| <!doctype html><html lang=en class=no-js><head><meta charset=utf-8><meta http-equiv=x-ua-compatible content="IE=edge"><meta name=viewport content="width=device-width,initial-scale=1"><title>Cross Language RunInference</title><meta name=description content="Apache Beam is an open source, unified model and set of language-specific SDKs for defining and executing data processing workflows, and also data ingestion and integration flows, supporting Enterprise Integration Patterns (EIPs) and Domain Specific Languages (DSLs). Dataflow pipelines simplify the mechanics of large-scale batch and streaming data processing and can run on a number of runtimes like Apache Flink, Apache Spark, and Google Cloud Dataflow (a cloud service). Beam also brings DSL in different languages, allowing users to easily implement their data integration processes."><link href="https://fonts.googleapis.com/css?family=Roboto:100,300,400,500,700" rel=stylesheet><link rel=preload href=/scss/main.min.408fddfe3e8a45f87a5a8c9a839d77db667c1c534e5e5cd0d957ffc3dd6c14cf.css as=style><link href=/scss/main.min.408fddfe3e8a45f87a5a8c9a839d77db667c1c534e5e5cd0d957ffc3dd6c14cf.css rel=stylesheet integrity><script src=https://code.jquery.com/jquery-2.2.4.min.js></script><style>.body__contained img{max-width:100%}</style><script type=text/javascript src=/js/bootstrap.min.2979f9a6e32fc42c3e7406339ee9fe76b31d1b52059776a02b4a7fa6a4fd280a.js defer></script> |
| <script type=text/javascript src=/js/language-switch-v2.min.121952b7980b920320ab229551857669209945e39b05ba2b433a565385ca44c6.js defer></script> |
| <script type=text/javascript src=/js/fix-menu.min.039174b67107465f2090a493f91e126f7aa797f29420f9edab8a54d9dd4b3d2d.js defer></script> |
| <script type=text/javascript src=/js/section-nav.min.1405fd5e70fab5f6c54037c269b1d137487d8f3d1b3009032525f6db3fbce991.js defer></script> |
| <script type=text/javascript src=/js/page-nav.min.af231204c9c52c5089d53a4c02739eacbb7f939e3be1c6ffcc212e0ac4dbf879.js defer></script> |
| <script type=text/javascript src=/js/expandable-list.min.75a4526624a3b8898fe7fb9e3428c205b581f8b38c7926922467aef17eac69f2.js defer></script> |
| <script type=text/javascript src=/js/copy-to-clipboard.min.364c06423d7e8993fc42bb4abc38c03195bc8386db26d18774ce775d08d5b18d.js defer></script> |
| <script type=text/javascript src=/js/calendar.min.336664054fa0f52b08bbd4e3c59b5cb6d63dcfb2b4d602839746516b0817446b.js defer></script> |
| <script type=text/javascript src=/js/fix-playground-nested-scroll.min.0283f1037cb1b9d5074c6eaf041292b524a8148a7cdb803d5ccd6d1fc4eb3253.js defer></script> |
| <script type=text/javascript src=/js/anchor-content-jump-fix.min.22d3240f81632e4c11179b9d2aaf37a40da9414333c43aa97344e8b21a7df0e4.js defer></script> |
| <link rel=alternate type=application/rss+xml title="Apache Beam" href=/feed.xml><link rel=canonical href=/documentation/ml/multi-language-inference/ data-proofer-ignore><link rel="shortcut icon" type=image/x-icon href=/images/favicon.ico><link rel=stylesheet href=https://use.fontawesome.com/releases/v5.4.1/css/all.css integrity=sha384-5sAR7xN1Nv6T6+dT2mhtzEpVJvfS3NScPQTrOxhwjIuvcA67KV2R5Jz6kr4abQsz crossorigin=anonymous><link rel=stylesheet href=https://unpkg.com/swiper@8/swiper-bundle.min.css><script async src=https://platform.twitter.com/widgets.js></script> |
| <script>(function(e,t,n,s,o,i,a){e.GoogleAnalyticsObject=o,e[o]=e[o]||function(){(e[o].q=e[o].q||[]).push(arguments)},e[o].l=1*new Date,i=t.createElement(n),a=t.getElementsByTagName(n)[0],i.async=1,i.src=s,a.parentNode.insertBefore(i,a)})(window,document,"script","//www.google-analytics.com/analytics.js","ga"),ga("create","UA-73650088-1","auto"),ga("send","pageview")</script><script>(function(e,t,n,s,o,i){e.hj=e.hj||function(){(e.hj.q=e.hj.q||[]).push(arguments)},e._hjSettings={hjid:2182187,hjsv:6},o=t.getElementsByTagName("head")[0],i=t.createElement("script"),i.async=1,i.src=n+e._hjSettings.hjid+s+e._hjSettings.hjsv,o.appendChild(i)})(window,document,"https://static.hotjar.com/c/hotjar-",".js?sv=")</script></head><body class=body data-spy=scroll data-target=.page-nav data-offset=0><nav class="navigation-bar-mobile header navbar navbar-fixed-top"><div class=navbar-header><a href=/ class=navbar-brand><img alt=Brand style=height:46px;width:43px src=/images/beam_logo_navbar_mobile.png></a> |
| <a class=navbar-link href=/get-started/>Get Started</a> |
| <a class=navbar-link href=/documentation/>Documentation</a> |
| <button type=button class="navbar-toggle menu-open" aria-expanded=false aria-controls=navbar onclick=openMenu()> |
| <span class=sr-only>Toggle navigation</span> |
| <span class=icon-bar></span> |
| <span class=icon-bar></span> |
| <span class=icon-bar></span></button></div><div class="navbar-mask closed"></div><div id=navbar class="navbar-container closed"><button type=button class=navbar-toggle aria-expanded=false aria-controls=navbar id=closeMenu> |
| <span class=sr-only>Toggle navigation</span> |
| <span class=icon-bar></span> |
| <span class=icon-bar></span> |
| <span class=icon-bar></span></button><ul class="nav navbar-nav"><li><div class=searchBar-mobile><script>(function(){var t,n="012923275103528129024:4emlchv9wzi",e=document.createElement("script");e.type="text/javascript",e.async=!0,e.src="https://cse.google.com/cse.js?cx="+n,t=document.getElementsByTagName("script")[0],t.parentNode.insertBefore(e,t)})()</script><gcse:search></gcse:search></div></li><li><a class=navbar-link href=/about>About</a></li><li><a class=navbar-link href=/get-started/>Get Started</a></li><li><span class=navbar-link>Documentation</span><ul><li><a href=/documentation/>General</a></li><li><a href=/documentation/sdks/java/>Languages</a></li><li><a href=/documentation/runners/capability-matrix/>Runners</a></li><li><a href=/documentation/io/connectors/>I/O Connectors</a></li></ul></li><li><a class=navbar-link href=/roadmap/>Roadmap</a></li><li><a class=navbar-link href=/community/>Community</a></li><li><a class=navbar-link href=/contribute/>Contribute</a></li><li><a class=navbar-link href=/blog/>Blog</a></li><li><a class=navbar-link href=/case-studies/>Case Studies</a></li></ul><ul class="nav navbar-nav navbar-right"><li><a href=https://github.com/apache/beam/edit/master/website/www/site/content/en/documentation/ml/multi-language-inference.md data-proofer-ignore><svg xmlns="http://www.w3.org/2000/svg" width="25" height="24" fill="none" viewBox="0 0 25 24"><path stroke="#ff6d00" stroke-linecap="round" stroke-linejoin="round" stroke-width="2.75" d="M4.543 20h4l10.5-10.5c.53-.53.828-1.25.828-2s-.298-1.47-.828-2-1.25-.828-2-.828-1.47.298-2 .828L4.543 16v4zm9.5-13.5 4 4"/></svg></a></li><li class=dropdown><a href=# class=dropdown-toggle id=apache-dropdown data-toggle=dropdown role=button aria-haspopup=true aria-expanded=false><img src=https://www.apache.org/foundation/press/kit/feather_small.png alt="Apache Logo" style=height:20px> |
| Apache |
| <span class=arrow-icon><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="none" viewBox="0 0 20 20"><circle cx="10" cy="10" r="10" fill="#ff6d00"/><path stroke="#fff" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M8.535 5.28l4.573 4.818-4.573 4.403"/></svg></span></a><ul class="dropdown-menu dropdown-menu-right"><li><a target=_blank href=https://www.apache.org/>ASF Homepage</a></li><li><a target=_blank href=https://www.apache.org/licenses/>License</a></li><li><a target=_blank href=https://www.apache.org/security/>Security</a></li><li><a target=_blank href=https://www.apache.org/foundation/thanks.html>Thanks</a></li><li><a target=_blank href=https://www.apache.org/foundation/sponsorship.html>Sponsorship</a></li><li><a target=_blank href=https://www.apache.org/foundation/policies/conduct>Code of Conduct</a></li></ul></li></ul></div></nav><nav class=navigation-bar-desktop><a href=/ class=navbar-logo><img src=/images/beam_logo_navbar.png alt="Beam Logo"></a><div class=navbar-bar-left><div class=navbar-links><a class=navbar-link href=/about>About</a> |
| <a class=navbar-link href=/get-started/>Get Started</a><li class="dropdown navbar-dropdown navbar-dropdown-documentation"><a href=# class="dropdown-toggle navbar-link" role=button aria-haspopup=true aria-expanded=false>Documentation |
| <span><svg xmlns="http://www.w3.org/2000/svg" width="12" height="11" fill="none" viewBox="0 0 12 11"><path stroke="#ff6d00" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M10.666 4.535 5.847 9.108 1.444 4.535"/></svg></span></a><ul class=dropdown-menu><li><a class=navbar-dropdown-menu-link href=/documentation/>General</a></li><li><a class=navbar-dropdown-menu-link href=/documentation/sdks/java/>Languages</a></li><li><a class=navbar-dropdown-menu-link href=/documentation/runners/capability-matrix/>Runners</a></li><li><a class=navbar-dropdown-menu-link href=/documentation/io/connectors/>I/O Connectors</a></li></ul></li><a class=navbar-link href=/roadmap/>Roadmap</a> |
| <a class=navbar-link href=/community/>Community</a> |
| <a class=navbar-link href=/contribute/>Contribute</a> |
| <a class=navbar-link href=/blog/>Blog</a> |
| <a class=navbar-link href=/case-studies/>Case Studies</a></div><div id=iconsBar><a type=button onclick=showSearch()><svg xmlns="http://www.w3.org/2000/svg" width="25" height="24" fill="none" viewBox="0 0 25 24"><path stroke="#ff6d00" stroke-linecap="round" stroke-linejoin="round" stroke-width="2.75" d="M10.191 17c3.866.0 7-3.134 7-7s-3.134-7-7-7-7 3.134-7 7 3.134 7 7 7zm11 4-6-6"/></svg></a><a target=_blank href=https://github.com/apache/beam/edit/master/website/www/site/content/en/documentation/ml/multi-language-inference.md data-proofer-ignore><svg xmlns="http://www.w3.org/2000/svg" width="25" height="24" fill="none" viewBox="0 0 25 24"><path stroke="#ff6d00" stroke-linecap="round" stroke-linejoin="round" stroke-width="2.75" d="M4.543 20h4l10.5-10.5c.53-.53.828-1.25.828-2s-.298-1.47-.828-2-1.25-.828-2-.828-1.47.298-2 .828L4.543 16v4zm9.5-13.5 4 4"/></svg></a><li class="dropdown navbar-dropdown navbar-dropdown-apache"><a href=# class=dropdown-toggle role=button aria-haspopup=true aria-expanded=false><img src=https://www.apache.org/foundation/press/kit/feather_small.png alt="Apache Logo" style=height:20px> |
| Apache |
| <span class=arrow-icon><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" fill="none" viewBox="0 0 20 20"><circle cx="10" cy="10" r="10" fill="#ff6d00"/><path stroke="#fff" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M8.535 5.28l4.573 4.818-4.573 4.403"/></svg></span></a><ul class=dropdown-menu><li><a class=navbar-dropdown-menu-link target=_blank href=https://www.apache.org/>ASF Homepage</a></li><li><a class=navbar-dropdown-menu-link target=_blank href=https://www.apache.org/licenses/>License</a></li><li><a class=navbar-dropdown-menu-link target=_blank href=https://www.apache.org/security/>Security</a></li><li><a class=navbar-dropdown-menu-link target=_blank href=https://www.apache.org/foundation/thanks.html>Thanks</a></li><li><a class=navbar-dropdown-menu-link target=_blank href=https://www.apache.org/foundation/sponsorship.html>Sponsorship</a></li><li><a class=navbar-dropdown-menu-link target=_blank href=https://www.apache.org/foundation/policies/conduct>Code of Conduct</a></li></ul></li></div><div class="searchBar disappear"><script>(function(){var t,n="012923275103528129024:4emlchv9wzi",e=document.createElement("script");e.type="text/javascript",e.async=!0,e.src="https://cse.google.com/cse.js?cx="+n,t=document.getElementsByTagName("script")[0],t.parentNode.insertBefore(e,t)})()</script><gcse:search></gcse:search> |
| <a type=button onclick=endSearch()><svg xmlns="http://www.w3.org/2000/svg" width="25" height="25" fill="none" viewBox="0 0 25 25"><path stroke="#ff6d00" stroke-linecap="round" stroke-linejoin="round" stroke-width="2.75" d="M21.122 20.827 4.727 4.432M21.122 4.43 4.727 20.827"/></svg></a></div></div></nav><div class=header-push></div><div class="top-banners swiper"><div class=swiper-wrapper><div class=swiper-slide><a href=https://tour.beam.apache.org><img class=banner-img-desktop src=/images/banners/tour-of-beam/tour-of-beam-desktop.png alt="Start Tour of Beam"> |
| <img class=banner-img-mobile src=/images/banners/tour-of-beam/tour-of-beam-mobile.png alt="Start Tour of Beam"></a></div><div class=swiper-slide><a href=https://beam.apache.org/documentation/ml/overview/><img class=banner-img-desktop src=/images/banners/machine-learning/machine-learning-desktop.jpg alt="Machine Learning"> |
| <img class=banner-img-mobile src=/images/banners/machine-learning/machine-learning-mobile.jpg alt="Machine Learning"></a></div></div><div class=swiper-pagination></div><div class=swiper-button-prev></div><div class=swiper-button-next></div></div><script src=/js/swiper-bundle.min.min.e0e8f81b0b15728d35ff73c07f42ddbb17a108d6f23df4953cb3e60df7ade675.js></script> |
| <script src=/js/sliders/top-banners.min.afa7d0a19acf7a3b28ca369490b3d401a619562a2a4c9612577be2f66a4b9855.js></script> |
| <script>function showSearch(){addPlaceholder();var e,t=document.querySelector(".searchBar");t.classList.remove("disappear"),e=document.querySelector("#iconsBar"),e.classList.add("disappear")}function addPlaceholder(){$("input:text").attr("placeholder","What are you looking for?")}function endSearch(){var e,t=document.querySelector(".searchBar");t.classList.add("disappear"),e=document.querySelector("#iconsBar"),e.classList.remove("disappear")}function blockScroll(){$("body").toggleClass("fixedPosition")}function openMenu(){addPlaceholder(),blockScroll()}</script><div class="clearfix container-main-content"><div class="section-nav closed" data-offset-top=90 data-offset-bottom=500><span class="section-nav-back glyphicon glyphicon-menu-left"></span><nav><ul class=section-nav-list data-section-nav><li><span class=section-nav-list-main-title>Documentation</span></li><li><a href=/documentation>Using the Documentation</a></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Concepts</span><ul class=section-nav-list><li><a href=/documentation/basics/>Basics of the Beam model</a></li><li><a href=/documentation/runtime/model/>How Beam executes a pipeline</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Beam programming guide</span><ul class=section-nav-list><li><a href=/documentation/programming-guide/>Overview</a></li><li><a href=/documentation/programming-guide/#creating-a-pipeline>Pipelines</a></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>PCollections</span><ul class=section-nav-list><li><a href=/documentation/programming-guide/#pcollections>Creating a PCollection</a></li><li><a href=/documentation/programming-guide/#pcollection-characteristics>PCollection characteristics</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Transforms</span><ul class=section-nav-list><li><a href=/documentation/programming-guide/#applying-transforms>Applying transforms</a></li><li><span class=section-nav-list-title>Core Beam transforms</span><ul class=section-nav-list><li><a href=/documentation/programming-guide/#pardo>ParDo</a></li><li><a href=/documentation/programming-guide/#groupbykey>GroupByKey</a></li><li><a href=/documentation/programming-guide/#cogroupbykey>CoGroupByKey</a></li><li><a href=/documentation/programming-guide/#combine>Combine</a></li><li><a href=/documentation/programming-guide/#flatten>Flatten</a></li><li><a href=/documentation/programming-guide/#partition>Partition</a></li></ul></li><li><a href=/documentation/programming-guide/#requirements-for-writing-user-code-for-beam-transforms>Requirements for user code</a></li><li><a href=/documentation/programming-guide/#side-inputs>Side inputs</a></li><li><a href=/documentation/programming-guide/#additional-outputs>Additional outputs</a></li><li><a href=/documentation/programming-guide/#composite-transforms>Composite transforms</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Pipeline I/O</span><ul class=section-nav-list><li><a href=/documentation/programming-guide/#pipeline-io>Using I/O transforms</a></li><li><a href=/documentation/io/connectors/>I/O connectors</a></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>I/O connector guides</span><ul class=section-nav-list><li><a href=/documentation/io/built-in/parquet/>Apache Parquet I/O connector</a></li><li><a href=/documentation/io/built-in/hadoop/>Hadoop Input/Output Format IO</a></li><li><a href=/documentation/io/built-in/hcatalog/>HCatalog IO</a></li><li><a href=/documentation/io/built-in/google-bigquery/>Google BigQuery I/O connector</a></li><li><a href=/documentation/io/built-in/snowflake/>Snowflake I/O connector</a></li><li><a href=/documentation/io/built-in/cdap/>CDAP I/O connector</a></li><li><a href=/documentation/io/built-in/sparkreceiver/>Spark Receiver I/O connector</a></li><li><a href=/documentation/io/built-in/singlestore/>SingleStoreDB I/O connector</a></li><li><a href=/documentation/io/built-in/webapis/>Web APIs I/O connector</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Developing new I/O connectors</span><ul class=section-nav-list><li><a href=/documentation/io/developing-io-overview/>Overview: Developing connectors</a></li><li><a href=/documentation/io/developing-io-java/>Developing connectors (Java)</a></li><li><a href=/documentation/io/developing-io-python/>Developing connectors (Python)</a></li><li><a href=/documentation/io/io-standards/>I/O Standards</a></li></ul></li><li><a href=/documentation/io/testing/>Testing I/O transforms</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Schemas</span><ul class=section-nav-list><li><a href=/documentation/programming-guide/#what-is-a-schema>What is a schema</a></li><li><a href=/documentation/programming-guide/#schemas-for-pl-types>Schemas for programming language types</a></li><li><a href=/documentation/programming-guide/#schema-definition>Schema definition</a></li><li><a href=/documentation/programming-guide/#logical-types>Logical types</a></li><li><a href=/documentation/programming-guide/#creating-schemas>Creating schemas</a></li><li><a href=/documentation/programming-guide/#using-schemas>Using schemas</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Data encoding and type safety</span><ul class=section-nav-list><li><a href=/documentation/programming-guide/#data-encoding-and-type-safety>Data encoding basics</a></li><li><a href=/documentation/programming-guide/#specifying-coders>Specifying coders</a></li><li><a href=/documentation/programming-guide/#default-coders-and-the-coderregistry>Default coders and the CoderRegistry</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Windowing</span><ul class=section-nav-list><li><a href=/documentation/programming-guide/#windowing>Windowing basics</a></li><li><a href=/documentation/programming-guide/#provided-windowing-functions>Provided windowing functions</a></li><li><a href=/documentation/programming-guide/#setting-your-pcollections-windowing-function>Setting your PCollection’s windowing function</a></li><li><a href=/documentation/programming-guide/#watermarks-and-late-data>Watermarks and late data</a></li><li><a href=/documentation/programming-guide/#adding-timestamps-to-a-pcollections-elements>Adding timestamps to a PCollection’s elements</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Triggers</span><ul class=section-nav-list><li><a href=/documentation/programming-guide/#triggers>Trigger basics</a></li><li><a href=/documentation/programming-guide/#event-time-triggers>Event time triggers and the default trigger</a></li><li><a href=/documentation/programming-guide/#processing-time-triggers>Processing time triggers</a></li><li><a href=/documentation/programming-guide/#data-driven-triggers>Data-driven triggers</a></li><li><a href=/documentation/programming-guide/#setting-a-trigger>Setting a trigger</a></li><li><a href=/documentation/programming-guide/#composite-triggers>Composite triggers</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Metrics</span><ul class=section-nav-list><li><a href=/documentation/programming-guide/#metrics>Metrics basics</a></li><li><a href=/documentation/programming-guide/#types-of-metrics>Types of metrics</a></li><li><a href=/documentation/programming-guide/#querying-metrics>Querying metrics</a></li><li><a href=/documentation/programming-guide/#using-metrics>Using metrics in pipeline</a></li><li><a href=/documentation/programming-guide/#export-metrics>Export metrics</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>State and Timers</span><ul class=section-nav-list><li><a href=/documentation/programming-guide/#types-of-state>Types of state</a></li><li><a href=/documentation/programming-guide/#deferred-state-reads>Deferred state reads</a></li><li><a href=/documentation/programming-guide/#timers>Timers</a></li><li><a href=/documentation/programming-guide/#garbage-collecting-state>Garbage collecting state</a></li><li><a href=/documentation/programming-guide/#state-timers-examples>State and timers examples</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Splittable DoFns</span><ul class=section-nav-list><li><a href=/documentation/programming-guide/#sdf-basics>Basics</a></li><li><a href=/documentation/programming-guide/#sizing-and-progress>Sizing and progress</a></li><li><a href=/documentation/programming-guide/#user-initiated-checkpoint>User-initiated checkpoint</a></li><li><a href=/documentation/programming-guide/#runner-initiated-split>Runner initiated split</a></li><li><a href=/documentation/programming-guide/#watermark-estimation>Watermark estimation</a></li><li><a href=/documentation/programming-guide/#truncating-during-drain>Truncating during drain</a></li><li><a href=/documentation/programming-guide/#bundle-finalization>Bundle finalization</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Multi-language Pipelines</span><ul class=section-nav-list><li><a href=/documentation/programming-guide/#create-x-lang-transforms>Creating cross-language transforms</a></li><li><a href=/documentation/programming-guide/#use-x-lang-transforms>Using cross-language transforms</a></li><li><a href=/documentation/programming-guide/#x-lang-transform-runner-support>Runner Support</a></li></ul></li><li><a href=/documentation/programming-guide/#batched-dofns>Batched DoFns</a></li><li><a href=/documentation/programming-guide/#transform-service>Transform service</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Pipeline development lifecycle</span><ul class=section-nav-list><li><a href=/documentation/pipelines/design-your-pipeline/>Design Your Pipeline</a></li><li><a href=/documentation/pipelines/create-your-pipeline/>Create Your Pipeline</a></li><li><a href=/documentation/pipelines/test-your-pipeline/>Test Your Pipeline</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Common pipeline patterns</span><ul class=section-nav-list><li><a href=/documentation/patterns/overview/>Overview</a></li><li><a href=/documentation/patterns/file-processing/>File processing</a></li><li><a href=/documentation/patterns/side-inputs/>Side inputs</a></li><li><a href=/documentation/patterns/pipeline-options/>Pipeline options</a></li><li><a href=/documentation/patterns/custom-io/>Custom I/O</a></li><li><a href=/documentation/patterns/custom-windows/>Custom windows</a></li><li><a href=/documentation/patterns/bigqueryio/>BigQueryIO</a></li><li><a href=/documentation/patterns/ai-platform/>AI Platform</a></li><li><a href=/documentation/patterns/schema/>Schema</a></li><li><a href=/documentation/patterns/bqml/>BigQuery ML</a></li><li><a href=/documentation/patterns/grouping-elements-for-efficient-external-service-calls/>Grouping elements for efficient external service calls</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>AI/ML pipelines</span><ul class=section-nav-list><li><a href=/documentation/ml/overview/>Get started with AI/ML</a></li><li><a href=/documentation/ml/about-ml/>About Beam ML</a></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Prediction and inference</span><ul class=section-nav-list><li><a href=/documentation/ml/inference-overview/>Overview</a></li><li><a href=/documentation/ml/multi-model-pipelines/>Build a pipeline with multiple models</a></li><li><a href=/documentation/ml/tensorrt-runinference>Build a custom model handler with TensorRT</a></li><li><a href=/documentation/ml/large-language-modeling>Use LLM inference</a></li><li><a href=/documentation/ml/multi-language-inference/>Build a multi-language inference pipeline</a></li><li><a href=/documentation/ml/side-input-updates/>Update your model in production</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Data processing</span><ul class=section-nav-list><li><a href=/documentation/ml/preprocess-data/>Preprocess data</a></li><li><a href=/documentation/ml/data-processing/>Explore your data</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Workflow orchestration</span><ul class=section-nav-list><li><a href=/documentation/ml/orchestration/>Use ML-OPS workflow orchestrators</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Model training</span><ul class=section-nav-list><li><a href=/documentation/ml/per-entity-training>Per-entity training</a></li><li><a href=/documentation/ml/online-clustering/>Online clustering</a></li><li><a href=/documentation/ml/model-evaluation/>ML model evaluation</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Use cases</span><ul class=section-nav-list><li><a href=/documentation/ml/anomaly-detection/>Build an anomaly detection pipeline</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Reference</span><ul class=section-nav-list><li><a href=/documentation/ml/runinference-metrics/>RunInference metrics</a></li><li><a href=/documentation/ml/model-evaluation/>Model validation</a></li></ul></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Runtime systems</span><ul class=section-nav-list><li><a href=/documentation/runtime/environments/>Container environments</a></li><li><a href=/documentation/runtime/resource-hints/>Resource hints</a></li><li><a href=/documentation/runtime/sdk-harness-config/>SDK Harness Configuration</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Transform catalog</span><ul class=section-nav-list><li class=section-nav-item--collapsible><span class=section-nav-list-title>Python</span><ul class=section-nav-list><li><a href=/documentation/transforms/python/overview/>Overview</a></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Element-wise</span><ul class=section-nav-list><li class=section-nav-item--collapsible><span class=section-nav-list-title>Enrichment</span><ul class=section-nav-list><li><a href=/documentation/transforms/python/elementwise/enrichment/>Overview</a></li><li><a href=/documentation/transforms/python/elementwise/enrichment-bigtable/>Bigtable example</a></li><li><a href=/documentation/transforms/python/elementwise/enrichment-vertexai/>Vertex AI Feature Store examples</a></li></ul></li><li><a href=/documentation/transforms/python/elementwise/filter/>Filter</a></li><li><a href=/documentation/transforms/python/elementwise/flatmap/>FlatMap</a></li><li><a href=/documentation/transforms/python/elementwise/keys/>Keys</a></li><li><a href=/documentation/transforms/python/elementwise/kvswap/>KvSwap</a></li><li><a href=/documentation/transforms/python/elementwise/map/>Map</a></li><li><a href=/documentation/transforms/python/elementwise/mltransform/>MLTransform</a></li><li><a href=/documentation/transforms/python/elementwise/pardo/>ParDo</a></li><li><a href=/documentation/transforms/python/elementwise/partition/>Partition</a></li><li><a href=/documentation/transforms/python/elementwise/regex/>Regex</a></li><li><a href=/documentation/transforms/python/elementwise/reify/>Reify</a></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>RunInference</span><ul class=section-nav-list><li><a href=/documentation/transforms/python/elementwise/runinference/>Overview</a></li><li><a href=/documentation/transforms/python/elementwise/runinference-pytorch/>PyTorch examples</a></li><li><a href=/documentation/transforms/python/elementwise/runinference-sklearn/>Sklearn examples</a></li></ul></li><li><a href=/documentation/transforms/python/elementwise/tostring/>ToString</a></li><li><a href=/documentation/transforms/python/elementwise/values/>Values</a></li><li><a href=/documentation/transforms/python/elementwise/withtimestamps/>WithTimestamps</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Aggregation</span><ul class=section-nav-list><li><a href=/documentation/transforms/python/aggregation/approximatequantiles/>ApproximateQuantiles</a></li><li><a href=/documentation/transforms/python/aggregation/approximateunique/>ApproximateUnique</a></li><li><a href=/documentation/transforms/python/aggregation/cogroupbykey/>CoGroupByKey</a></li><li><a href=/documentation/transforms/python/aggregation/combineglobally/>CombineGlobally</a></li><li><a href=/documentation/transforms/python/aggregation/combineperkey/>CombinePerKey</a></li><li><a href=/documentation/transforms/python/aggregation/combinevalues/>CombineValues</a></li><li><a href=/documentation/transforms/python/aggregation/count/>Count</a></li><li><a href=/documentation/transforms/python/aggregation/distinct/>Distinct</a></li><li><a href=/documentation/transforms/python/aggregation/groupby/>GroupBy</a></li><li><a href=/documentation/transforms/python/aggregation/groupbykey/>GroupByKey</a></li><li><a href=/documentation/transforms/python/aggregation/groupintobatches/>GroupIntoBatches</a></li><li><a href=/documentation/transforms/python/aggregation/latest/>Latest</a></li><li><a href=/documentation/transforms/python/aggregation/max/>Max</a></li><li><a href=/documentation/transforms/python/aggregation/mean/>Mean</a></li><li><a href=/documentation/transforms/python/aggregation/min/>Min</a></li><li><a href=/documentation/transforms/python/aggregation/sample/>Sample</a></li><li><a href=/documentation/transforms/python/aggregation/sum/>Sum</a></li><li><a href=/documentation/transforms/python/aggregation/top/>Top</a></li><li><a href=/documentation/transforms/python/aggregation/tolist/>ToList</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Other</span><ul class=section-nav-list><li><a href=/documentation/transforms/python/other/create/>Create</a></li><li><a href=/documentation/transforms/python/other/flatten/>Flatten</a></li><li><a href=/documentation/transforms/python/other/reshuffle/>Reshuffle</a></li><li><a href=/documentation/transforms/python/other/windowinto/>WindowInto</a></li></ul></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Java</span><ul class=section-nav-list><li><a href=/documentation/transforms/java/overview/>Overview</a></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Element-wise</span><ul class=section-nav-list><li><a href=/documentation/transforms/java/elementwise/filter/>Filter</a></li><li><a href=/documentation/transforms/java/elementwise/flatmapelements/>FlatMapElements</a></li><li><a href=/documentation/transforms/java/elementwise/keys/>Keys</a></li><li><a href=/documentation/transforms/java/elementwise/kvswap/>KvSwap</a></li><li><a href=/documentation/transforms/java/elementwise/mapelements/>MapElements</a></li><li><a href=/documentation/transforms/java/elementwise/pardo/>ParDo</a></li><li><a href=/documentation/transforms/java/elementwise/partition/>Partition</a></li><li><a href=/documentation/transforms/java/elementwise/regex/>Regex</a></li><li><a href=/documentation/transforms/java/elementwise/reify/>Reify</a></li><li><a href=/documentation/transforms/java/elementwise/tostring/>ToString</a></li><li><a href=/documentation/transforms/java/elementwise/values/>Values</a></li><li><a href=/documentation/transforms/java/elementwise/withkeys/>WithKeys</a></li><li><a href=/documentation/transforms/java/elementwise/withtimestamps/>WithTimestamps</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Aggregation</span><ul class=section-nav-list><li><a href=/documentation/transforms/java/aggregation/approximatequantiles/>ApproximateQuantiles</a></li><li><a href=/documentation/transforms/java/aggregation/approximateunique/>ApproximateUnique</a></li><li><a href=/documentation/transforms/java/aggregation/cogroupbykey/>CoGroupByKey</a></li><li><a href=/documentation/transforms/java/aggregation/combine/>Combine</a></li><li><a href=/documentation/transforms/java/aggregation/combinewithcontext/>CombineWithContext</a></li><li><a href=/documentation/transforms/java/aggregation/count/>Count</a></li><li><a href=/documentation/transforms/java/aggregation/distinct/>Distinct</a></li><li><a href=/documentation/transforms/java/aggregation/groupbykey/>GroupByKey</a></li><li><a href=/documentation/transforms/java/aggregation/groupintobatches/>GroupIntoBatches</a></li><li><a href=/documentation/transforms/java/aggregation/hllcount/>HllCount</a></li><li><a href=/documentation/transforms/java/aggregation/latest/>Latest</a></li><li><a href=/documentation/transforms/java/aggregation/max/>Max</a></li><li><a href=/documentation/transforms/java/aggregation/mean/>Mean</a></li><li><a href=/documentation/transforms/java/aggregation/min/>Min</a></li><li><a href=/documentation/transforms/java/aggregation/sample/>Sample</a></li><li><a href=/documentation/transforms/java/aggregation/sum/>Sum</a></li><li><a href=/documentation/transforms/java/aggregation/top/>Top</a></li></ul></li><li class=section-nav-item--collapsible><span class=section-nav-list-title>Other</span><ul class=section-nav-list><li><a href=/documentation/transforms/java/other/create/>Create</a></li><li><a href=/documentation/transforms/java/other/flatten/>Flatten</a></li><li><a href=/documentation/transforms/java/other/passert/>PAssert</a></li><li><a href=/documentation/transforms/java/other/view/>View</a></li><li><a href=/documentation/transforms/java/other/window/>Window</a></li></ul></li></ul></li></ul></li><li><a href=/documentation/glossary/>Glossary</a></li><li><a href=https://cwiki.apache.org/confluence/display/BEAM/Apache+Beam>Beam Wiki <img src=/images/external-link-icon.png width=14 height=14 alt="External link."></a></li></ul></nav></div><nav class="page-nav clearfix" data-offset-top=90 data-offset-bottom=500><nav id=TableOfContents><ul><li><a href=#nlp-model-and-dataset>NLP model and dataset</a></li><li><a href=#multi-language-inference-pipeline>Multi-language Inference pipeline</a><ul><li><a href=#custom-python-transform>Custom Python transform</a></li><li><a href=#compile-python-code-into-package>Compile Python code into package</a></li><li><a href=#run-the-java-pipeline>Run the Java pipeline</a></li></ul></li><li><a href=#final-remarks>Final remarks</a></li></ul></nav></nav><div class="body__contained body__section-nav arrow-list arrow-list--no-mt"><h1 id=using-runinference-from-java-sdk>Using RunInference from Java SDK</h1><p>The pipeline in this example is written in Java and reads the input data from Google Cloud Storage. With the help of a <a href=https://beam.apache.org/documentation/programming-guide/#1312-creating-cross-language-python-transforms>PythonExternalTransform</a>, |
| a composite Python transform is called to do the preprocessing, postprocessing, and inference. |
| Lastly, the data is written back to Google Cloud Storage in the Java pipeline.</p><p>You can find the code used in this example in the <a href=https://github.com/apache/beam/tree/master/sdks/python/apache_beam/examples/inference/multi_language_inference>Beam repository</a>.</p><h2 id=nlp-model-and-dataset>NLP model and dataset</h2><p>A <code>bert-base-uncased</code> natural language processing (NLP) model is used to make inference. This model is open source and available on <a href=https://huggingface.co/bert-base-uncased>HuggingFace</a>. This BERT-model is |
| used to predict the last word of a sentence based on the context of the sentence.</p><p>We also use an <a href="https://www.kaggle.com/datasets/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews?select=IMDB+Dataset.csv">IMDB movie reviews</a> dataset, which is an open-source dataset that is available on Kaggle.</p><p>The following is a sample of the data after preprocessing:</p><table><thead><tr><th><strong>Text</strong></th><th style=text-align:left><strong>Last Word</strong></th></tr></thead><tbody><tr><td><img width=700/></td><td style=text-align:left><img width=100/></td></tr><tr><td>One of the other reviewers has mentioned that after watching just 1 Oz episode you’ll be [MASK]</td><td style=text-align:left>hooked</td></tr><tr><td>A wonderful little [MASK]</td><td style=text-align:left>production</td></tr><tr><td>So im not a big fan of Boll’s work but then again not many [MASK]</td><td style=text-align:left>are</td></tr><tr><td>This a fantastic movie of three prisoners who become [MASK]</td><td style=text-align:left>famous</td></tr><tr><td>Some films just simply should not be [MASK]</td><td style=text-align:left>remade</td></tr><tr><td>The Karen Carpenter Story shows a little more about singer Karen Carpenter’s complex [MASK]</td><td style=text-align:left>life</td></tr></tbody></table><h2 id=multi-language-inference-pipeline>Multi-language Inference pipeline</h2><p>When using multi-language pipelines, you have access to a much larger pool of transforms. For more information, see <a href=https://beam.apache.org/documentation/programming-guide/#multi-language-pipelines>Multi-language pipelines</a> in the Apache Beam Programming Guide.</p><h3 id=custom-python-transform>Custom Python transform</h3><p>In addition to running inference, we also need to perform preprocessing and postprocessing on the data. Postprocessing the data makes it possible to interpret the output. In order to do these three tasks, one single composite custom PTransform is written, with a unit DoFn or PTransform for each of the tasks, as shown in the following snippet:</p><div class=highlight><pre tabindex=0 class=chroma><code class=language-python data-lang=python><span class=line><span class=cl><span class=k>def</span> <span class=nf>expand</span><span class=p>(</span><span class=bp>self</span><span class=p>,</span> <span class=n>pcoll</span><span class=p>):</span> |
| </span></span><span class=line><span class=cl> <span class=k>return</span> <span class=p>(</span> |
| </span></span><span class=line><span class=cl> <span class=n>pcoll</span> |
| </span></span><span class=line><span class=cl> <span class=o>|</span> <span class=s1>'Preprocess'</span> <span class=o>>></span> <span class=n>beam</span><span class=o>.</span><span class=n>ParDo</span><span class=p>(</span><span class=bp>self</span><span class=o>.</span><span class=n>Preprocess</span><span class=p>(</span><span class=bp>self</span><span class=o>.</span><span class=n>_tokenizer</span><span class=p>))</span> |
| </span></span><span class=line><span class=cl> <span class=o>|</span> <span class=s1>'Inference'</span> <span class=o>>></span> <span class=n>RunInference</span><span class=p>(</span><span class=n>KeyedModelHandler</span><span class=p>(</span><span class=bp>self</span><span class=o>.</span><span class=n>_model_handler</span><span class=p>))</span> |
| </span></span><span class=line><span class=cl> <span class=o>|</span> <span class=s1>'Postprocess'</span> <span class=o>>></span> <span class=n>beam</span><span class=o>.</span><span class=n>ParDo</span><span class=p>(</span><span class=bp>self</span><span class=o>.</span><span class=n>Postprocess</span><span class=p>(</span> |
| </span></span><span class=line><span class=cl> <span class=bp>self</span><span class=o>.</span><span class=n>_tokenizer</span><span class=p>))</span> |
| </span></span><span class=line><span class=cl> <span class=p>)</span> |
| </span></span></code></pre></div><p>First, the preprocessing of the data. In this case, the raw textual data is cleaned and tokenized for the BERT-model. All these steps are run in the <code>Preprocess</code> DoFn. The <code>Preprocess</code> DoFn takes a single element as input and returns a list with both the original text and the tokenized text.</p><p>The preprocessed data is then used to make inference. This is done in the <a href=https://beam.apache.org/documentation/ml/overview/#runinference><code>RunInference</code></a> PTransform, which is already available in the Apache Beam SDK. The <code>RunInference</code> PTransform requires one parameter, a model handler. In this example the <code>KeyedModelHandler</code> is used, because the <code>Preprocess</code> DoFn also outputs the original sentence. You can change how preprocessing is done based on your requirements. This model handler is defined in the following initialization function of the composite PTransform:</p><div class=highlight><pre tabindex=0 class=chroma><code class=language-python data-lang=python><span class=line><span class=cl><span class=k>def</span> <span class=fm>__init__</span><span class=p>(</span><span class=bp>self</span><span class=p>,</span> <span class=n>model</span><span class=p>,</span> <span class=n>model_path</span><span class=p>):</span> |
| </span></span><span class=line><span class=cl> <span class=bp>self</span><span class=o>.</span><span class=n>_model</span> <span class=o>=</span> <span class=n>model</span> |
| </span></span><span class=line><span class=cl> <span class=n>logging</span><span class=o>.</span><span class=n>info</span><span class=p>(</span><span class=sa>f</span><span class=s2>"Downloading </span><span class=si>{</span><span class=bp>self</span><span class=o>.</span><span class=n>_model</span><span class=si>}</span><span class=s2> model from GCS."</span><span class=p>)</span> |
| </span></span><span class=line><span class=cl> <span class=bp>self</span><span class=o>.</span><span class=n>_model_config</span> <span class=o>=</span> <span class=n>BertConfig</span><span class=o>.</span><span class=n>from_pretrained</span><span class=p>(</span><span class=bp>self</span><span class=o>.</span><span class=n>_model</span><span class=p>)</span> |
| </span></span><span class=line><span class=cl> <span class=bp>self</span><span class=o>.</span><span class=n>_tokenizer</span> <span class=o>=</span> <span class=n>BertTokenizer</span><span class=o>.</span><span class=n>from_pretrained</span><span class=p>(</span><span class=bp>self</span><span class=o>.</span><span class=n>_model</span><span class=p>)</span> |
| </span></span><span class=line><span class=cl> <span class=bp>self</span><span class=o>.</span><span class=n>_model_handler</span> <span class=o>=</span> <span class=bp>self</span><span class=o>.</span><span class=n>PytorchModelHandlerKeyedTensorWrapper</span><span class=p>(</span> |
| </span></span><span class=line><span class=cl> <span class=n>state_dict_path</span><span class=o>=</span><span class=p>(</span><span class=n>model_path</span><span class=p>),</span> |
| </span></span><span class=line><span class=cl> <span class=n>model_class</span><span class=o>=</span><span class=n>BertForMaskedLM</span><span class=p>,</span> |
| </span></span><span class=line><span class=cl> <span class=n>model_params</span><span class=o>=</span><span class=p>{</span><span class=s1>'config'</span><span class=p>:</span> <span class=bp>self</span><span class=o>.</span><span class=n>_model_config</span><span class=p>},</span> |
| </span></span><span class=line><span class=cl> <span class=n>device</span><span class=o>=</span><span class=s1>'cuda:0'</span><span class=p>)</span> |
| </span></span></code></pre></div><p>The <code>PytorchModelHandlerKeyedTensorWrapper</code>, a wrapper around the <code>PytorchModelHandlerKeyedTensor</code> model handler, is used. The <code>PytorchModelHandlerKeyedTensor</code> model handler makes inference on a PyTorch model. Because the tokenized strings generated from <code>BertTokenizer</code> might have different lengths and stack() requires tensors to be the same size, the <code>PytorchModelHandlerKeyedTensorWrapper</code> limits the batch size to 1. Restricting <code>max_batch_size</code> to 1 means the run_inference() call contains one example per batch. The following code shows the definition of the wrapper:</p><div class=highlight><pre tabindex=0 class=chroma><code class=language-python data-lang=python><span class=line><span class=cl><span class=k>class</span> <span class=nc>PytorchModelHandlerKeyedTensorWrapper</span><span class=p>(</span><span class=n>PytorchModelHandlerKeyedTensor</span><span class=p>):</span> |
| </span></span><span class=line><span class=cl> |
| </span></span><span class=line><span class=cl> <span class=k>def</span> <span class=nf>batch_elements_kwargs</span><span class=p>(</span><span class=bp>self</span><span class=p>):</span> |
| </span></span><span class=line><span class=cl> <span class=k>return</span> <span class=p>{</span><span class=s1>'max_batch_size'</span><span class=p>:</span> <span class=mi>1</span><span class=p>}</span> |
| </span></span></code></pre></div><p>An alternative aproach is to make all the tensors have the same length. This <a href=https://github.com/apache/beam/blob/master/examples/notebooks/beam-ml/run_inference_pytorch_tensorflow_sklearn.ipynb>example</a> shows how to do that.</p><p>The <code>ModelConfig</code> and <code>ModelTokenizer</code> are loaded in the initialization function. The <code>ModelConfig</code> is used to define the model architecture, and the <code>ModelTokenizer</code> is used to tokenize the input data. The following two parameters are used for these tasks:</p><ul><li><code>model</code>: The name of the model that is used for inference. In this example it is <code>bert-base-uncased</code>.</li><li><code>model_path</code>: The path to the <code>state_dict</code> of the model that is used for inference. In this example it is a path to a Google Cloud Storage bucket, where the <code>state_dict</code> is stored.</li></ul><p>Both of these parameters are specified in the Java <code>PipelineOptions</code>.</p><p>Finally, we postprocess the model predictions in the <code>Postprocess</code> DoFn. The <code>Postprocess</code> DoFn returns the original text, the last word of the sentence, and the predicted word.</p><h3 id=compile-python-code-into-package>Compile Python code into package</h3><p>The custom Python code needs to be written in a local package and be compiled as a tarball. This package can then be used by the Java pipeline. The following example shows how to compile the Python package into a tarball:</p><div class=highlight><pre tabindex=0 class=chroma><code class=language-bash data-lang=bash><span class=line><span class=cl> pip install --upgrade build <span class=o>&&</span> python -m build --sdist |
| </span></span></code></pre></div><p>In order to run this, a <code>setup.py</code> is required. The path to the tarball will be used as an argument in the pipeline options of the Java pipeline.</p><h3 id=run-the-java-pipeline>Run the Java pipeline</h3><p>The Java pipeline is defined in the <a href=https://github.com/apache/beam/blob/master/sdks/python/apache_beam/examples/inference/multi_language_inference/last_word_prediction/src/main/java/org/apache/beam/examples/MultiLangRunInference.java#L32><code>MultiLangRunInference</code></a> class. In this pipeline, the data is read from Google Cloud Storage, the cross-language Python transform is applied, and the output is written back to Google Cloud Storage.</p><p>The <code>PythonExternalTransform</code> is used to inject the cross-language Python transform into the Java pipeline. <code>PythonExternalTransform</code> takes a string parameter which is the fully qualified name of the Python transform.</p><p>The <code>withKwarg</code> method is used to specify the parameters that are needed for the Python transform. In this example the <code>model</code> and <code>model_path</code> parameters are specified. These parameters are used in the initialization function of the composite Python PTransform, as shown in the first section. Finally the <code>withExtraPackages</code> method is used to specify the additional Python dependencies that are needed for the Python transform. In this example the <code>local_packages</code> list is used, which contains Python requirements and the path to the compiled tarball.</p><p>To run the pipeline, use the following command:</p><div class=highlight><pre tabindex=0 class=chroma><code class=language-bash data-lang=bash><span class=line><span class=cl>mvn compile exec:java -Dexec.mainClass<span class=o>=</span>org.apache.beam.examples.MultiLangRunInference <span class=se>\ |
| </span></span></span><span class=line><span class=cl><span class=se></span> -Dexec.args<span class=o>=</span><span class=s2>"--runner=DataflowRunner \ |
| </span></span></span><span class=line><span class=cl><span class=s2> --project=</span><span class=nv>$GCP_PROJECT</span><span class=s2>\ |
| </span></span></span><span class=line><span class=cl><span class=s2> --region=</span><span class=nv>$GCP_REGION</span><span class=s2> \ |
| </span></span></span><span class=line><span class=cl><span class=s2> --gcpTempLocation=gs://</span><span class=nv>$GCP_BUCKET</span><span class=s2>/temp/ \ |
| </span></span></span><span class=line><span class=cl><span class=s2> --inputFile=gs://</span><span class=nv>$GCP_BUCKET</span><span class=s2>/input/imdb_reviews.csv \ |
| </span></span></span><span class=line><span class=cl><span class=s2> --outputFile=gs://</span><span class=nv>$GCP_BUCKET</span><span class=s2>/output/ouput.txt \ |
| </span></span></span><span class=line><span class=cl><span class=s2> --modelPath=gs://</span><span class=nv>$GCP_BUCKET</span><span class=s2>/input/bert-model/bert-base-uncased.pth \ |
| </span></span></span><span class=line><span class=cl><span class=s2> --modelName=</span><span class=nv>$MODEL_NAME</span><span class=s2> \ |
| </span></span></span><span class=line><span class=cl><span class=s2> --localPackage=</span><span class=nv>$LOCAL_PACKAGE</span><span class=s2>"</span> <span class=se>\ |
| </span></span></span><span class=line><span class=cl><span class=se></span> -Pdataflow-runner |
| </span></span></code></pre></div><p>The standard Google Cloud and Runner parameters are specified. The <code>inputFile</code> and <code>outputFile</code> parameters are used to specify the input and output files. The <code>modelPath</code> and <code>modelName</code> custom parameters are passed to the <code>PythonExternalTransform</code>. Finally the <code>localPackage</code> parameter is used to specify the path to the compiled Python package, which contains the custom Python transform.</p><h2 id=final-remarks>Final remarks</h2><p>Use this example as a base to create other custom multi-language inference pipelines. You can also use other SDKs. For example, Go also has a wrapper that can make cross-language transforms. For more information, see <a href=https://beam.apache.org/documentation/programming-guide/#1323-using-cross-language-transforms-in-a-go-pipeline>Using cross-language transforms in a Go pipeline</a> in the Apache Beam Programming Guide.</p><p>The full code used in this example can be found on <a href=https://github.com/apache/beam/tree/master/sdks/python/apache_beam/examples/inference/multi_language_inference>GitHub</a>.</p><div class=feedback><p class=update>Last updated on 2024/05/03</p><h3>Have you found everything you were looking for?</h3><p class=description>Was it all useful and clear? Is there anything that you would like to change? Let us know!</p><button class=load-button><a href="https://docs.google.com/forms/d/e/1FAIpQLSfID7abne3GE6k6RdJIyZhPz2Gef7UkpggUEhTIDjjplHuxSA/viewform?usp=header_link" target=_blank>SEND FEEDBACK</a></button></div></div></div><footer class=footer><div class=footer__contained><div class=footer__cols><div class="footer__cols__col footer__cols__col__logos"><div class=footer__cols__col__logo><img src=/images/beam_logo_circle.svg class=footer__logo alt="Beam logo"></div><div class=footer__cols__col__logo><img src=/images/apache_logo_circle.svg class=footer__logo alt="Apache logo"></div></div><div class=footer-wrapper><div class=wrapper-grid><div class=footer__cols__col><div class=footer__cols__col__title>Start</div><div class=footer__cols__col__link><a href=/get-started/beam-overview/>Overview</a></div><div class=footer__cols__col__link><a href=/get-started/quickstart-java/>Quickstart (Java)</a></div><div class=footer__cols__col__link><a href=/get-started/quickstart-py/>Quickstart (Python)</a></div><div class=footer__cols__col__link><a href=/get-started/quickstart-go/>Quickstart (Go)</a></div><div class=footer__cols__col__link><a href=/get-started/downloads/>Downloads</a></div></div><div class=footer__cols__col><div class=footer__cols__col__title>Docs</div><div class=footer__cols__col__link><a href=/documentation/programming-guide/>Concepts</a></div><div class=footer__cols__col__link><a href=/documentation/pipelines/design-your-pipeline/>Pipelines</a></div><div class=footer__cols__col__link><a href=/documentation/runners/capability-matrix/>Runners</a></div></div><div class=footer__cols__col><div class=footer__cols__col__title>Community</div><div class=footer__cols__col__link><a href=/contribute/>Contribute</a></div><div class=footer__cols__col__link><a href=https://projects.apache.org/committee.html?beam target=_blank>Team<img src=/images/external-link-icon.png width=14 height=14 alt="External link."></a></div><div class=footer__cols__col__link><a href=/community/presentation-materials/>Media</a></div><div class=footer__cols__col__link><a href=/community/in-person/>Events/Meetups</a></div><div class=footer__cols__col__link><a href=/community/contact-us/>Contact Us</a></div></div><div class=footer__cols__col><div class=footer__cols__col__title>Resources</div><div class=footer__cols__col__link><a href=/blog/>Blog</a></div><div class=footer__cols__col__link><a href=https://github.com/apache/beam>GitHub</a></div></div></div><div class=footer__bottom>© |
| <a href=https://www.apache.org>The Apache Software Foundation</a> |
| | <a href=/privacy_policy>Privacy Policy</a> |
| | <a href=/feed.xml>RSS Feed</a><br><br>Apache Beam, Apache, Beam, the Beam logo, and the Apache feather logo are either registered trademarks or trademarks of The Apache Software Foundation. All other products or name brands are trademarks of their respective holders, including The Apache Software Foundation.</div></div><div class="footer__cols__col footer__cols__col__logos"><div class=footer__cols__col--group><div class=footer__cols__col__logo><a href=https://github.com/apache/beam><img src=/images/logos/social-icons/github-logo-150.png class=footer__logo alt="Github logo"></a></div><div class=footer__cols__col__logo><a href=https://www.linkedin.com/company/apache-beam/><img src=/images/logos/social-icons/linkedin-logo-150.png class=footer__logo alt="Linkedin logo"></a></div></div><div class=footer__cols__col--group><div class=footer__cols__col__logo><a href=https://twitter.com/apachebeam><img src=/images/logos/social-icons/twitter-logo-150.png class=footer__logo alt="Twitter logo"></a></div><div class=footer__cols__col__logo><a href=https://www.youtube.com/channel/UChNnb_YO_7B0HlW6FhAXZZQ><img src=/images/logos/social-icons/youtube-logo-150.png class=footer__logo alt="Youtube logo"></a></div></div></div></div></div></footer></body></html> |
