SlideShare a Scribd company logo
Big data. Real time.
The open big data serving engine: Store, search, rank and organize big data at user serving time.
Big data maturity levels
0: Latent Data is produced but not systematically leveraged
1: Analysis Data is used to inform decisions made by humans
2: Learning Data is used to learn automated decisions disconnected from direct action
3: Acting Automated data-driven decisions are made in real time
Examples: Statistics on credit card fraud are gathered to create policies for flagging fraudulent transactions.
Lists of movies popular with various user segments are compiled to inform curated recommendation lists.
Examples: Fraudulent credit card transactions are automatically flagged.
Lists of movie recommendations per user segment are automatically generated.
Examples: Fraudulent credit card transactions are automatically blocked.
Personalized movie recommendations are computed when needed by that user.
Examples: Credit card transaction data is stored for audit purposes.
Movie streaming events are logged.
Zooming in
3: Acting Automated data-driven decisions are made in real time
Examples: Fraudulent credit card transactions are automatically blocked.
Personalized movie recommendations are computed when needed by that user.
Two types
● Decisions can be made by considering a single data item: Streaming or stateless model evaluation
● Decisions are made over many data items: Big data serving
Big data serving: What is required?
Realtime actions: Find data and make inferences in tens of milliseconds.
Realtime knowledge: Handle data changes at high continuous rates.
Scalable: Handle large requests rates over big data sets.
Always available: Recover from hardware failures without human intervention.
Online evolvable: Change schemas, logic, models, hardware while online.
Integrated: Data feeds from Hadoop, learned models from TensorFlow etc.
Introducing Vespa
An open source platform for big data serving.
As Hadoop - developed at Yahoo for search, now for all big data serving cases
Recently open sourced at http://vespa.ai
Makes the big data serving features available to everyone.
Vespa at Oath/Yahoo
Oath: Flickr, Tumblr, TechCrunch, Huffington Post, Aol, Engadget, Gemini, Yahoo
News Sports Finance Mail etc.
Hundreds of Vespa applications,
… serving over a billion users,
… over 200.000 queries per second,
… over billions of content items.
A platform for low latency computations over large, evolving data sets:
● Search and selection over structured and unstructured data
● Relevance scoring: NL features, advanced ML models, TensorFlow etc.
● Query time organization and aggregation of matching data
● Real-time writes at a high sustained rate
● Live elastic and auto-recovering stateful content clusters
● Processing logic container (Java)
● Managed clusters: One to hundreds of nodes
Typical use cases: text search, personalization / recommendation / targeting,
real-time data display
Vespa is
Another use case: Zedge
The primary motivations for Zedge to use Vespa
are:
1) simplify search and recommender systems for
Zedge Android and iOS apps, both for serving
(reduce amount of custom code to maintain) and for
processing/indexing (reduce need for big data jobs
by calculating more on the fly with tensors in Vespa)
2) accelerate innovation for content discovery, e.g.
easier to improve ranking with machine learning
using Vespa in combination with Tensorflow than
with e.g. our custom code recommender systems
An added bonus so far has been that more people
understand both search and recommender systems
due to the overall reduction in complexity of search
and recommender systems.
- Zedge VP of Data, Amund Tveit
Comparisons
Vespa: Focus on big data serving: Large scale, efficient, ML models
ElasticSearch: Focus on analytics: Log ingestion, visualization etc.
Solr: Focused on enterprise search: Handling document formats etc.
Relational databases: Transactions, hard to scale, no IR, no relevance
NoSQl stores: Easier to scale, no transactions, no IR, no relevance
Hadoop/Cloudera/Hortonworks: Big Data, but not for serving
Analytics vs big data serving
Analytics Big data serving
Response time in low seconds Response time in low milliseconds
Low query rate High query rate
Time series, append only Random writes
Down time, data loss acceptable HA, no data loss, online redistribution
Massive data sets (trillions of docs) are
cheap
Massive data sets are more expensive
Analytics GUI integration Machine learning integration
Vespa and Elastic Search use cases
Big data serving Text search, relevance,
grouping and aggregation
Analytics
Vespa Elastic
search
Vespa architecture
Scalable low latency execution: How to bound latency
Container node
Query
Application
Package
Admin &
Config
Content node
Deploy
- Configuration
- Components
- ML models
Scatter-gather
Core
sharding
models models models
1) Parallelization
2) Move execution to data nodes
3) Prepared data structures (indexes etc.)
Inference in Vespa
Tensor data model: Multidimensional collections
of numbers in queries, documents, models
Tensor math express all common
machine-learned models with join, map, reduce
TensorFlow and ONNX integration: Deploy
TensorFlow and ONNX (SciKit, Caffe2, PyTorch
etc.) directly on Vespa
Vespa execution engine optimized for
repeated execution of models over many data
items, and running many inferences in parallel
Wrapping up
Making the best use of big data often implies making decisions in real time
Vespa is the only open source platform optimized for such big data serving
Available on https://vespa.ai
Quick start: Run a complete application (on a laptop or AWS) in 10 minutes:
http://docs.vespa.ai/documentation/vespa-quick-start.html
Tutorial: Make a scalable blog search and recommendation engine from scratch:
http://docs.vespa.ai/documentation/tutorials/blog-search.html

More Related Content

What's hot

Linux history & features
Linux history & featuresLinux history & features
Linux history & features
Rohit Kumar
 
Embedded Android : System Development - Part III
Embedded Android : System Development - Part IIIEmbedded Android : System Development - Part III
Embedded Android : System Development - Part III
Emertxe Information Technologies Pvt Ltd
 
Serving BERT Models in Production with TorchServe
Serving BERT Models in Production with TorchServeServing BERT Models in Production with TorchServe
Serving BERT Models in Production with TorchServe
Nidhin Pattaniyil
 
AWS 를 활용한 저지연 라이브 (Low Latency Live) 서비스 구현 - 류재춘 컨설턴트/에반젤리스트, GS Neot다 :: AW...
AWS 를 활용한 저지연 라이브 (Low Latency Live) 서비스 구현 - 류재춘 컨설턴트/에반젤리스트, GS Neot다 :: AW...AWS 를 활용한 저지연 라이브 (Low Latency Live) 서비스 구현 - 류재춘 컨설턴트/에반젤리스트, GS Neot다 :: AW...
AWS 를 활용한 저지연 라이브 (Low Latency Live) 서비스 구현 - 류재춘 컨설턴트/에반젤리스트, GS Neot다 :: AW...
Amazon Web Services Korea
 
Android Internals at Linaro Connect Asia 2013
Android Internals at Linaro Connect Asia 2013Android Internals at Linaro Connect Asia 2013
Android Internals at Linaro Connect Asia 2013
Opersys inc.
 
Ceph Block Devices: A Deep Dive
Ceph Block Devices:  A Deep DiveCeph Block Devices:  A Deep Dive
Ceph Block Devices: A Deep Dive
Red_Hat_Storage
 
SPU Shaders
SPU ShadersSPU Shaders
SPU Shaders
Slide_N
 
RISC-V Boot Process: One Step at a Time
RISC-V Boot Process: One Step at a TimeRISC-V Boot Process: One Step at a Time
RISC-V Boot Process: One Step at a Time
Atish Patra
 
Learning AOSP - Android Linux Device Driver
Learning AOSP - Android Linux Device DriverLearning AOSP - Android Linux Device Driver
Learning AOSP - Android Linux Device Driver
Nanik Tolaram
 
Monitoring and tuning your chef server - chef conf talk
Monitoring and tuning your chef server - chef conf talk Monitoring and tuning your chef server - chef conf talk
Monitoring and tuning your chef server - chef conf talk
Andrew DuFour
 
클라우드 네이티브로 가는길 - AWS 컨테이너 서비스 파헤치기 - 최진영 AWS 테크니컬 트레이너 / 배주혁 소프트웨어 엔지니어, 삼성전자...
클라우드 네이티브로 가는길 - AWS 컨테이너 서비스 파헤치기 - 최진영 AWS 테크니컬 트레이너 / 배주혁 소프트웨어 엔지니어, 삼성전자...클라우드 네이티브로 가는길 - AWS 컨테이너 서비스 파헤치기 - 최진영 AWS 테크니컬 트레이너 / 배주혁 소프트웨어 엔지니어, 삼성전자...
클라우드 네이티브로 가는길 - AWS 컨테이너 서비스 파헤치기 - 최진영 AWS 테크니컬 트레이너 / 배주혁 소프트웨어 엔지니어, 삼성전자...
Amazon Web Services Korea
 
CloudInit Introduction
CloudInit IntroductionCloudInit Introduction
CloudInit Introduction
Publicis Sapient Engineering
 
TensorFlow Lite for mobile & IoT
TensorFlow Lite for mobile & IoT   TensorFlow Lite for mobile & IoT
TensorFlow Lite for mobile & IoT
Mia Chang
 
클라우드 환경에서 알아야할 성능 이야기
클라우드 환경에서 알아야할 성능 이야기클라우드 환경에서 알아야할 성능 이야기
클라우드 환경에서 알아야할 성능 이야기
YoungSu Son
 
Android OS Porting: Introduction
Android OS Porting: IntroductionAndroid OS Porting: Introduction
Android OS Porting: Introduction
Jollen Chen
 
Jenkins CI
Jenkins CIJenkins CI
Jenkins CI
Viyaan Jhiingade
 
NiFi 시작하기
NiFi 시작하기NiFi 시작하기
NiFi 시작하기
Byunghwa Yoon
 
Kernel Recipes 2017: Using Linux perf at Netflix
Kernel Recipes 2017: Using Linux perf at NetflixKernel Recipes 2017: Using Linux perf at Netflix
Kernel Recipes 2017: Using Linux perf at Netflix
Brendan Gregg
 
백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스
백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스
백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스
NAVER D2
 
게임 운영에 필요한 로그성 데이터들에 대하여
게임 운영에 필요한 로그성 데이터들에 대하여게임 운영에 필요한 로그성 데이터들에 대하여
게임 운영에 필요한 로그성 데이터들에 대하여
iFunFactory Inc.
 

What's hot (20)

Linux history & features
Linux history & featuresLinux history & features
Linux history & features
 
Embedded Android : System Development - Part III
Embedded Android : System Development - Part IIIEmbedded Android : System Development - Part III
Embedded Android : System Development - Part III
 
Serving BERT Models in Production with TorchServe
Serving BERT Models in Production with TorchServeServing BERT Models in Production with TorchServe
Serving BERT Models in Production with TorchServe
 
AWS 를 활용한 저지연 라이브 (Low Latency Live) 서비스 구현 - 류재춘 컨설턴트/에반젤리스트, GS Neot다 :: AW...
AWS 를 활용한 저지연 라이브 (Low Latency Live) 서비스 구현 - 류재춘 컨설턴트/에반젤리스트, GS Neot다 :: AW...AWS 를 활용한 저지연 라이브 (Low Latency Live) 서비스 구현 - 류재춘 컨설턴트/에반젤리스트, GS Neot다 :: AW...
AWS 를 활용한 저지연 라이브 (Low Latency Live) 서비스 구현 - 류재춘 컨설턴트/에반젤리스트, GS Neot다 :: AW...
 
Android Internals at Linaro Connect Asia 2013
Android Internals at Linaro Connect Asia 2013Android Internals at Linaro Connect Asia 2013
Android Internals at Linaro Connect Asia 2013
 
Ceph Block Devices: A Deep Dive
Ceph Block Devices:  A Deep DiveCeph Block Devices:  A Deep Dive
Ceph Block Devices: A Deep Dive
 
SPU Shaders
SPU ShadersSPU Shaders
SPU Shaders
 
RISC-V Boot Process: One Step at a Time
RISC-V Boot Process: One Step at a TimeRISC-V Boot Process: One Step at a Time
RISC-V Boot Process: One Step at a Time
 
Learning AOSP - Android Linux Device Driver
Learning AOSP - Android Linux Device DriverLearning AOSP - Android Linux Device Driver
Learning AOSP - Android Linux Device Driver
 
Monitoring and tuning your chef server - chef conf talk
Monitoring and tuning your chef server - chef conf talk Monitoring and tuning your chef server - chef conf talk
Monitoring and tuning your chef server - chef conf talk
 
클라우드 네이티브로 가는길 - AWS 컨테이너 서비스 파헤치기 - 최진영 AWS 테크니컬 트레이너 / 배주혁 소프트웨어 엔지니어, 삼성전자...
클라우드 네이티브로 가는길 - AWS 컨테이너 서비스 파헤치기 - 최진영 AWS 테크니컬 트레이너 / 배주혁 소프트웨어 엔지니어, 삼성전자...클라우드 네이티브로 가는길 - AWS 컨테이너 서비스 파헤치기 - 최진영 AWS 테크니컬 트레이너 / 배주혁 소프트웨어 엔지니어, 삼성전자...
클라우드 네이티브로 가는길 - AWS 컨테이너 서비스 파헤치기 - 최진영 AWS 테크니컬 트레이너 / 배주혁 소프트웨어 엔지니어, 삼성전자...
 
CloudInit Introduction
CloudInit IntroductionCloudInit Introduction
CloudInit Introduction
 
TensorFlow Lite for mobile & IoT
TensorFlow Lite for mobile & IoT   TensorFlow Lite for mobile & IoT
TensorFlow Lite for mobile & IoT
 
클라우드 환경에서 알아야할 성능 이야기
클라우드 환경에서 알아야할 성능 이야기클라우드 환경에서 알아야할 성능 이야기
클라우드 환경에서 알아야할 성능 이야기
 
Android OS Porting: Introduction
Android OS Porting: IntroductionAndroid OS Porting: Introduction
Android OS Porting: Introduction
 
Jenkins CI
Jenkins CIJenkins CI
Jenkins CI
 
NiFi 시작하기
NiFi 시작하기NiFi 시작하기
NiFi 시작하기
 
Kernel Recipes 2017: Using Linux perf at Netflix
Kernel Recipes 2017: Using Linux perf at NetflixKernel Recipes 2017: Using Linux perf at Netflix
Kernel Recipes 2017: Using Linux perf at Netflix
 
백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스
백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스
백억개의 로그를 모아 검색하고 분석하고 학습도 시켜보자 : 로기스
 
게임 운영에 필요한 로그성 데이터들에 대하여
게임 운영에 필요한 로그성 데이터들에 대하여게임 운영에 필요한 로그성 데이터들에 대하여
게임 운영에 필요한 로그성 데이터들에 대하여
 

Similar to Introduction to Vespa – The Open Source Big Data Serving Engine, Jon Bratseth, Distinguished Architect, Oath

Big Data Serving with Vespa - Jon Bratseth, Distinguished Architect, Oath
Big Data Serving with Vespa - Jon Bratseth, Distinguished Architect, OathBig Data Serving with Vespa - Jon Bratseth, Distinguished Architect, Oath
Big Data Serving with Vespa - Jon Bratseth, Distinguished Architect, Oath
Yahoo Developer Network
 
Introduction Big Data
Introduction Big DataIntroduction Big Data
Introduction Big Data
Frank Kienle
 
Big Data Session 1.pptx
Big Data Session 1.pptxBig Data Session 1.pptx
Big Data Session 1.pptx
ElsonPaul2
 
Big data technologies with Case Study Finance and Healthcare
Big data technologies with Case Study Finance and HealthcareBig data technologies with Case Study Finance and Healthcare
Big data technologies with Case Study Finance and Healthcare
Sandeep Sharma IIMK Smart City,IoT,Bigdata,Cloud,BI,DW
 
No sql databases
No sql databasesNo sql databases
Big Data and Hadoop
Big Data and HadoopBig Data and Hadoop
Big Data and Hadoop
MaulikLakhani
 
Big data analytics with Apache Hadoop
Big data analytics with Apache  HadoopBig data analytics with Apache  Hadoop
Big data analytics with Apache Hadoop
Suman Saurabh
 
Big data serving: Processing and inference at scale in real time
Big data serving: Processing and inference at scale in real timeBig data serving: Processing and inference at scale in real time
Big data serving: Processing and inference at scale in real time
Itai Yaffe
 
Big data on_aws in korea by abhishek sinha (lunch and learn)
Big data on_aws in korea by abhishek sinha (lunch and learn)Big data on_aws in korea by abhishek sinha (lunch and learn)
Big data on_aws in korea by abhishek sinha (lunch and learn)
Amazon Web Services Korea
 
Lecture1 BIG DATA and Types of data in details
Lecture1 BIG DATA and Types of data in detailsLecture1 BIG DATA and Types of data in details
Lecture1 BIG DATA and Types of data in details
AbhishekKumarAgrahar2
 
Big data
Big dataBig data
Big data
Pietro Nardone
 
Big data analytics: Technology's bleeding edge
Big data analytics: Technology's bleeding edgeBig data analytics: Technology's bleeding edge
Big data analytics: Technology's bleeding edge
Bhavya Gulati
 
Big Data
Big DataBig Data
Big Data
NGDATA
 
A Gentle Introduction to Big Data
A Gentle Introduction to Big DataA Gentle Introduction to Big Data
A Gentle Introduction to Big Data
Mehmet Ali Akyol
 
bigdataintro.pptx
bigdataintro.pptxbigdataintro.pptx
bigdataintro.pptx
Albert Alex
 
Lecture 5 - Big Data and Hadoop Intro.ppt
Lecture 5 - Big Data and Hadoop Intro.pptLecture 5 - Big Data and Hadoop Intro.ppt
Lecture 5 - Big Data and Hadoop Intro.ppt
almaraniabwmalk
 
Data analytics & its Trends
Data analytics & its TrendsData analytics & its Trends
Data analytics & its Trends
Dr.K.Sreenivas Rao
 
Hadoop-based architecture approaches
Hadoop-based architecture approachesHadoop-based architecture approaches
Hadoop-based architecture approaches
Miraj Godha
 
Big data unit 2
Big data unit 2Big data unit 2
Big data unit 2
RojaT4
 
NoSQL Type, Bigdata, and Analytics
NoSQL Type, Bigdata, and AnalyticsNoSQL Type, Bigdata, and Analytics
NoSQL Type, Bigdata, and Analytics
Sandeep Sharma IIMK Smart City,IoT,Bigdata,Cloud,BI,DW
 

Similar to Introduction to Vespa – The Open Source Big Data Serving Engine, Jon Bratseth, Distinguished Architect, Oath (20)

Big Data Serving with Vespa - Jon Bratseth, Distinguished Architect, Oath
Big Data Serving with Vespa - Jon Bratseth, Distinguished Architect, OathBig Data Serving with Vespa - Jon Bratseth, Distinguished Architect, Oath
Big Data Serving with Vespa - Jon Bratseth, Distinguished Architect, Oath
 
Introduction Big Data
Introduction Big DataIntroduction Big Data
Introduction Big Data
 
Big Data Session 1.pptx
Big Data Session 1.pptxBig Data Session 1.pptx
Big Data Session 1.pptx
 
Big data technologies with Case Study Finance and Healthcare
Big data technologies with Case Study Finance and HealthcareBig data technologies with Case Study Finance and Healthcare
Big data technologies with Case Study Finance and Healthcare
 
No sql databases
No sql databasesNo sql databases
No sql databases
 
Big Data and Hadoop
Big Data and HadoopBig Data and Hadoop
Big Data and Hadoop
 
Big data analytics with Apache Hadoop
Big data analytics with Apache  HadoopBig data analytics with Apache  Hadoop
Big data analytics with Apache Hadoop
 
Big data serving: Processing and inference at scale in real time
Big data serving: Processing and inference at scale in real timeBig data serving: Processing and inference at scale in real time
Big data serving: Processing and inference at scale in real time
 
Big data on_aws in korea by abhishek sinha (lunch and learn)
Big data on_aws in korea by abhishek sinha (lunch and learn)Big data on_aws in korea by abhishek sinha (lunch and learn)
Big data on_aws in korea by abhishek sinha (lunch and learn)
 
Lecture1 BIG DATA and Types of data in details
Lecture1 BIG DATA and Types of data in detailsLecture1 BIG DATA and Types of data in details
Lecture1 BIG DATA and Types of data in details
 
Big data
Big dataBig data
Big data
 
Big data analytics: Technology's bleeding edge
Big data analytics: Technology's bleeding edgeBig data analytics: Technology's bleeding edge
Big data analytics: Technology's bleeding edge
 
Big Data
Big DataBig Data
Big Data
 
A Gentle Introduction to Big Data
A Gentle Introduction to Big DataA Gentle Introduction to Big Data
A Gentle Introduction to Big Data
 
bigdataintro.pptx
bigdataintro.pptxbigdataintro.pptx
bigdataintro.pptx
 
Lecture 5 - Big Data and Hadoop Intro.ppt
Lecture 5 - Big Data and Hadoop Intro.pptLecture 5 - Big Data and Hadoop Intro.ppt
Lecture 5 - Big Data and Hadoop Intro.ppt
 
Data analytics & its Trends
Data analytics & its TrendsData analytics & its Trends
Data analytics & its Trends
 
Hadoop-based architecture approaches
Hadoop-based architecture approachesHadoop-based architecture approaches
Hadoop-based architecture approaches
 
Big data unit 2
Big data unit 2Big data unit 2
Big data unit 2
 
NoSQL Type, Bigdata, and Analytics
NoSQL Type, Bigdata, and AnalyticsNoSQL Type, Bigdata, and Analytics
NoSQL Type, Bigdata, and Analytics
 

More from Yahoo Developer Network

Developing Mobile Apps for Performance - Swapnil Patel, Verizon Media
Developing Mobile Apps for Performance - Swapnil Patel, Verizon MediaDeveloping Mobile Apps for Performance - Swapnil Patel, Verizon Media
Developing Mobile Apps for Performance - Swapnil Patel, Verizon Media
Yahoo Developer Network
 
Athenz - The Open-Source Solution to Provide Access Control in Dynamic Infras...
Athenz - The Open-Source Solution to Provide Access Control in Dynamic Infras...Athenz - The Open-Source Solution to Provide Access Control in Dynamic Infras...
Athenz - The Open-Source Solution to Provide Access Control in Dynamic Infras...
Yahoo Developer Network
 
Athenz & SPIFFE, Tatsuya Yano, Yahoo Japan
Athenz & SPIFFE, Tatsuya Yano, Yahoo JapanAthenz & SPIFFE, Tatsuya Yano, Yahoo Japan
Athenz & SPIFFE, Tatsuya Yano, Yahoo Japan
Yahoo Developer Network
 
Athenz with Istio - Single Access Control Model in Cloud Infrastructures, Tat...
Athenz with Istio - Single Access Control Model in Cloud Infrastructures, Tat...Athenz with Istio - Single Access Control Model in Cloud Infrastructures, Tat...
Athenz with Istio - Single Access Control Model in Cloud Infrastructures, Tat...
Yahoo Developer Network
 
CICD at Oath using Screwdriver
CICD at Oath using ScrewdriverCICD at Oath using Screwdriver
CICD at Oath using Screwdriver
Yahoo Developer Network
 
How @TwitterHadoop Chose Google Cloud, Joep Rottinghuis, Lohit VijayaRenu
How @TwitterHadoop Chose Google Cloud, Joep Rottinghuis, Lohit VijayaRenuHow @TwitterHadoop Chose Google Cloud, Joep Rottinghuis, Lohit VijayaRenu
How @TwitterHadoop Chose Google Cloud, Joep Rottinghuis, Lohit VijayaRenu
Yahoo Developer Network
 
The Future of Hadoop in an AI World, Milind Bhandarkar, CEO, Ampool
The Future of Hadoop in an AI World, Milind Bhandarkar, CEO, AmpoolThe Future of Hadoop in an AI World, Milind Bhandarkar, CEO, Ampool
The Future of Hadoop in an AI World, Milind Bhandarkar, CEO, Ampool
Yahoo Developer Network
 
Apache YARN Federation and Tez at Microsoft, Anupam Upadhyay, Adrian Nicoara,...
Apache YARN Federation and Tez at Microsoft, Anupam Upadhyay, Adrian Nicoara,...Apache YARN Federation and Tez at Microsoft, Anupam Upadhyay, Adrian Nicoara,...
Apache YARN Federation and Tez at Microsoft, Anupam Upadhyay, Adrian Nicoara,...
Yahoo Developer Network
 
Containerized Services on Apache Hadoop YARN: Past, Present, and Future, Shan...
Containerized Services on Apache Hadoop YARN: Past, Present, and Future, Shan...Containerized Services on Apache Hadoop YARN: Past, Present, and Future, Shan...
Containerized Services on Apache Hadoop YARN: Past, Present, and Future, Shan...
Yahoo Developer Network
 
HDFS Scalability and Security, Daryn Sharp, Senior Engineer, Oath
HDFS Scalability and Security, Daryn Sharp, Senior Engineer, OathHDFS Scalability and Security, Daryn Sharp, Senior Engineer, Oath
HDFS Scalability and Security, Daryn Sharp, Senior Engineer, Oath
Yahoo Developer Network
 
Hadoop {Submarine} Project: Running deep learning workloads on YARN, Wangda T...
Hadoop {Submarine} Project: Running deep learning workloads on YARN, Wangda T...Hadoop {Submarine} Project: Running deep learning workloads on YARN, Wangda T...
Hadoop {Submarine} Project: Running deep learning workloads on YARN, Wangda T...
Yahoo Developer Network
 
Moving the Oath Grid to Docker, Eric Badger, Oath
Moving the Oath Grid to Docker, Eric Badger, OathMoving the Oath Grid to Docker, Eric Badger, Oath
Moving the Oath Grid to Docker, Eric Badger, Oath
Yahoo Developer Network
 
Architecting Petabyte Scale AI Applications
Architecting Petabyte Scale AI ApplicationsArchitecting Petabyte Scale AI Applications
Architecting Petabyte Scale AI Applications
Yahoo Developer Network
 
Jun 2017 HUG: YARN Scheduling – A Step Beyond
Jun 2017 HUG: YARN Scheduling – A Step BeyondJun 2017 HUG: YARN Scheduling – A Step Beyond
Jun 2017 HUG: YARN Scheduling – A Step Beyond
Yahoo Developer Network
 
Jun 2017 HUG: Large-Scale Machine Learning: Use Cases and Technologies
Jun 2017 HUG: Large-Scale Machine Learning: Use Cases and Technologies Jun 2017 HUG: Large-Scale Machine Learning: Use Cases and Technologies
Jun 2017 HUG: Large-Scale Machine Learning: Use Cases and Technologies
Yahoo Developer Network
 
February 2017 HUG: Slow, Stuck, or Runaway Apps? Learn How to Quickly Fix Pro...
February 2017 HUG: Slow, Stuck, or Runaway Apps? Learn How to Quickly Fix Pro...February 2017 HUG: Slow, Stuck, or Runaway Apps? Learn How to Quickly Fix Pro...
February 2017 HUG: Slow, Stuck, or Runaway Apps? Learn How to Quickly Fix Pro...
Yahoo Developer Network
 
February 2017 HUG: Exactly-once end-to-end processing with Apache Apex
February 2017 HUG: Exactly-once end-to-end processing with Apache ApexFebruary 2017 HUG: Exactly-once end-to-end processing with Apache Apex
February 2017 HUG: Exactly-once end-to-end processing with Apache Apex
Yahoo Developer Network
 
February 2017 HUG: Data Sketches: A required toolkit for Big Data Analytics
February 2017 HUG: Data Sketches: A required toolkit for Big Data AnalyticsFebruary 2017 HUG: Data Sketches: A required toolkit for Big Data Analytics
February 2017 HUG: Data Sketches: A required toolkit for Big Data Analytics
Yahoo Developer Network
 
October 2016 HUG: Pulsar,  a highly scalable, low latency pub-sub messaging s...
October 2016 HUG: Pulsar,  a highly scalable, low latency pub-sub messaging s...October 2016 HUG: Pulsar,  a highly scalable, low latency pub-sub messaging s...
October 2016 HUG: Pulsar,  a highly scalable, low latency pub-sub messaging s...
Yahoo Developer Network
 
October 2016 HUG: Architecture of an Open Source RDBMS powered by HBase and ...
October 2016 HUG: Architecture of an Open Source RDBMS powered by HBase and ...October 2016 HUG: Architecture of an Open Source RDBMS powered by HBase and ...
October 2016 HUG: Architecture of an Open Source RDBMS powered by HBase and ...
Yahoo Developer Network
 

More from Yahoo Developer Network (20)

Developing Mobile Apps for Performance - Swapnil Patel, Verizon Media
Developing Mobile Apps for Performance - Swapnil Patel, Verizon MediaDeveloping Mobile Apps for Performance - Swapnil Patel, Verizon Media
Developing Mobile Apps for Performance - Swapnil Patel, Verizon Media
 
Athenz - The Open-Source Solution to Provide Access Control in Dynamic Infras...
Athenz - The Open-Source Solution to Provide Access Control in Dynamic Infras...Athenz - The Open-Source Solution to Provide Access Control in Dynamic Infras...
Athenz - The Open-Source Solution to Provide Access Control in Dynamic Infras...
 
Athenz & SPIFFE, Tatsuya Yano, Yahoo Japan
Athenz & SPIFFE, Tatsuya Yano, Yahoo JapanAthenz & SPIFFE, Tatsuya Yano, Yahoo Japan
Athenz & SPIFFE, Tatsuya Yano, Yahoo Japan
 
Athenz with Istio - Single Access Control Model in Cloud Infrastructures, Tat...
Athenz with Istio - Single Access Control Model in Cloud Infrastructures, Tat...Athenz with Istio - Single Access Control Model in Cloud Infrastructures, Tat...
Athenz with Istio - Single Access Control Model in Cloud Infrastructures, Tat...
 
CICD at Oath using Screwdriver
CICD at Oath using ScrewdriverCICD at Oath using Screwdriver
CICD at Oath using Screwdriver
 
How @TwitterHadoop Chose Google Cloud, Joep Rottinghuis, Lohit VijayaRenu
How @TwitterHadoop Chose Google Cloud, Joep Rottinghuis, Lohit VijayaRenuHow @TwitterHadoop Chose Google Cloud, Joep Rottinghuis, Lohit VijayaRenu
How @TwitterHadoop Chose Google Cloud, Joep Rottinghuis, Lohit VijayaRenu
 
The Future of Hadoop in an AI World, Milind Bhandarkar, CEO, Ampool
The Future of Hadoop in an AI World, Milind Bhandarkar, CEO, AmpoolThe Future of Hadoop in an AI World, Milind Bhandarkar, CEO, Ampool
The Future of Hadoop in an AI World, Milind Bhandarkar, CEO, Ampool
 
Apache YARN Federation and Tez at Microsoft, Anupam Upadhyay, Adrian Nicoara,...
Apache YARN Federation and Tez at Microsoft, Anupam Upadhyay, Adrian Nicoara,...Apache YARN Federation and Tez at Microsoft, Anupam Upadhyay, Adrian Nicoara,...
Apache YARN Federation and Tez at Microsoft, Anupam Upadhyay, Adrian Nicoara,...
 
Containerized Services on Apache Hadoop YARN: Past, Present, and Future, Shan...
Containerized Services on Apache Hadoop YARN: Past, Present, and Future, Shan...Containerized Services on Apache Hadoop YARN: Past, Present, and Future, Shan...
Containerized Services on Apache Hadoop YARN: Past, Present, and Future, Shan...
 
HDFS Scalability and Security, Daryn Sharp, Senior Engineer, Oath
HDFS Scalability and Security, Daryn Sharp, Senior Engineer, OathHDFS Scalability and Security, Daryn Sharp, Senior Engineer, Oath
HDFS Scalability and Security, Daryn Sharp, Senior Engineer, Oath
 
Hadoop {Submarine} Project: Running deep learning workloads on YARN, Wangda T...
Hadoop {Submarine} Project: Running deep learning workloads on YARN, Wangda T...Hadoop {Submarine} Project: Running deep learning workloads on YARN, Wangda T...
Hadoop {Submarine} Project: Running deep learning workloads on YARN, Wangda T...
 
Moving the Oath Grid to Docker, Eric Badger, Oath
Moving the Oath Grid to Docker, Eric Badger, OathMoving the Oath Grid to Docker, Eric Badger, Oath
Moving the Oath Grid to Docker, Eric Badger, Oath
 
Architecting Petabyte Scale AI Applications
Architecting Petabyte Scale AI ApplicationsArchitecting Petabyte Scale AI Applications
Architecting Petabyte Scale AI Applications
 
Jun 2017 HUG: YARN Scheduling – A Step Beyond
Jun 2017 HUG: YARN Scheduling – A Step BeyondJun 2017 HUG: YARN Scheduling – A Step Beyond
Jun 2017 HUG: YARN Scheduling – A Step Beyond
 
Jun 2017 HUG: Large-Scale Machine Learning: Use Cases and Technologies
Jun 2017 HUG: Large-Scale Machine Learning: Use Cases and Technologies Jun 2017 HUG: Large-Scale Machine Learning: Use Cases and Technologies
Jun 2017 HUG: Large-Scale Machine Learning: Use Cases and Technologies
 
February 2017 HUG: Slow, Stuck, or Runaway Apps? Learn How to Quickly Fix Pro...
February 2017 HUG: Slow, Stuck, or Runaway Apps? Learn How to Quickly Fix Pro...February 2017 HUG: Slow, Stuck, or Runaway Apps? Learn How to Quickly Fix Pro...
February 2017 HUG: Slow, Stuck, or Runaway Apps? Learn How to Quickly Fix Pro...
 
February 2017 HUG: Exactly-once end-to-end processing with Apache Apex
February 2017 HUG: Exactly-once end-to-end processing with Apache ApexFebruary 2017 HUG: Exactly-once end-to-end processing with Apache Apex
February 2017 HUG: Exactly-once end-to-end processing with Apache Apex
 
February 2017 HUG: Data Sketches: A required toolkit for Big Data Analytics
February 2017 HUG: Data Sketches: A required toolkit for Big Data AnalyticsFebruary 2017 HUG: Data Sketches: A required toolkit for Big Data Analytics
February 2017 HUG: Data Sketches: A required toolkit for Big Data Analytics
 
October 2016 HUG: Pulsar,  a highly scalable, low latency pub-sub messaging s...
October 2016 HUG: Pulsar,  a highly scalable, low latency pub-sub messaging s...October 2016 HUG: Pulsar,  a highly scalable, low latency pub-sub messaging s...
October 2016 HUG: Pulsar,  a highly scalable, low latency pub-sub messaging s...
 
October 2016 HUG: Architecture of an Open Source RDBMS powered by HBase and ...
October 2016 HUG: Architecture of an Open Source RDBMS powered by HBase and ...October 2016 HUG: Architecture of an Open Source RDBMS powered by HBase and ...
October 2016 HUG: Architecture of an Open Source RDBMS powered by HBase and ...
 

Recently uploaded

Discovery Series - Zero to Hero - Task Mining Session 1
Discovery Series - Zero to Hero - Task Mining Session 1Discovery Series - Zero to Hero - Task Mining Session 1
Discovery Series - Zero to Hero - Task Mining Session 1
DianaGray10
 
Acumatica vs. Sage Intacct _Construction_July (1).pptx
Acumatica vs. Sage Intacct _Construction_July (1).pptxAcumatica vs. Sage Intacct _Construction_July (1).pptx
Acumatica vs. Sage Intacct _Construction_July (1).pptx
BrainSell Technologies
 
Semantic-Aware Code Model: Elevating the Future of Software Development
Semantic-Aware Code Model: Elevating the Future of Software DevelopmentSemantic-Aware Code Model: Elevating the Future of Software Development
Semantic-Aware Code Model: Elevating the Future of Software Development
Baishakhi Ray
 
Camunda Chapter NY Meetup July 2024.pptx
Camunda Chapter NY Meetup July 2024.pptxCamunda Chapter NY Meetup July 2024.pptx
Camunda Chapter NY Meetup July 2024.pptx
ZachWylie3
 
Improving Learning Content Efficiency with Reusable Learning Content
Improving Learning Content Efficiency with Reusable Learning ContentImproving Learning Content Efficiency with Reusable Learning Content
Improving Learning Content Efficiency with Reusable Learning Content
Enterprise Knowledge
 
Intel Unveils Core Ultra 200V Lunar chip .pdf
Intel Unveils Core Ultra 200V Lunar chip .pdfIntel Unveils Core Ultra 200V Lunar chip .pdf
Intel Unveils Core Ultra 200V Lunar chip .pdf
Tech Guru
 
Generative AI Reasoning Tech Talk - July 2024
Generative AI Reasoning Tech Talk - July 2024Generative AI Reasoning Tech Talk - July 2024
Generative AI Reasoning Tech Talk - July 2024
siddu769252
 
LeadMagnet IQ Review: Unlock the Secret to Effortless Traffic and Leads.pdf
LeadMagnet IQ Review:  Unlock the Secret to Effortless Traffic and Leads.pdfLeadMagnet IQ Review:  Unlock the Secret to Effortless Traffic and Leads.pdf
LeadMagnet IQ Review: Unlock the Secret to Effortless Traffic and Leads.pdf
SelfMade bd
 
UX Webinar Series: Drive Revenue and Decrease Costs with Passkeys for Consume...
UX Webinar Series: Drive Revenue and Decrease Costs with Passkeys for Consume...UX Webinar Series: Drive Revenue and Decrease Costs with Passkeys for Consume...
UX Webinar Series: Drive Revenue and Decrease Costs with Passkeys for Consume...
FIDO Alliance
 
Latest Tech Trends Series 2024 By EY India
Latest Tech Trends Series 2024 By EY IndiaLatest Tech Trends Series 2024 By EY India
Latest Tech Trends Series 2024 By EY India
EYIndia1
 
Choosing the Best Outlook OST to PST Converter: Key Features and Considerations
Choosing the Best Outlook OST to PST Converter: Key Features and ConsiderationsChoosing the Best Outlook OST to PST Converter: Key Features and Considerations
Choosing the Best Outlook OST to PST Converter: Key Features and Considerations
webbyacad software
 
Uncharted Together- Navigating AI's New Frontiers in Libraries
Uncharted Together- Navigating AI's New Frontiers in LibrariesUncharted Together- Navigating AI's New Frontiers in Libraries
Uncharted Together- Navigating AI's New Frontiers in Libraries
Brian Pichman
 
Redefining Cybersecurity with AI Capabilities
Redefining Cybersecurity with AI CapabilitiesRedefining Cybersecurity with AI Capabilities
Redefining Cybersecurity with AI Capabilities
Priyanka Aash
 
Required Documents for ISO 17021 Certification.PPT
Required Documents for ISO 17021 Certification.PPTRequired Documents for ISO 17021 Certification.PPT
Required Documents for ISO 17021 Certification.PPT
mithun772
 
The Path to General-Purpose Robots - Coatue
The Path to General-Purpose Robots - CoatueThe Path to General-Purpose Robots - Coatue
The Path to General-Purpose Robots - Coatue
Razin Mustafiz
 
Types of Weaving loom machine & it's technology
Types of Weaving loom machine & it's technologyTypes of Weaving loom machine & it's technology
Types of Weaving loom machine & it's technology
ldtexsolbl
 
kk vathada _digital transformation frameworks_2024.pdf
kk vathada _digital transformation frameworks_2024.pdfkk vathada _digital transformation frameworks_2024.pdf
kk vathada _digital transformation frameworks_2024.pdf
KIRAN KV
 
It's your unstructured data: How to get your GenAI app to production (and spe...
It's your unstructured data: How to get your GenAI app to production (and spe...It's your unstructured data: How to get your GenAI app to production (and spe...
It's your unstructured data: How to get your GenAI app to production (and spe...
Zilliz
 
Integrating Kafka with MuleSoft 4 and usecase
Integrating Kafka with MuleSoft 4 and usecaseIntegrating Kafka with MuleSoft 4 and usecase
Integrating Kafka with MuleSoft 4 and usecase
shyamraj55
 
Mastering OnlyFans Clone App Development: Key Strategies for Success
Mastering OnlyFans Clone App Development: Key Strategies for SuccessMastering OnlyFans Clone App Development: Key Strategies for Success
Mastering OnlyFans Clone App Development: Key Strategies for Success
David Wilson
 

Recently uploaded (20)

Discovery Series - Zero to Hero - Task Mining Session 1
Discovery Series - Zero to Hero - Task Mining Session 1Discovery Series - Zero to Hero - Task Mining Session 1
Discovery Series - Zero to Hero - Task Mining Session 1
 
Acumatica vs. Sage Intacct _Construction_July (1).pptx
Acumatica vs. Sage Intacct _Construction_July (1).pptxAcumatica vs. Sage Intacct _Construction_July (1).pptx
Acumatica vs. Sage Intacct _Construction_July (1).pptx
 
Semantic-Aware Code Model: Elevating the Future of Software Development
Semantic-Aware Code Model: Elevating the Future of Software DevelopmentSemantic-Aware Code Model: Elevating the Future of Software Development
Semantic-Aware Code Model: Elevating the Future of Software Development
 
Camunda Chapter NY Meetup July 2024.pptx
Camunda Chapter NY Meetup July 2024.pptxCamunda Chapter NY Meetup July 2024.pptx
Camunda Chapter NY Meetup July 2024.pptx
 
Improving Learning Content Efficiency with Reusable Learning Content
Improving Learning Content Efficiency with Reusable Learning ContentImproving Learning Content Efficiency with Reusable Learning Content
Improving Learning Content Efficiency with Reusable Learning Content
 
Intel Unveils Core Ultra 200V Lunar chip .pdf
Intel Unveils Core Ultra 200V Lunar chip .pdfIntel Unveils Core Ultra 200V Lunar chip .pdf
Intel Unveils Core Ultra 200V Lunar chip .pdf
 
Generative AI Reasoning Tech Talk - July 2024
Generative AI Reasoning Tech Talk - July 2024Generative AI Reasoning Tech Talk - July 2024
Generative AI Reasoning Tech Talk - July 2024
 
LeadMagnet IQ Review: Unlock the Secret to Effortless Traffic and Leads.pdf
LeadMagnet IQ Review:  Unlock the Secret to Effortless Traffic and Leads.pdfLeadMagnet IQ Review:  Unlock the Secret to Effortless Traffic and Leads.pdf
LeadMagnet IQ Review: Unlock the Secret to Effortless Traffic and Leads.pdf
 
UX Webinar Series: Drive Revenue and Decrease Costs with Passkeys for Consume...
UX Webinar Series: Drive Revenue and Decrease Costs with Passkeys for Consume...UX Webinar Series: Drive Revenue and Decrease Costs with Passkeys for Consume...
UX Webinar Series: Drive Revenue and Decrease Costs with Passkeys for Consume...
 
Latest Tech Trends Series 2024 By EY India
Latest Tech Trends Series 2024 By EY IndiaLatest Tech Trends Series 2024 By EY India
Latest Tech Trends Series 2024 By EY India
 
Choosing the Best Outlook OST to PST Converter: Key Features and Considerations
Choosing the Best Outlook OST to PST Converter: Key Features and ConsiderationsChoosing the Best Outlook OST to PST Converter: Key Features and Considerations
Choosing the Best Outlook OST to PST Converter: Key Features and Considerations
 
Uncharted Together- Navigating AI's New Frontiers in Libraries
Uncharted Together- Navigating AI's New Frontiers in LibrariesUncharted Together- Navigating AI's New Frontiers in Libraries
Uncharted Together- Navigating AI's New Frontiers in Libraries
 
Redefining Cybersecurity with AI Capabilities
Redefining Cybersecurity with AI CapabilitiesRedefining Cybersecurity with AI Capabilities
Redefining Cybersecurity with AI Capabilities
 
Required Documents for ISO 17021 Certification.PPT
Required Documents for ISO 17021 Certification.PPTRequired Documents for ISO 17021 Certification.PPT
Required Documents for ISO 17021 Certification.PPT
 
The Path to General-Purpose Robots - Coatue
The Path to General-Purpose Robots - CoatueThe Path to General-Purpose Robots - Coatue
The Path to General-Purpose Robots - Coatue
 
Types of Weaving loom machine & it's technology
Types of Weaving loom machine & it's technologyTypes of Weaving loom machine & it's technology
Types of Weaving loom machine & it's technology
 
kk vathada _digital transformation frameworks_2024.pdf
kk vathada _digital transformation frameworks_2024.pdfkk vathada _digital transformation frameworks_2024.pdf
kk vathada _digital transformation frameworks_2024.pdf
 
It's your unstructured data: How to get your GenAI app to production (and spe...
It's your unstructured data: How to get your GenAI app to production (and spe...It's your unstructured data: How to get your GenAI app to production (and spe...
It's your unstructured data: How to get your GenAI app to production (and spe...
 
Integrating Kafka with MuleSoft 4 and usecase
Integrating Kafka with MuleSoft 4 and usecaseIntegrating Kafka with MuleSoft 4 and usecase
Integrating Kafka with MuleSoft 4 and usecase
 
Mastering OnlyFans Clone App Development: Key Strategies for Success
Mastering OnlyFans Clone App Development: Key Strategies for SuccessMastering OnlyFans Clone App Development: Key Strategies for Success
Mastering OnlyFans Clone App Development: Key Strategies for Success
 

Introduction to Vespa – The Open Source Big Data Serving Engine, Jon Bratseth, Distinguished Architect, Oath

  • 1. Big data. Real time. The open big data serving engine: Store, search, rank and organize big data at user serving time.
  • 2. Big data maturity levels 0: Latent Data is produced but not systematically leveraged 1: Analysis Data is used to inform decisions made by humans 2: Learning Data is used to learn automated decisions disconnected from direct action 3: Acting Automated data-driven decisions are made in real time Examples: Statistics on credit card fraud are gathered to create policies for flagging fraudulent transactions. Lists of movies popular with various user segments are compiled to inform curated recommendation lists. Examples: Fraudulent credit card transactions are automatically flagged. Lists of movie recommendations per user segment are automatically generated. Examples: Fraudulent credit card transactions are automatically blocked. Personalized movie recommendations are computed when needed by that user. Examples: Credit card transaction data is stored for audit purposes. Movie streaming events are logged.
  • 3. Zooming in 3: Acting Automated data-driven decisions are made in real time Examples: Fraudulent credit card transactions are automatically blocked. Personalized movie recommendations are computed when needed by that user. Two types ● Decisions can be made by considering a single data item: Streaming or stateless model evaluation ● Decisions are made over many data items: Big data serving
  • 4. Big data serving: What is required? Realtime actions: Find data and make inferences in tens of milliseconds. Realtime knowledge: Handle data changes at high continuous rates. Scalable: Handle large requests rates over big data sets. Always available: Recover from hardware failures without human intervention. Online evolvable: Change schemas, logic, models, hardware while online. Integrated: Data feeds from Hadoop, learned models from TensorFlow etc.
  • 5. Introducing Vespa An open source platform for big data serving. As Hadoop - developed at Yahoo for search, now for all big data serving cases Recently open sourced at http://vespa.ai Makes the big data serving features available to everyone.
  • 6. Vespa at Oath/Yahoo Oath: Flickr, Tumblr, TechCrunch, Huffington Post, Aol, Engadget, Gemini, Yahoo News Sports Finance Mail etc. Hundreds of Vespa applications, … serving over a billion users, … over 200.000 queries per second, … over billions of content items.
  • 7. A platform for low latency computations over large, evolving data sets: ● Search and selection over structured and unstructured data ● Relevance scoring: NL features, advanced ML models, TensorFlow etc. ● Query time organization and aggregation of matching data ● Real-time writes at a high sustained rate ● Live elastic and auto-recovering stateful content clusters ● Processing logic container (Java) ● Managed clusters: One to hundreds of nodes Typical use cases: text search, personalization / recommendation / targeting, real-time data display Vespa is
  • 8. Another use case: Zedge The primary motivations for Zedge to use Vespa are: 1) simplify search and recommender systems for Zedge Android and iOS apps, both for serving (reduce amount of custom code to maintain) and for processing/indexing (reduce need for big data jobs by calculating more on the fly with tensors in Vespa) 2) accelerate innovation for content discovery, e.g. easier to improve ranking with machine learning using Vespa in combination with Tensorflow than with e.g. our custom code recommender systems An added bonus so far has been that more people understand both search and recommender systems due to the overall reduction in complexity of search and recommender systems. - Zedge VP of Data, Amund Tveit
  • 9. Comparisons Vespa: Focus on big data serving: Large scale, efficient, ML models ElasticSearch: Focus on analytics: Log ingestion, visualization etc. Solr: Focused on enterprise search: Handling document formats etc. Relational databases: Transactions, hard to scale, no IR, no relevance NoSQl stores: Easier to scale, no transactions, no IR, no relevance Hadoop/Cloudera/Hortonworks: Big Data, but not for serving
  • 10. Analytics vs big data serving Analytics Big data serving Response time in low seconds Response time in low milliseconds Low query rate High query rate Time series, append only Random writes Down time, data loss acceptable HA, no data loss, online redistribution Massive data sets (trillions of docs) are cheap Massive data sets are more expensive Analytics GUI integration Machine learning integration
  • 11. Vespa and Elastic Search use cases Big data serving Text search, relevance, grouping and aggregation Analytics Vespa Elastic search
  • 13. Scalable low latency execution: How to bound latency Container node Query Application Package Admin & Config Content node Deploy - Configuration - Components - ML models Scatter-gather Core sharding models models models 1) Parallelization 2) Move execution to data nodes 3) Prepared data structures (indexes etc.)
  • 14. Inference in Vespa Tensor data model: Multidimensional collections of numbers in queries, documents, models Tensor math express all common machine-learned models with join, map, reduce TensorFlow and ONNX integration: Deploy TensorFlow and ONNX (SciKit, Caffe2, PyTorch etc.) directly on Vespa Vespa execution engine optimized for repeated execution of models over many data items, and running many inferences in parallel
  • 15. Wrapping up Making the best use of big data often implies making decisions in real time Vespa is the only open source platform optimized for such big data serving Available on https://vespa.ai Quick start: Run a complete application (on a laptop or AWS) in 10 minutes: http://docs.vespa.ai/documentation/vespa-quick-start.html Tutorial: Make a scalable blog search and recommendation engine from scratch: http://docs.vespa.ai/documentation/tutorials/blog-search.html