Tools:  BOSH vs Juju Charms
Cloud Foundry Deployment Tools: BOSH vs Juju Charms
Altoros
 

What's hot (20)

[OpenInfra Days Korea 2018] Day 2 - E5-1: "Invited Talk: Kubicorn - Building ...
[OpenInfra Days Korea 2018] Day 2 - E5-1: "Invited Talk: Kubicorn - Building ...[OpenInfra Days Korea 2018] Day 2 - E5-1: "Invited Talk: Kubicorn - Building ...
[OpenInfra Days Korea 2018] Day 2 - E5-1: "Invited Talk: Kubicorn - Building ...
 
Building an external CPI for CloudStack
Building an external CPI for CloudStackBuilding an external CPI for CloudStack
Building an external CPI for CloudStack
 
Cassandra: Now and the Future @ Yahoo! JAPAN
Cassandra: Now and the Future @ Yahoo! JAPANCassandra: Now and the Future @ Yahoo! JAPAN
Cassandra: Now and the Future @ Yahoo! JAPAN
 
Docker Summit 2016 - Kubernetes: Sweets and Bitters
Docker Summit 2016 - Kubernetes: Sweets and BittersDocker Summit 2016 - Kubernetes: Sweets and Bitters
Docker Summit 2016 - Kubernetes: Sweets and Bitters
 
DevOps Practices: Configuration as Code
DevOps Practices:Configuration as CodeDevOps Practices:Configuration as Code
DevOps Practices: Configuration as Code
 
OpenStack Trove Update - Juno, Kilo and Beyond
OpenStack Trove Update - Juno, Kilo and BeyondOpenStack Trove Update - Juno, Kilo and Beyond
OpenStack Trove Update - Juno, Kilo and Beyond
 
Apache Tajo - BWC 2014
Apache Tajo - BWC 2014Apache Tajo - BWC 2014
Apache Tajo - BWC 2014
 
Nise BOSH in Action
Nise BOSH in ActionNise BOSH in Action
Nise BOSH in Action
 
Kubernetes x PaaS – コンテナアプリケーションのNoOpsへの挑戦
Kubernetes x PaaS – コンテナアプリケーションのNoOpsへの挑戦Kubernetes x PaaS – コンテナアプリケーションのNoOpsへの挑戦
Kubernetes x PaaS – コンテナアプリケーションのNoOpsへの挑戦
 
Provisioning your Environment with Vagrant and Ansible
Provisioning your Environment with Vagrant and AnsibleProvisioning your Environment with Vagrant and Ansible
Provisioning your Environment with Vagrant and Ansible
 
Apache Bigtop: a crash course in deploying a Hadoop bigdata management platform
Apache Bigtop: a crash course in deploying a Hadoop bigdata management platformApache Bigtop: a crash course in deploying a Hadoop bigdata management platform
Apache Bigtop: a crash course in deploying a Hadoop bigdata management platform
 
Dragon: A Distributed Object Storage at Yahoo! JAPAN (WebDB Forum 2017 / E...
   Dragon: A Distributed Object Storage at Yahoo! JAPAN (WebDB Forum 2017 / E...   Dragon: A Distributed Object Storage at Yahoo! JAPAN (WebDB Forum 2017 / E...
Dragon: A Distributed Object Storage at Yahoo! JAPAN (WebDB Forum 2017 / E...
 
Making sense of Apache Bigtop's role in ODPi and how it matters to Apache Apex
Making sense of Apache Bigtop's role in ODPi and how it matters to Apache ApexMaking sense of Apache Bigtop's role in ODPi and how it matters to Apache Apex
Making sense of Apache Bigtop's role in ODPi and how it matters to Apache Apex
 
One-click Hadoop Cluster Deployment on OpenPOWER Systems
One-click Hadoop Cluster Deployment on OpenPOWER SystemsOne-click Hadoop Cluster Deployment on OpenPOWER Systems
One-click Hadoop Cluster Deployment on OpenPOWER Systems
 
Apache: Big Data North America 2017 参加報告 #streamctjp
Apache: Big Data North America 2017 参加報告  #streamctjpApache: Big Data North America 2017 参加報告  #streamctjp
Apache: Big Data North America 2017 参加報告 #streamctjp
 
Whats all the FaaS About
Whats all the FaaS AboutWhats all the FaaS About
Whats all the FaaS About
 
Git ops & Continuous Infrastructure with terra*
Git ops  & Continuous Infrastructure with terra*Git ops  & Continuous Infrastructure with terra*
Git ops & Continuous Infrastructure with terra*
 
London HUG 12/4
London HUG 12/4London HUG 12/4
London HUG 12/4
 
Build an affordable Cloud Stroage
Build an affordable Cloud StroageBuild an affordable Cloud Stroage
Build an affordable Cloud Stroage
 
Cloud Foundry Deployment Tools: BOSH vs Juju Charms
Cloud Foundry Deployment Tools:  BOSH vs Juju CharmsCloud Foundry Deployment Tools:  BOSH vs Juju Charms
Cloud Foundry Deployment Tools: BOSH vs Juju Charms
 

Similar to Vespa - Tokyo Meetup #yjmu

SAS integration with NoSQL data
SAS integration with NoSQL dataSAS integration with NoSQL data
SAS integration with NoSQL data
Kevin Lee
 
ITB2019 NGINX Overview and Technical Aspects - Kevin Jones
ITB2019 NGINX Overview and Technical Aspects - Kevin JonesITB2019 NGINX Overview and Technical Aspects - Kevin Jones
ITB2019 NGINX Overview and Technical Aspects - Kevin Jones
Ortus Solutions, Corp
 
Infrastructure Considerations : Design : "webops"
Infrastructure Considerations : Design : "webops"Infrastructure Considerations : Design : "webops"
Infrastructure Considerations : Design : "webops"
Piyush Kumar
 
nodejs_at_a_glance.ppt
nodejs_at_a_glance.pptnodejs_at_a_glance.ppt
nodejs_at_a_glance.ppt
WalaSidhom1
 
T3 - Deploy, manage, and scale your apps
T3 - Deploy, manage, and scale your appsT3 - Deploy, manage, and scale your apps
T3 - Deploy, manage, and scale your apps
Amazon Web Services
 
App fabric introduction
App fabric introductionApp fabric introduction
App fabric introduction
Dennis van der Stelt
 
Automated release management - DevConFu 2014
Automated release management - DevConFu 2014Automated release management - DevConFu 2014
Automated release management - DevConFu 2014
Kristoffer Deinoff
 
Deploy and Destroy: Testing Environments - Michael Arenzon - DevOpsDays Tel A...
Deploy and Destroy: Testing Environments - Michael Arenzon - DevOpsDays Tel A...Deploy and Destroy: Testing Environments - Michael Arenzon - DevOpsDays Tel A...
Deploy and Destroy: Testing Environments - Michael Arenzon - DevOpsDays Tel A...
DevOpsDays Tel Aviv
 
Apache Samza 1.0 - What's New, What's Next
Apache Samza 1.0 - What's New, What's NextApache Samza 1.0 - What's New, What's Next
Apache Samza 1.0 - What's New, What's Next
Prateek Maheshwari
 
Introduction to node js - From "hello world" to deploying on azure
Introduction to node js - From "hello world" to deploying on azureIntroduction to node js - From "hello world" to deploying on azure
Introduction to node js - From "hello world" to deploying on azure
Colin Mackay
 
Introduction to Chef
Introduction to ChefIntroduction to Chef
Introduction to Chef
Suresh Paulraj
 
Using Elasticsearch for Analytics
Using Elasticsearch for AnalyticsUsing Elasticsearch for Analytics
Using Elasticsearch for Analytics
Vaidik Kapoor
 
OpenStack LA meetup Feb 18, 2015
OpenStack LA meetup Feb 18, 2015OpenStack LA meetup Feb 18, 2015
OpenStack LA meetup Feb 18, 2015
Tesora
 
Manage Infrastructure Securely at Scale and Eliminate Operational Risks - DEV...
Manage Infrastructure Securely at Scale and Eliminate Operational Risks - DEV...Manage Infrastructure Securely at Scale and Eliminate Operational Risks - DEV...
Manage Infrastructure Securely at Scale and Eliminate Operational Risks - DEV...
Amazon Web Services
 
Deploy, Manage, and Scale Your Apps with OpsWorks and Elastic Beanstalk
Deploy, Manage, and Scale Your Apps with OpsWorks and Elastic BeanstalkDeploy, Manage, and Scale Your Apps with OpsWorks and Elastic Beanstalk
Deploy, Manage, and Scale Your Apps with OpsWorks and Elastic Beanstalk
Amazon Web Services
 
Devops continuousintegration and deployment onaws puttingmoneybackintoyourmis...
Devops continuousintegration and deployment onaws puttingmoneybackintoyourmis...Devops continuousintegration and deployment onaws puttingmoneybackintoyourmis...
Devops continuousintegration and deployment onaws puttingmoneybackintoyourmis...
Emerson Eduardo Rodrigues Von Staffen
 
DevOps, Continuous Integration and Deployment on AWS: Putting Money Back into...
DevOps, Continuous Integration and Deployment on AWS: Putting Money Back into...DevOps, Continuous Integration and Deployment on AWS: Putting Money Back into...
DevOps, Continuous Integration and Deployment on AWS: Putting Money Back into...
Amazon Web Services
 
Infrastructure as code, using Terraform
Infrastructure as code, using TerraformInfrastructure as code, using Terraform
Infrastructure as code, using Terraform
Harkamal Singh
 
AWS Summit Stockholm 2014 – T5 – Deploy, manage and scale applications on AWS
AWS Summit Stockholm 2014 – T5 – Deploy, manage and scale applications on AWSAWS Summit Stockholm 2014 – T5 – Deploy, manage and scale applications on AWS
AWS Summit Stockholm 2014 – T5 – Deploy, manage and scale applications on AWS
Amazon Web Services
 
Azue_Serverless.pptx
Azue_Serverless.pptxAzue_Serverless.pptx
Azue_Serverless.pptx
PRATAPRAMISETTY1
 

Similar to Vespa - Tokyo Meetup #yjmu (20)

SAS integration with NoSQL data
SAS integration with NoSQL dataSAS integration with NoSQL data
SAS integration with NoSQL data
 
ITB2019 NGINX Overview and Technical Aspects - Kevin Jones
ITB2019 NGINX Overview and Technical Aspects - Kevin JonesITB2019 NGINX Overview and Technical Aspects - Kevin Jones
ITB2019 NGINX Overview and Technical Aspects - Kevin Jones
 
Infrastructure Considerations : Design : "webops"
Infrastructure Considerations : Design : "webops"Infrastructure Considerations : Design : "webops"
Infrastructure Considerations : Design : "webops"
 
nodejs_at_a_glance.ppt
nodejs_at_a_glance.pptnodejs_at_a_glance.ppt
nodejs_at_a_glance.ppt
 
T3 - Deploy, manage, and scale your apps
T3 - Deploy, manage, and scale your appsT3 - Deploy, manage, and scale your apps
T3 - Deploy, manage, and scale your apps
 
App fabric introduction
App fabric introductionApp fabric introduction
App fabric introduction
 
Automated release management - DevConFu 2014
Automated release management - DevConFu 2014Automated release management - DevConFu 2014
Automated release management - DevConFu 2014
 
Deploy and Destroy: Testing Environments - Michael Arenzon - DevOpsDays Tel A...
Deploy and Destroy: Testing Environments - Michael Arenzon - DevOpsDays Tel A...Deploy and Destroy: Testing Environments - Michael Arenzon - DevOpsDays Tel A...
Deploy and Destroy: Testing Environments - Michael Arenzon - DevOpsDays Tel A...
 
Apache Samza 1.0 - What's New, What's Next
Apache Samza 1.0 - What's New, What's NextApache Samza 1.0 - What's New, What's Next
Apache Samza 1.0 - What's New, What's Next
 
Introduction to node js - From "hello world" to deploying on azure
Introduction to node js - From "hello world" to deploying on azureIntroduction to node js - From "hello world" to deploying on azure
Introduction to node js - From "hello world" to deploying on azure
 
Introduction to Chef
Introduction to ChefIntroduction to Chef
Introduction to Chef
 
Using Elasticsearch for Analytics
Using Elasticsearch for AnalyticsUsing Elasticsearch for Analytics
Using Elasticsearch for Analytics
 
OpenStack LA meetup Feb 18, 2015
OpenStack LA meetup Feb 18, 2015OpenStack LA meetup Feb 18, 2015
OpenStack LA meetup Feb 18, 2015
 
Manage Infrastructure Securely at Scale and Eliminate Operational Risks - DEV...
Manage Infrastructure Securely at Scale and Eliminate Operational Risks - DEV...Manage Infrastructure Securely at Scale and Eliminate Operational Risks - DEV...
Manage Infrastructure Securely at Scale and Eliminate Operational Risks - DEV...
 
Deploy, Manage, and Scale Your Apps with OpsWorks and Elastic Beanstalk
Deploy, Manage, and Scale Your Apps with OpsWorks and Elastic BeanstalkDeploy, Manage, and Scale Your Apps with OpsWorks and Elastic Beanstalk
Deploy, Manage, and Scale Your Apps with OpsWorks and Elastic Beanstalk
 
Devops continuousintegration and deployment onaws puttingmoneybackintoyourmis...
Devops continuousintegration and deployment onaws puttingmoneybackintoyourmis...Devops continuousintegration and deployment onaws puttingmoneybackintoyourmis...
Devops continuousintegration and deployment onaws puttingmoneybackintoyourmis...
 
DevOps, Continuous Integration and Deployment on AWS: Putting Money Back into...
DevOps, Continuous Integration and Deployment on AWS: Putting Money Back into...DevOps, Continuous Integration and Deployment on AWS: Putting Money Back into...
DevOps, Continuous Integration and Deployment on AWS: Putting Money Back into...
 
Infrastructure as code, using Terraform
Infrastructure as code, using TerraformInfrastructure as code, using Terraform
Infrastructure as code, using Terraform
 
AWS Summit Stockholm 2014 – T5 – Deploy, manage and scale applications on AWS
AWS Summit Stockholm 2014 – T5 – Deploy, manage and scale applications on AWSAWS Summit Stockholm 2014 – T5 – Deploy, manage and scale applications on AWS
AWS Summit Stockholm 2014 – T5 – Deploy, manage and scale applications on AWS
 
Azue_Serverless.pptx
Azue_Serverless.pptxAzue_Serverless.pptx
Azue_Serverless.pptx
 

More from Yahoo!デベロッパーネットワーク

ゼロから始める転移学習
ゼロから始める転移学習ゼロから始める転移学習
ゼロから始める転移学習
Yahoo!デベロッパーネットワーク
 
継続的なモデルモニタリングを実現するKubernetes Operator
継続的なモデルモニタリングを実現するKubernetes Operator継続的なモデルモニタリングを実現するKubernetes Operator
継続的なモデルモニタリングを実現するKubernetes Operator
Yahoo!デベロッパーネットワーク
 
ヤフーでは開発迅速性と品質のバランスをどう取ってるか
ヤフーでは開発迅速性と品質のバランスをどう取ってるかヤフーでは開発迅速性と品質のバランスをどう取ってるか
ヤフーでは開発迅速性と品質のバランスをどう取ってるか
Yahoo!デベロッパーネットワーク
 
オンプレML基盤on Kubernetes パネルディスカッション
オンプレML基盤on Kubernetes パネルディスカッションオンプレML基盤on Kubernetes パネルディスカッション
オンプレML基盤on Kubernetes パネルディスカッション
Yahoo!デベロッパーネットワーク
 
LakeTahoe
LakeTahoeLakeTahoe
オンプレML基盤on Kubernetes 〜Yahoo! JAPAN AIPF〜
オンプレML基盤on Kubernetes 〜Yahoo! JAPAN AIPF〜オンプレML基盤on Kubernetes 〜Yahoo! JAPAN AIPF〜
オンプレML基盤on Kubernetes 〜Yahoo! JAPAN AIPF〜
Yahoo!デベロッパーネットワーク
 
Persistent-memory-native Database High-availability Feature
Persistent-memory-native Database High-availability FeaturePersistent-memory-native Database High-availability Feature
Persistent-memory-native Database High-availability Feature
Yahoo!デベロッパーネットワーク
 
データの価値を最大化させるためのデザイン~データビジュアライゼーションの方法~ #devsumi 17-E-2
データの価値を最大化させるためのデザイン~データビジュアライゼーションの方法~ #devsumi 17-E-2データの価値を最大化させるためのデザイン~データビジュアライゼーションの方法~ #devsumi 17-E-2
データの価値を最大化させるためのデザイン~データビジュアライゼーションの方法~ #devsumi 17-E-2
Yahoo!デベロッパーネットワーク
 
eコマースと実店舗の相互利益を目指したデザイン #yjtc
eコマースと実店舗の相互利益を目指したデザイン #yjtceコマースと実店舗の相互利益を目指したデザイン #yjtc
eコマースと実店舗の相互利益を目指したデザイン #yjtc
Yahoo!デベロッパーネットワーク
 
ヤフーを支えるセキュリティ ~サイバー攻撃を防ぐエンジニアの仕事とは~ #yjtc
ヤフーを支えるセキュリティ ~サイバー攻撃を防ぐエンジニアの仕事とは~ #yjtcヤフーを支えるセキュリティ ~サイバー攻撃を防ぐエンジニアの仕事とは~ #yjtc
ヤフーを支えるセキュリティ ~サイバー攻撃を防ぐエンジニアの仕事とは~ #yjtc
Yahoo!デベロッパーネットワーク
 
Yahoo! JAPANのIaaSを支えるKubernetesクラスタ、アップデート自動化への挑戦 #yjtc
Yahoo! JAPANのIaaSを支えるKubernetesクラスタ、アップデート自動化への挑戦 #yjtcYahoo! JAPANのIaaSを支えるKubernetesクラスタ、アップデート自動化への挑戦 #yjtc
Yahoo! JAPANのIaaSを支えるKubernetesクラスタ、アップデート自動化への挑戦 #yjtc
Yahoo!デベロッパーネットワーク
 
ビッグデータから人々のムードを捉える #yjtc
ビッグデータから人々のムードを捉える #yjtcビッグデータから人々のムードを捉える #yjtc
ビッグデータから人々のムードを捉える #yjtc
Yahoo!デベロッパーネットワーク
 
サイエンス領域におけるMLOpsの取り組み #yjtc
サイエンス領域におけるMLOpsの取り組み #yjtcサイエンス領域におけるMLOpsの取り組み #yjtc
サイエンス領域におけるMLOpsの取り組み #yjtc
Yahoo!デベロッパーネットワーク
 
ヤフーのAIプラットフォーム紹介 ~AIテックカンパニーを支えるデータ基盤~ #yjtc
ヤフーのAIプラットフォーム紹介 ~AIテックカンパニーを支えるデータ基盤~ #yjtcヤフーのAIプラットフォーム紹介 ~AIテックカンパニーを支えるデータ基盤~ #yjtc
ヤフーのAIプラットフォーム紹介 ~AIテックカンパニーを支えるデータ基盤~ #yjtc
Yahoo!デベロッパーネットワーク
 
Yahoo! JAPAN Tech Conference 2022 Day2 Keynote #yjtc
Yahoo! JAPAN Tech Conference 2022 Day2 Keynote #yjtcYahoo! JAPAN Tech Conference 2022 Day2 Keynote #yjtc
Yahoo! JAPAN Tech Conference 2022 Day2 Keynote #yjtc
Yahoo!デベロッパーネットワーク
 
新技術を使った次世代の商品の見せ方 ~ヤフオク!のマルチビュー機能~ #yjtc
新技術を使った次世代の商品の見せ方 ~ヤフオク!のマルチビュー機能~ #yjtc新技術を使った次世代の商品の見せ方 ~ヤフオク!のマルチビュー機能~ #yjtc
新技術を使った次世代の商品の見せ方 ~ヤフオク!のマルチビュー機能~ #yjtc
Yahoo!デベロッパーネットワーク
 
PC版Yahoo!メールリニューアル ~サービスのUI/UX統合と改善プロセス~ #yjtc
PC版Yahoo!メールリニューアル ~サービスのUI/UX統合と改善プロセス~ #yjtcPC版Yahoo!メールリニューアル ~サービスのUI/UX統合と改善プロセス~ #yjtc
PC版Yahoo!メールリニューアル ~サービスのUI/UX統合と改善プロセス~ #yjtc
Yahoo!デベロッパーネットワーク
 
モブデザインによる多職種チームのコミュニケーション改善 #yjtc
モブデザインによる多職種チームのコミュニケーション改善 #yjtcモブデザインによる多職種チームのコミュニケーション改善 #yjtc
モブデザインによる多職種チームのコミュニケーション改善 #yjtc
Yahoo!デベロッパーネットワーク
 
「新しいおうち探し」のためのAIアシスト検索 #yjtc
「新しいおうち探し」のためのAIアシスト検索 #yjtc「新しいおうち探し」のためのAIアシスト検索 #yjtc
「新しいおうち探し」のためのAIアシスト検索 #yjtc
Yahoo!デベロッパーネットワーク
 
ユーザーの地域を考慮した検索入力補助機能の改善の試み #yjtc
ユーザーの地域を考慮した検索入力補助機能の改善の試み #yjtcユーザーの地域を考慮した検索入力補助機能の改善の試み #yjtc
ユーザーの地域を考慮した検索入力補助機能の改善の試み #yjtc
Yahoo!デベロッパーネットワーク
 

More from Yahoo!デベロッパーネットワーク (20)

ゼロから始める転移学習
ゼロから始める転移学習ゼロから始める転移学習
ゼロから始める転移学習
 
継続的なモデルモニタリングを実現するKubernetes Operator
継続的なモデルモニタリングを実現するKubernetes Operator継続的なモデルモニタリングを実現するKubernetes Operator
継続的なモデルモニタリングを実現するKubernetes Operator
 
ヤフーでは開発迅速性と品質のバランスをどう取ってるか
ヤフーでは開発迅速性と品質のバランスをどう取ってるかヤフーでは開発迅速性と品質のバランスをどう取ってるか
ヤフーでは開発迅速性と品質のバランスをどう取ってるか
 
オンプレML基盤on Kubernetes パネルディスカッション
オンプレML基盤on Kubernetes パネルディスカッションオンプレML基盤on Kubernetes パネルディスカッション
オンプレML基盤on Kubernetes パネルディスカッション
 
LakeTahoe
LakeTahoeLakeTahoe
LakeTahoe
 
オンプレML基盤on Kubernetes 〜Yahoo! JAPAN AIPF〜
オンプレML基盤on Kubernetes 〜Yahoo! JAPAN AIPF〜オンプレML基盤on Kubernetes 〜Yahoo! JAPAN AIPF〜
オンプレML基盤on Kubernetes 〜Yahoo! JAPAN AIPF〜
 
Persistent-memory-native Database High-availability Feature
Persistent-memory-native Database High-availability FeaturePersistent-memory-native Database High-availability Feature
Persistent-memory-native Database High-availability Feature
 
データの価値を最大化させるためのデザイン~データビジュアライゼーションの方法~ #devsumi 17-E-2
データの価値を最大化させるためのデザイン~データビジュアライゼーションの方法~ #devsumi 17-E-2データの価値を最大化させるためのデザイン~データビジュアライゼーションの方法~ #devsumi 17-E-2
データの価値を最大化させるためのデザイン~データビジュアライゼーションの方法~ #devsumi 17-E-2
 
eコマースと実店舗の相互利益を目指したデザイン #yjtc
eコマースと実店舗の相互利益を目指したデザイン #yjtceコマースと実店舗の相互利益を目指したデザイン #yjtc
eコマースと実店舗の相互利益を目指したデザイン #yjtc
 
ヤフーを支えるセキュリティ ~サイバー攻撃を防ぐエンジニアの仕事とは~ #yjtc
ヤフーを支えるセキュリティ ~サイバー攻撃を防ぐエンジニアの仕事とは~ #yjtcヤフーを支えるセキュリティ ~サイバー攻撃を防ぐエンジニアの仕事とは~ #yjtc
ヤフーを支えるセキュリティ ~サイバー攻撃を防ぐエンジニアの仕事とは~ #yjtc
 
Yahoo! JAPANのIaaSを支えるKubernetesクラスタ、アップデート自動化への挑戦 #yjtc
Yahoo! JAPANのIaaSを支えるKubernetesクラスタ、アップデート自動化への挑戦 #yjtcYahoo! JAPANのIaaSを支えるKubernetesクラスタ、アップデート自動化への挑戦 #yjtc
Yahoo! JAPANのIaaSを支えるKubernetesクラスタ、アップデート自動化への挑戦 #yjtc
 
ビッグデータから人々のムードを捉える #yjtc
ビッグデータから人々のムードを捉える #yjtcビッグデータから人々のムードを捉える #yjtc
ビッグデータから人々のムードを捉える #yjtc
 
サイエンス領域におけるMLOpsの取り組み #yjtc
サイエンス領域におけるMLOpsの取り組み #yjtcサイエンス領域におけるMLOpsの取り組み #yjtc
サイエンス領域におけるMLOpsの取り組み #yjtc
 
ヤフーのAIプラットフォーム紹介 ~AIテックカンパニーを支えるデータ基盤~ #yjtc
ヤフーのAIプラットフォーム紹介 ~AIテックカンパニーを支えるデータ基盤~ #yjtcヤフーのAIプラットフォーム紹介 ~AIテックカンパニーを支えるデータ基盤~ #yjtc
ヤフーのAIプラットフォーム紹介 ~AIテックカンパニーを支えるデータ基盤~ #yjtc
 
Yahoo! JAPAN Tech Conference 2022 Day2 Keynote #yjtc
Yahoo! JAPAN Tech Conference 2022 Day2 Keynote #yjtcYahoo! JAPAN Tech Conference 2022 Day2 Keynote #yjtc
Yahoo! JAPAN Tech Conference 2022 Day2 Keynote #yjtc
 
新技術を使った次世代の商品の見せ方 ~ヤフオク!のマルチビュー機能~ #yjtc
新技術を使った次世代の商品の見せ方 ~ヤフオク!のマルチビュー機能~ #yjtc新技術を使った次世代の商品の見せ方 ~ヤフオク!のマルチビュー機能~ #yjtc
新技術を使った次世代の商品の見せ方 ~ヤフオク!のマルチビュー機能~ #yjtc
 
PC版Yahoo!メールリニューアル ~サービスのUI/UX統合と改善プロセス~ #yjtc
PC版Yahoo!メールリニューアル ~サービスのUI/UX統合と改善プロセス~ #yjtcPC版Yahoo!メールリニューアル ~サービスのUI/UX統合と改善プロセス~ #yjtc
PC版Yahoo!メールリニューアル ~サービスのUI/UX統合と改善プロセス~ #yjtc
 
モブデザインによる多職種チームのコミュニケーション改善 #yjtc
モブデザインによる多職種チームのコミュニケーション改善 #yjtcモブデザインによる多職種チームのコミュニケーション改善 #yjtc
モブデザインによる多職種チームのコミュニケーション改善 #yjtc
 
「新しいおうち探し」のためのAIアシスト検索 #yjtc
「新しいおうち探し」のためのAIアシスト検索 #yjtc「新しいおうち探し」のためのAIアシスト検索 #yjtc
「新しいおうち探し」のためのAIアシスト検索 #yjtc
 
ユーザーの地域を考慮した検索入力補助機能の改善の試み #yjtc
ユーザーの地域を考慮した検索入力補助機能の改善の試み #yjtcユーザーの地域を考慮した検索入力補助機能の改善の試み #yjtc
ユーザーの地域を考慮した検索入力補助機能の改善の試み #yjtc
 

Recently uploaded

leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
alexjohnson7307
 
Monitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdfMonitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdf
Tosin Akinosho
 
Generating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and MilvusGenerating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and Milvus
Zilliz
 
Fueling AI with Great Data with Airbyte Webinar
Fueling AI with Great Data with Airbyte WebinarFueling AI with Great Data with Airbyte Webinar
Fueling AI with Great Data with Airbyte Webinar
Zilliz
 
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
saastr
 
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUHCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
panagenda
 
Serial Arm Control in Real Time Presentation
Serial Arm Control in Real Time PresentationSerial Arm Control in Real Time Presentation
Serial Arm Control in Real Time Presentation
tolgahangng
 
System Design Case Study: Building a Scalable E-Commerce Platform - Hiike
System Design Case Study: Building a Scalable E-Commerce Platform - HiikeSystem Design Case Study: Building a Scalable E-Commerce Platform - Hiike
System Design Case Study: Building a Scalable E-Commerce Platform - Hiike
Hiike
 
Taking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdfTaking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdf
ssuserfac0301
 
Azure API Management to expose backend services securely
Azure API Management to expose backend services securelyAzure API Management to expose backend services securely
Azure API Management to expose backend services securely
Dinusha Kumarasiri
 
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStrDeep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
saastr
 
Choosing The Best AWS Service For Your Website + API.pptx
Choosing The Best AWS Service For Your Website + API.pptxChoosing The Best AWS Service For Your Website + API.pptx
Choosing The Best AWS Service For Your Website + API.pptx
Brandon Minnick, MBA
 
AWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptxAWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptx
HarisZaheer8
 
HCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAUHCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAU
panagenda
 
WeTestAthens: Postman's AI & Automation Techniques
WeTestAthens: Postman's AI & Automation TechniquesWeTestAthens: Postman's AI & Automation Techniques
WeTestAthens: Postman's AI & Automation Techniques
Postman
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
Chart Kalyan
 
A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024
Intelisync
 
Digital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying AheadDigital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying Ahead
Wask
 
Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)
Jakub Marek
 
5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
DanBrown980551
 

Recently uploaded (20)

leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
leewayhertz.com-AI in predictive maintenance Use cases technologies benefits ...
 
Monitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdfMonitoring and Managing Anomaly Detection on OpenShift.pdf
Monitoring and Managing Anomaly Detection on OpenShift.pdf
 
Generating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and MilvusGenerating privacy-protected synthetic data using Secludy and Milvus
Generating privacy-protected synthetic data using Secludy and Milvus
 
Fueling AI with Great Data with Airbyte Webinar
Fueling AI with Great Data with Airbyte WebinarFueling AI with Great Data with Airbyte Webinar
Fueling AI with Great Data with Airbyte Webinar
 
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
Deep Dive: AI-Powered Marketing to Get More Leads and Customers with HyperGro...
 
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUHCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAU
 
Serial Arm Control in Real Time Presentation
Serial Arm Control in Real Time PresentationSerial Arm Control in Real Time Presentation
Serial Arm Control in Real Time Presentation
 
System Design Case Study: Building a Scalable E-Commerce Platform - Hiike
System Design Case Study: Building a Scalable E-Commerce Platform - HiikeSystem Design Case Study: Building a Scalable E-Commerce Platform - Hiike
System Design Case Study: Building a Scalable E-Commerce Platform - Hiike
 
Taking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdfTaking AI to the Next Level in Manufacturing.pdf
Taking AI to the Next Level in Manufacturing.pdf
 
Azure API Management to expose backend services securely
Azure API Management to expose backend services securelyAzure API Management to expose backend services securely
Azure API Management to expose backend services securely
 
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStrDeep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
Deep Dive: Getting Funded with Jason Jason Lemkin Founder & CEO @ SaaStr
 
Choosing The Best AWS Service For Your Website + API.pptx
Choosing The Best AWS Service For Your Website + API.pptxChoosing The Best AWS Service For Your Website + API.pptx
Choosing The Best AWS Service For Your Website + API.pptx
 
AWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptxAWS Cloud Cost Optimization Presentation.pptx
AWS Cloud Cost Optimization Presentation.pptx
 
HCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAUHCL Notes and Domino License Cost Reduction in the World of DLAU
HCL Notes and Domino License Cost Reduction in the World of DLAU
 
WeTestAthens: Postman's AI & Automation Techniques
WeTestAthens: Postman's AI & Automation TechniquesWeTestAthens: Postman's AI & Automation Techniques
WeTestAthens: Postman's AI & Automation Techniques
 
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfHow to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdf
 
A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024A Comprehensive Guide to DeFi Development Services in 2024
A Comprehensive Guide to DeFi Development Services in 2024
 
Digital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying AheadDigital Marketing Trends in 2024 | Guide for Staying Ahead
Digital Marketing Trends in 2024 | Guide for Staying Ahead
 
Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)Main news related to the CCS TSI 2023 (2023/1695)
Main news related to the CCS TSI 2023 (2023/1695)
 
5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides5th LF Energy Power Grid Model Meet-up Slides
5th LF Energy Power Grid Model Meet-up Slides
 

Vespa - Tokyo Meetup #yjmu

  • 1. Vespa - Tokyo Meetup Kristian Aune | March 2018
  • 2. Kristian Aune Tech Product Manager Vespa Worked in Vespa Team since 2000
  • 4. Vespa Team 26 developers in Trondheim, Norway History: ● Fast Search & Transfer: 1998 (alltheweb.com) ● Overture: 2004 ● Yahoo: 2004 ● Oath: 2017 ● Vespa Open Source: September 2017 - we want comitters from Japan ! 😊
  • 5. Topics What is Vespa ● History ● The Vespa Team Vespa usage in Oath ● Select use cases Vespa features (highlights) ● Ease of use ● Scalability ● Advanced Ranking (tensors)
  • 6. Vespa A platform for low latency computations over large, evolving data sets: ● Search and selection over structured and unstructured data ● Relevance scoring ● Query time organization and aggregation of matching data ● Real-time writes Typical use cases: text search, personalization/recommendation/targeting, real-time data display
  • 7. Gemini Native Ads Ads blend into streams “natively” ● Relevance ● Budget updates ● Diversity ● Match-phase
  • 8. Taiwan & Hong Kong E-commerce Auctions and search
  • 9. Streams: Personalized Articles Popular and personalized articles ● Relevance ● Newsroom
  • 10. News Direct Display Search Results ● Freshness News Search
  • 11. Image Search Flickr Search and navigation ● Machine learned models ● Public and personal ● Massive updates after model training
  • 12. Fantasy Sports Backend for all player data ● Team rosters ● Results ● Vespa is cornerstone in serving architecture ● Grid batch updates ● Extremely low-cost serving
  • 13. Recommendations Recommendation engine ● Videos ● Contacts ● Questions / answers
  • 14. Question-to-Answer Search Direct Display From question to answer ● In Search, return answer!
  • 16. Installing ● Rpm packages or Docker images ● All nodes have the same packages/image ● CentOS (Runs on mac and win inside Docker or VirtualBox) ● 1 config variable: http://docs.vespa.ai/documentation/vespa-quick-start.html http://docs.vespa.ai/documentation/vespa-quick-start-centos.html http://docs.vespa.ai/documentation/vespa-quick-start-multinode-aws.html echo "override VESPA_CONFIGSERVERS [config-server-hostnames]" >> $VESPA_HOME/conf/vespa/default-env.txt
  • 17. ./hosts.xml Ease of Use ./services.xml <hosts> <host name="host1.domain.name"> <alias>node1</alias> </host> <host name="host2.domain.name"> <alias>node2</alias> </host> <host name="host3.domain.name"> <alias>node3</alias> </host> </hosts> <services version='1.0'> <container id='default' version='1.0'> <search/> <document-api/> <nodes> <node hostalias=”node1”/> </nodes> </container> <content id='music' version='1.0'> <redundancy>2</redundancy> <documents> <document mode='index' type='music'/> </documents> <nodes> <node hostalias=”node2” distribution-key=”1”/> <node hostalias=”node3” distribution-key=”2”/> </nodes> </content> </services>
  • 18. Application Packages ./searchdefinitions/music.sd http://docs.vespa.ai/documentation/ search-definitions.html search music { document music { field artist type string { indexing: summary | index } field album type string { indexing: summary | index } field track type string { indexing: summary | index } field popularity type int { indexing: summary | attribute attribute: fast-search } } rank-profile song inherits default { first-phase { expression { 0.7 * nativeRank(artist,album,track) + 0.3 * attribute(popularity) } } } }
  • 19. Scalability Vespa distributes data over ● A set of nodes ● With a certain replication factor ● In a set of groups Nodes or distribution (config) change > Dynamic redistribution No need to manually partition data - no shards!
  • 20. Tensors A data type in ranking expressions (in addition to double) Makes it possible to deploy large and complex ML models to Vespa Examples ● Deep neural nets ● FTRL (regression models with millions of parameters) ● Word2vec models http://docs.vespa.ai/documentation/tensor-intro.html
  • 21. What is a tensor? Tensor: A multidimensional array which can be used for computation Textual form: { {address}:double, .. } where address is {identifier:value},... Examples ● 0-dimensional: A scalar {{}:0.1} ● 1-dimensional: A vector {{x:0}:0.1, {x:1}:0.2} ● 2-dimensional: A matrix {{x:0,y:0}:0.1, {x:0,y:1}:0.2} Indexed tensor dimensions: Values addressed by numbers, continuous from 0 Mapped tensor dimensions: Values addressed by identifiers, sparse
  • 22. TensorFlow import Import machine learned ranking models trained with TensorFlow directly. Add the files to the application package, and point to the model during ranking: first-phase { expression: sum(tensorflow("my_model/saved")) } http://docs.vespa.ai/documentation/tensorflow.html