CINXE.COM

<!doctype html><html lang="en-US" dir="ltr"><head><base href="https://cloud.google.com/blog/"><link rel="preconnect" href="//www.gstatic.com"><meta name="referrer" content="origin"><meta name="viewport" content="initial-scale=1, width=device-width"><meta name="track-metadata-page_hosting_platform" content="blog_boq"><meta name="mobile-web-app-capable" content="yes"><meta name="apple-mobile-web-app-capable" content="yes"><meta name="application-name" content="Google Cloud Blog"><meta name="apple-mobile-web-app-title" content="Google Cloud Blog"><meta name="apple-mobile-web-app-status-bar-style" content="black"><meta name="msapplication-tap-highlight" content="no"><link rel="preconnect" href="//fonts.googleapis.com"><link rel="preconnect" href="//fonts.gstatic.com"><link rel="preconnect" href="//www.gstatic.com"><link rel="preconnect" href="//storage.googleapis.com"><link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Google+Sans+Text_old:400,500,700,400i,500i,700i"><link rel="manifest" crossorigin="use-credentials" href="_/TransformBlogUi/manifest.json"><link rel="home" href="/?lfhs=2"><link rel="msapplication-starturl" href="/?lfhs=2"><link rel="icon" href="//www.gstatic.com/cloud/images/icons/favicon.ico" sizes="32x32"><link rel="apple-touch-icon-precomposed" href="//www.gstatic.com/cloud/images/icons/favicon.ico" sizes="32x32"><link rel="msapplication-square32x32logo" href="//www.gstatic.com/cloud/images/icons/favicon.ico" sizes="32x32"><script data-id="_gd" nonce="5dAgjnjZnWn0wEH1uLTSYA">window.WIZ_global_data = {"Bwo7Jf":"%.@.\"SG\",1]","CGQM5":"%.@.[[1]]]","DpimGf":false,"EP1ykd":["/_/*","/accounts/*","/transform","/transform/*"],"FdrFJe":"-1380568030393767848","Im6cmf":"/blog/_/TransformBlogUi","JvMKJd":"%.@.\"GTM-5CVQBG\",[[\"en\",\"\\u202aEnglish\\u202c\",true,\"en\"],[\"de\",\"\\u202aDeutsch\\u202c\",true,\"de\"],[\"es\",\"\\u202aEspañol\\u202c\",true,\"es\"],[\"es-419\",\"\\u202aEspañol (Latinoamérica)\\u202c\",true,\"es-419\"],[\"fr\",\"\\u202aFrançais\\u202c\",true,\"fr\"],[\"id\",\"\\u202aIndonesia\\u202c\",true,\"id\"],[\"it\",\"\\u202aItaliano\\u202c\",true,\"it\"],[\"pt-BR\",\"\\u202aPortuguês (Brasil)\\u202c\",true,\"pt-BR\"],[\"zh-CN\",\"\\u202a简体中文\\u202c\",true,\"zh-Hans\"],[\"zh-TW\",\"\\u202a繁體中文\\u202c\",true,\"zh-Hant\"],[\"ja\",\"\\u202a日本語\\u202c\",true,\"ja\"],[\"ko\",\"\\u202a한국어\\u202c\",true,\"ko\"]],[\"83405\",\"AIzaSyD3LJeW4Q6gtdgJlyeFZUp-GhpIoc6EUeg\"],\"en\",null,null,[],[[\"https://cloud.google.com/innovators\",\"https://cloud.google.com/innovators/plus/activate\",\"https://cloud.google.com/innovators/innovatorsplus\"],[\"https://workspace.google.com/pricing\",\"https://www.x.com/googleworkspace\",\"https://www.facebook.com/googleworkspace\",\"https://www.youtube.com/channel/UCBmwzQnSoj9b6HzNmFrg_yw\",\"https://www.instagram.com/googleworkspace\",\"https://www.linkedin.com/showcase/googleworkspace\",\"https://about.google/?utm_source\\u003dworkspace.google.com\\u0026utm_medium\\u003dreferral\\u0026utm_campaign\\u003dgsuite-footer-en\",\"https://about.google/products/?tip\\u003dexplore\",\"https://workspace.google.com\",\"https://workspace.google.com/contact/?source\\u003dgafb-form-globalnav-en\",\"https://workspace.google.com/business/signup/welcome?hl\\u003den\\u0026source\\u003dgafb-form-globalnav-en\",\"https://workspace.google.com/blog\"],[\"https://www.cloudskillsboost.google\",\"https://www.cloudskillsboost.google?utm_source\\u003dcgc\\u0026utm_medium\\u003dwebsite\\u0026utm_campaign\\u003devergreen\",\"https://www.cloudskillsboost.google/subscriptions?utm_source\\u003dcgc\\u0026utm_medium\\u003dwebsite\\u0026utm_campaign\\u003devergreenlaunchpromo\",\"https://www.cloudskillsboost.google/subscriptions?utm_source\\u003dcgc\\u0026utm_medium\\u003dwebsite\\u0026utm_campaign\\u003devergreen\",\"https://www.cloudskillsboost.google/catalog?utm_source\\u003dcgc\\u0026utm_medium\\u003dwebsite\\u0026utm_campaign\\u003devergreen\",\"https://www.cloudskillsboost.google/paths?utm_source\\u003dcgc\\u0026utm_medium\\u003dwebsite\\u0026utm_campaign\\u003devergreen\"],[\"https://mapsplatform.google.com\"],[\"https://cloud.google.com/developers\",\"https://cloud.google.com/developers/settings?utm_source\\u003dinnovators\"],[\"https://console.cloud.google.com/freetrial\",\"https://console.cloud.google.com/\",\"https://console.cloud.google.com/freetrial?redirectPath\\u003dhttps://cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai\"],[\"https://aitestkitchen.withgoogle.com/signup\",\"https://blog.google/technology/ai/join-us-in-the-ai-test-kitchen/\",\"https://cloud.google.com/ai\"],[\"https://googlecloudplatform.blogspot.com/\",\"https://github.com/GoogleCloudPlatform\",\"https://www.linkedin.com/company/google-cloud\",\"https://twitter.com/GoogleCloud_sg\",\"https://www.facebook.com/googlecloud\",\"https://www.youtube.com/GoogleCloudAPAC\"]],[2024,11,27],[[\"en\",\"x-default\"],\"x-default\"],[null,true],null,\"/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai?hl\\u003den\",[\"6LcsrxUqAAAAAFhpR1lXsPN2j2nsTwy6JTbRKzJr\"]]","LVIXXb":1,"LoQv7e":false,"M55kSc":"%.@.]","MT7f9b":[],"MUE6Ne":"TransformBlogUi","PylxI":"%.@.\"cloudblog\",\"products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai\",[\"en\",\"de\",\"fr\",\"ko\",\"ja\"],\"en\",null,\"https://cloud.google.com/blog\",\"blog_article\",\"cloud.google.com\",[\"https://console.cloud.google.com/freetrial/\",\"https://cloud.google.com/contact/\",\"https://cloud.google.com/\",\"https://cloud.google.com/blog\",\"https://cloud.google.com/\",\"https://www.google.com/\",\"https://cloud.google.com/products/\",\"https://about.google.com/products/\",\"https://about.google/intl/en/\",\"https://support.google.com\"],[\"googlecloud\",\"googlecloud\",\"showcase/google-cloud\",\"googlecloud/\",\"googlecloud/\"],true]","QrtxK":"","S06Grb":"","S6lZl":105833389,"TSDtV":"%.@.[[null,[[45449436,null,false,null,null,null,\"NCoWOd\"],[45667527,null,false,null,null,null,\"Qzt9sd\"],[45449424,null,null,null,\"default\",null,\"PB4oCc\"],[45532645,null,true,null,null,null,\"wFnpse\"],[45643590,null,false,null,null,null,\"w7jzef\"],[45449433,null,true,null,null,null,\"BotAtd\"],[45662378,null,true,null,null,null,\"DG71uf\"],[45449442,null,true,null,null,null,\"dsKk4d\"],[45449449,null,true,null,null,null,\"b5B1L\"],[45663339,null,false,null,null,null,\"OEmSkb\"],[45664956,null,false,null,null,null,\"aeNUHe\"],[45459555,null,false,null,null,null,\"Imeoqb\"],[45646404,null,false,null,null,null,\"tfPPe\"],[45651445,null,true,null,null,null,\"XzXOC\"],[45449440,null,false,null,null,null,\"j9nUqf\"],[45631885,null,false,null,null,null,\"kG32O\"],[45449445,null,true,null,null,null,\"C4H3Td\"],[45649370,null,false,null,null,null,\"LibkZ\"],[45657332,null,true,null,null,null,\"oBUucf\"],[45449438,null,false,null,null,null,\"m0uJSe\"],[45449471,null,null,null,\"default\",null,\"Ammqqf\"],[45612748,null,false,null,null,null,\"fdXYmb\"],[45449467,null,null,null,\"control\",null,\"qL2Vf\"],[45449469,null,null,null,\"default\",null,\"mBNY1\"],[45449443,null,false,null,null,null,\"wvKxS\"],[45616194,null,false,null,null,null,\"y3jdm\"],[45449434,null,true,null,null,null,\"PvZHQ\"],[45449428,null,null,null,\"default\",null,\"cbPi4d\"],[45664077,null,false,null,null,null,\"w1axY\"],[45449423,null,null,null,\"default\",null,\"FIJFKf\"],[45449450,null,false,null,null,null,\"PTNaKe\"],[45632110,null,true,null,null,null,\"QK58Od\"],[45449435,null,false,null,null,null,\"s7Z7Ld\"],[45449446,null,true,null,null,null,\"ktxJzc\"],[45449468,null,null,null,\"variant2\",null,\"BUEcUe\"],[45659313,null,false,null,null,null,\"i2rGv\"],[45532646,null,true,null,null,null,\"RIvlU\"],[45449439,null,true,null,null,null,\"lsuui\"],[45650156,null,false,null,null,null,\"Pr5Lcf\"],[45449422,null,null,null,\"default\",null,\"epsxQe\"],[45628378,null,true,null,null,null,\"hRRuzd\"],[45651724,null,true,null,null,null,\"xYDLRc\"],[45662552,null,false,null,null,null,\"epuB3d\"],[45449444,null,true,null,null,null,\"HGJqie\"],[45655733,null,true,null,null,null,\"xPTOyb\"],[45663526,null,false,null,null,null,\"kG33G\"]],\"CAMSHR0c3M2IEK/+BPfvF8K/sBKhkOMGFrecDRbN9Q14\"]]]","UUFaWc":"%.@.null,1000,2]","Vvafkd":false,"Yllh3e":"%.@.1732705252485894,12007801,1929950302]","aAofAd":"%.@.[[[\"Solutions \\u0026 technology\",null,[[[\"AI \\u0026 Machine Learning\",\"/blog/products/ai-machine-learning\"],[\"API Management\",\"/blog/products/api-management\"],[\"Application Development\",\"/blog/products/application-development\"],[\"Application Modernization\",\"/blog/products/application-modernization\"],[\"Chrome Enterprise\",\"/blog/products/chrome-enterprise\"],[\"Compute\",\"/blog/products/compute\"],[\"Containers \\u0026 Kubernetes\",\"/blog/products/containers-kubernetes\"],[\"Data Analytics\",\"/blog/products/data-analytics\"],[\"Databases\",\"/blog/products/databases\"],[\"DevOps \\u0026 SRE\",\"/blog/products/devops-sre\"],[\"Maps \\u0026 Geospatial\",\"/blog/topics/maps-geospatial\"],[\"Security\",null,[[[\"Security \\u0026 Identity\",\"/blog/products/identity-security\"],[\"Threat Intelligence\",\"/blog/topics/threat-intelligence\"]]]],[\"Infrastructure\",\"/blog/products/infrastructure\"],[\"Infrastructure Modernization\",\"/blog/products/infrastructure-modernization\"],[\"Networking\",\"/blog/products/networking\"],[\"Productivity \\u0026 Collaboration\",\"/blog/products/productivity-collaboration\"],[\"SAP on Google Cloud\",\"/blog/products/sap-google-cloud\"],[\"Storage \\u0026 Data Transfer\",\"/blog/products/storage-data-transfer\"],[\"Sustainability\",\"/blog/topics/sustainability\"]]]],[\"Ecosystem\",null,[[[\"IT Leaders\",\"/transform\"],[\"Industries\",null,[[[\"Financial Services\",\"/blog/topics/financial-services\"],[\"Healthcare \\u0026 Life Sciences\",\"/blog/topics/healthcare-life-sciences\"],[\"Manufacturing\",\"/blog/topics/manufacturing\"],[\"Media \\u0026 Entertainment\",\"/blog/products/media-entertainment\"],[\"Public Sector\",\"/blog/topics/public-sector\"],[\"Retail\",\"/blog/topics/retail\"],[\"Supply Chain\",\"/blog/topics/supply-chain-logistics\"],[\"Telecommunications\",\"/blog/topics/telecommunications\"]]]],[\"Partners\",\"/blog/topics/partners\"],[\"Startups \\u0026 SMB\",\"/blog/topics/startups\"],[\"Training \\u0026 Certifications\",\"/blog/topics/training-certifications\"],[\"Inside Google Cloud\",\"/blog/topics/inside-google-cloud\"],[\"Google Cloud Next \\u0026 Events\",\"/blog/topics/google-cloud-next\"],[\"Google Maps Platform\",\"https://mapsplatform.google.com/resources/blog/\"],[\"Google Workspace\",\"https://workspace.google.com/blog\"]]]],[\"Developers \\u0026 Practitioners\",\"/blog/topics/developers-practitioners\"],[\"Transform with Google Cloud\",\"/transform\"]]],[[\"de\",[[[\"Neuigkeiten\",\"/blog/de/topics/whats-new/aktuelles-auf-dem-google-cloud-blog\"],[\"Lösungen \\u0026 Technologien\",null,[[[\"Anwendungsentwicklung\",\"/blog/de/products/application-development\"],[\"Anwendungsmodernisierung\",\"/blog/de/products/anwendungsmodernisierung\"],[\"API-Verwaltung\",\"/blog/de/products/api-management\"],[\"Chrome Enterprise\",\"/blog/de/products/chrome-enterprise\"],[\"Computing\",\"/blog/de/products/compute\"],[\"Containers \\u0026 Kubernetes\",\"/blog/de/products/containers-kubernetes\"],[\"Datenanalysen\",\"/blog/de/products/data-analytics\"],[\"Datenbanken\",\"/blog/de/products/databases\"],[\"DevOps \\u0026 SRE\",\"/blog/de/products/devops-sre\"],[\"Infrastruktur\",\"/blog/de/products/infrastructure\"],[\"KI \\u0026 Machine Learning\",\"/blog/de/products/ai-machine-learning\"],[\"Maps \\u0026 Geospatial\",\"/blog/de/topics/maps-geospatial\"],[\"Modernisierung der Infrastruktur\",\"/blog/de/products/modernisierung-der-infrastruktur\"],[\"Nachhaltigkeit\",\"/blog/de/topics/nachhaltigkeit\"],[\"Netzwerk\",\"/blog/de/products/networking\"],[\"Produktivität und Zusammenarbeit\",\"/blog/de/products/produktivitaet-und-kollaboration\"],[\"SAP in Google Cloud\",\"/blog/de/products/sap-google-cloud\"],[\"Sicherheit \\u0026 Identität\",\"/blog/de/products/identity-security\"],[\"Speicher und Datentransfer\",\"/blog/de/products/storage-data-transfer\"]]]],[\"Ökosystem\",null,[[[\"IT Leader\",\"/transform/de\"],[\"Industrien\",null,[[[\"Behörden und öffentlicher Sektor\",\"/blog/de/topics/public-sector\"],[\"Einzelhandel\",\"/blog/de/topics/retail\"],[\"Fertigung\",\"/blog/de/topics/fertigung\"],[\"Finanzdienstleistungen\",\"/blog/de/topics/financial-services\"],[\"Gesundheitswesen und Biowissenschaften\",\"/blog/de/topics/healthcare-life-sciences\"],[\"Lieferkette und Logistik\",\"/blog/de/topics/lieferkette-und-logistik\"],[\"Medien und Unterhaltung\",\"/blog/de/products/media-entertainment\"],[\"Telekommunikation\",\"/blog/de/topics/telecommunications\"]]]],[\"Entwickler*innen \\u0026 Fachkräfte\",\"/blog/de/topics/developers-practitioners\"],[\"Google Cloud Next \\u0026 Events\",\"/blog/de/topics/events\"],[\"Google Maps Platform\",\"/blog/de/products/maps-platform\"],[\"Google Workspace\",\"https://workspace.google.com/blog/de\"],[\"Inside Google Cloud\",\"/blog/de/topics/inside-google-cloud\"],[\"Kunden\",\"/blog/de/topics/kunden\"],[\"Partner\",\"/blog/de/topics/partners\"],[\"Start-ups und KMU\",\"/blog/de/topics/startups\"],[\"Training und Zertifizierung\",\"/blog/de/topics/training-certifications\"]]]],[\"Transformation mit Google Cloud\",\"/transform/de\"]]]],[\"en\",[[[\"Solutions \\u0026 technology\",null,[[[\"AI \\u0026 Machine Learning\",\"/blog/products/ai-machine-learning\"],[\"API Management\",\"/blog/products/api-management\"],[\"Application Development\",\"/blog/products/application-development\"],[\"Application Modernization\",\"/blog/products/application-modernization\"],[\"Chrome Enterprise\",\"/blog/products/chrome-enterprise\"],[\"Compute\",\"/blog/products/compute\"],[\"Containers \\u0026 Kubernetes\",\"/blog/products/containers-kubernetes\"],[\"Data Analytics\",\"/blog/products/data-analytics\"],[\"Databases\",\"/blog/products/databases\"],[\"DevOps \\u0026 SRE\",\"/blog/products/devops-sre\"],[\"Maps \\u0026 Geospatial\",\"/blog/topics/maps-geospatial\"],[\"Security\",null,[[[\"Security \\u0026 Identity\",\"/blog/products/identity-security\"],[\"Threat Intelligence\",\"/blog/topics/threat-intelligence\"]]]],[\"Infrastructure\",\"/blog/products/infrastructure\"],[\"Infrastructure Modernization\",\"/blog/products/infrastructure-modernization\"],[\"Networking\",\"/blog/products/networking\"],[\"Productivity \\u0026 Collaboration\",\"/blog/products/productivity-collaboration\"],[\"SAP on Google Cloud\",\"/blog/products/sap-google-cloud\"],[\"Storage \\u0026 Data Transfer\",\"/blog/products/storage-data-transfer\"],[\"Sustainability\",\"/blog/topics/sustainability\"]]]],[\"Ecosystem\",null,[[[\"IT Leaders\",\"/transform\"],[\"Industries\",null,[[[\"Financial Services\",\"/blog/topics/financial-services\"],[\"Healthcare \\u0026 Life Sciences\",\"/blog/topics/healthcare-life-sciences\"],[\"Manufacturing\",\"/blog/topics/manufacturing\"],[\"Media \\u0026 Entertainment\",\"/blog/products/media-entertainment\"],[\"Public Sector\",\"/blog/topics/public-sector\"],[\"Retail\",\"/blog/topics/retail\"],[\"Supply Chain\",\"/blog/topics/supply-chain-logistics\"],[\"Telecommunications\",\"/blog/topics/telecommunications\"]]]],[\"Partners\",\"/blog/topics/partners\"],[\"Startups \\u0026 SMB\",\"/blog/topics/startups\"],[\"Training \\u0026 Certifications\",\"/blog/topics/training-certifications\"],[\"Inside Google Cloud\",\"/blog/topics/inside-google-cloud\"],[\"Google Cloud Next \\u0026 Events\",\"/blog/topics/google-cloud-next\"],[\"Google Maps Platform\",\"https://mapsplatform.google.com/resources/blog/\"],[\"Google Workspace\",\"https://workspace.google.com/blog\"]]]],[\"Developers \\u0026 Practitioners\",\"/blog/topics/developers-practitioners\"],[\"Transform with Google Cloud\",\"/transform\"]]]],[\"fr\",[[[\"Les tendances\",\"/blog/fr/topics/les-tendances/quelles-sont-les-nouveautes-de-google-cloud\"],[\"Solutions et Technologie\",null,[[[\"Analyse de données\",\"/blog/fr/products/analyse-de-donnees/\"],[\"Bases de données\",\"/blog/fr/products/databases\"],[\"Calcul\",\"/blog/fr/products/calcul/\"],[\"Chrome Entreprise\",\"/blog/fr/products/chrome-enterprise/\"],[\"Conteneurs et Kubernetes\",\"/blog/fr/products/conteneurs-et-kubernetes/\"],[\"Développement d\u0027Applications\",\"/blog/fr/products/application-development\"],[\"Développement durable\",\"/blog/fr/topics/developpement-durable\"],[\"DevOps et ingénierie SRE\",\"/blog/fr/products/devops-sre\"],[\"Gestion des API\",\"/blog/fr/products/api-management\"],[\"IA et Machine Learning\",\"/blog/fr/products/ai-machine-learning\"],[\"Infrastructure\",\"/blog/fr/products/infrastructure\"],[\"Maps et Géospatial\",\"/blog/fr/topics/maps-geospatial\"],[\"Modernisation d\u0027Applications\",\"/blog/fr/products/modernisation-dapplications/\"],[\"Modernisation d\u0027Infrastructure\",\"/blog/fr/products/modernisation-dinfrastructure/\"],[\"Networking\",\"/blog/fr/products/networking\"],[\"Productivité et Collaboration\",\"/blog/fr/products/productivite-et-collaboration\"],[\"SAP sur Google Cloud\",\"/blog/fr/products/sap-google-cloud\"],[\"Sécurité et Identité\",\"/blog/fr/products/identity-security\"],[\"Stockage et transfert de données\",\"/blog/fr/products/storage-data-transfer\"]]]],[\"Écosystème\",null,[[[\"Responsables IT\",\"/transform/fr\"],[\"Industries\",null,[[[\"Commerce\",\"/blog/fr/topics/retail\"],[\"Manufacturing\",\"/blog/fr/topics/manufacturing\"],[\"Médias et Divertissement\",\"/blog/fr/products/media-entertainment\"],[\"Santé\",\"/blog/fr/topics/healthcare-life-sciences\"],[\"Secteur Public\",\"/blog/fr/topics/public-sector\"],[\"Services Financiers\",\"/blog/fr/topics/financial-services\"],[\"Supply Chain\",\"/blog/fr/topics/supply-chain/\"],[\"Telecommunications\",\"/blog/fr/topics/telecommunications\"]]]],[\"Clients\",\"/blog/fr/topics/clients/\"],[\"Développeurs et professionnels\",\"/blog/fr/topics/developers-practitioners\"],[\"Formations et certifications\",\"/blog/fr/topics/training-certifications\"],[\"Google Cloud Next et Événements\",\"/blog/fr/topics/evenements\"],[\"Google Maps Platform\",\"/blog/fr/products/maps-platform\"],[\"Google Workspace\",\"https://workspace.google.com/blog/fr\"],[\"Inside Google Cloud\",\"/blog/fr/topics/inside-google-cloud\"],[\"Partenaires\",\"/blog/fr/topics/partners\"],[\"Start-ups et PME\",\"/blog/fr/topics/startups\"]]]],[\"Transformer avec Google Cloud\",\"/transform/fr\"]]]],[\"ja\",[[[\"ソリューションとテクノロジー\",null,[[[\"AI \\u0026 機械学習\",\"/blog/ja/products/ai-machine-learning\"],[\"API 管理\",\"/blog/ja/products/api-management\"],[\"アプリケーション開発\",\"/blog/ja/products/application-development\"],[\"アプリケーションモダナイゼーション\",\"/blog/ja/products/application-modernization\"],[\"Chrome Enterprise\",\"/blog/ja/products/chrome-enterprise\"],[\"コンピューティング\",\"/blog/ja/products/compute\"],[\"Containers \\u0026 Kubernetes\",\"/blog/ja/products/containers-kubernetes\"],[\"データ分析\",\"/blog/ja/products/data-analytics\"],[\"データベース\",\"/blog/ja/products/databases\"],[\"DevOps \\u0026 SRE\",\"/blog/ja/products/devops-sre\"],[\"Maps \\u0026 Geospatial\",\"/blog/ja/products/maps-platform\"],[\"セキュリティ\",null,[[[\"セキュリティ \\u0026 アイデンティティ\",\"/blog/ja/products/identity-security\"],[\"脅威インテリジェンス\",\"/blog/ja/topics/threat-intelligence\"]]]],[\"インフラストラクチャ\",\"/blog/ja/products/infrastructure\"],[\"インフラモダナイゼーション\",\"/blog/ja/products/infrastructure-modernization\"],[\"ネットワーキング\",\"/blog/ja/products/networking\"],[\"生産性とコラボレーション\",\"/blog/ja/products/productivity-collaboration\"],[\"Google Cloud での SAP\",\"/blog/ja/products/sap-google-cloud\"],[\"ストレージとデータ転送\",\"/blog/ja/products/storage-data-transfer\"],[\"サステナビリティ\",\"/blog/ja/topics/sustainability\"]]]],[\"エコシステム\",null,[[[\"ITリーダー\",\"/transform/ja\"],[\"業種\",null,[[[\"金融サービス\",\"/blog/ja/topics/financial-services\"],[\"ヘルスケア、ライフサイエンス\",\"/blog/ja/topics/healthcare-life-sciences\"],[\"製造\",\"/blog/ja/topics/manufacturing\"],[\"メディア、エンターテイメント\",\"/blog/ja/products/media-entertainment\"],[\"公共部門\",\"/blog/ja/topics/public-sector\"],[\"小売業\",\"/blog/ja/topics/retail\"],[\"サプライチェーン\",\"/blog/ja/topics/supply-chain-logistics\"],[\"通信\",\"/blog/ja/topics/telecommunications\"]]]],[\"顧客事例\",\"/blog/ja/topics/customers\"],[\"パートナー\",\"/blog/ja/topics/partners\"],[\"スタートアップ \\u0026 SMB\",\"/blog/ja/topics/startups\"],[\"トレーニングと認定\",\"/blog/ja/topics/training-certifications\"],[\"Inside Google Cloud\",\"/blog/ja/topics/inside-google-cloud\"],[\"Google Cloud Next とイベント\",\"/blog/ja/topics/google-cloud-next\"],[\"Google Maps Platform\",\"/blog/ja/products/maps-platform\"],[\"Google Workspace\",\"https://workspace.google.com/blog/ja\"]]]],[\"デベロッパー\",\"/blog/ja/topics/developers-practitioners\"],[\"Transform with Google Cloud\",\"/transform/ja\"]]]],[\"ko\",[[[\"솔루션 및 기술\",null,[[[\"AI 및 머신러닝\",\"/blog/ko/products/ai-machine-learning\"],[\"API 관리\",\"/blog/ko/products/api-management\"],[\"애플리케이션 개발\",\"/blog/ko/products/application-development\"],[\"애플리케이션 현대화\",\"/blog/ko/products/application-modernization\"],[\"Chrome Enterprise\",\"/blog/products/chrome-enterprise\"],[\"컴퓨팅\",\"/blog/ko/products/compute\"],[\"컨테이너 \\u0026 Kubernetes\",\"/blog/ko/products/containers-kubernetes\"],[\"데이터 분석\",\"/blog/ko/products/data-analytics\"],[\"데이터베이스\",\"/blog/ko/products/databases\"],[\"DevOps 및 SRE\",\"/blog/ko/products/devops-sre\"],[\"Maps \\u0026 Geospatial\",\"/blog/ko/products/maps-platform\"],[\"보안\",null,[[[\"보안 \\u0026 아이덴티티\",\"/blog/ko/products/identity-security\"],[\"위협 인텔리전스\",\"/blog/ko/topics/threat-intelligence\"]]]],[\"인프라\",\"/blog/ko/products/infrastructure\"],[\"Infrastructure Modernization\",\"/blog/ko/products/infrastructure-modernization\"],[\"네트워킹\",\"/blog/ko/products/networking\"],[\"생산성 및 공동작업\",\"/blog/ko/products/productivity-collaboration\"],[\"SAP on Google Cloud\",\"/blog/ko/products/sap-google-cloud\"],[\"스토리지 및 데이터 전송\",\"/blog/ko/products/storage-data-transfer\"],[\"지속가능성\",\"/blog/ko/topics/sustainability\"]]]],[\"에코시스템\",null,[[[\"IT Leaders\",\"/transform/ko\"],[\"업종\",null,[[[\"금융 서비스\",\"/blog/ko/topics/financial-services\"],[\"의료 및 생명과학\",\"/blog/ko/topics/healthcare-life-sciences\"],[\"제조업\",\"/blog/ko/topics/manufacturing\"],[\"미디어 및 엔터테인먼트\",\"/blog/ko/products/media-entertainment\"],[\"공공부문\",\"/blog/ko/topics/public-sector\"],[\"소매업\",\"/blog/ko/topics/retail\"],[\"공급망\",\"/blog/topics/supply-chain-logistics\"],[\"통신\",\"/blog/ko/topics/telecommunications\"]]]],[\"고객 사례\",\"/blog/ko/topics/customers\"],[\"파트너\",\"/blog/ko/topics/partners\"],[\"스타트업 \\u0026 SMB\",\"/blog/ko/topics/startups\"],[\"교육 \\u0026 인증\",\"/blog/ko/topics/training-certifications\"],[\"Inside Google Cloud\",\"/blog/ko/topics/inside-google-cloud\"],[\"Google Cloud Next 및 이벤트\",\"/blog/ko/topics/google-cloud-next\"],[\"Google Maps Platform\",\"/blog/ko/products/maps-platform\"],[\"Google Workspace\",\"https://workspace.google.com/blog/ko\"]]]],[\"개발 및 IT운영\",\"/blog/ko/topics/developers-practitioners\"],[\"Google Cloud와 함께 하는 디지털 혁신\",\"/transform/ko\"]]]]]]","cfb2h":"boq_cloudx-web-blog-uiserver_20241121.08_p0","eptZe":"/blog/_/TransformBlogUi/","f8POw":"%.@.[97656899,97863170,97517172,97535270,48887082,93778619,97442199,48554500,1706538,97785988,1714240,93874004,97684535,97863042,48830069,97716267,48489819,97656881,97517154,48887064,97442181,97785970,93873986,97684517],null,null,null,null,true]","fPDxwd":[97517172,97684535,97863042,97863170],"gGcLoe":false,"iCzhFc":false,"nQyAE":{"b5B1L":"true","PTNaKe":"false","ktxJzc":"true","BUEcUe":"variant2","XzXOC":"true","kG32O":"false","C4H3Td":"true","w1axY":"false","Pr5Lcf":"false","kG33G":"false","OEmSkb":"false","aeNUHe":"false","j9nUqf":"false","wvKxS":"false","wFnpse":"true","tfPPe":"false","LibkZ":"false","m0uJSe":"false","PvZHQ":"true","s7Z7Ld":"false","i2rGv":"false","RIvlU":"true","lsuui":"true","HGJqie":"true","NCoWOd":"false","Qzt9sd":"false","dsKk4d":"true","fdXYmb":"false","epuB3d":"false","BotAtd":"true"},"p9hQne":"https://www.gstatic.com/_/boq-cloudx-web-blog/_/r/","qwAQke":"TransformBlogUi","rtQCxc":-480,"u4g7r":"%.@.null,1000,2]","vJ2GOe":"%.@.null,[[\"de\",[[[\"Themen\",null,[[[\"Product Announcements\",\"/blog/de/product-announcements\"],[\"KI \\u0026 Machine Learning\",\"/blog/de/ai-machine-learning\"],[\"Produktivität und Kollaboration\",\"/blog/de/productivity-collaboration\"],[\"Identität und Sicherheit\",\"/blog/de/identity-and-security\"],[\"Future of Work\",\"/blog/de/future-of-work\"],[\"Hybrides Arbeiten\",\"/blog/de/hybrid-work\"],[\"Kundenreferenzen\",\"/blog/de/customer-stories\"],[\"Entwickler*innen und Fachkräfte\",\"/blog/de/developers-practitioners\"],[\"Partner\",\"/blog/de/partners\"],[\"Events\",\"/blog/de/events\"],[\"Öffentlicher Sektor\",\"/blog/de/public-sector\"]]]],[\"Produktneuigkeiten\",null,[[[\"Gmail\",\"/blog/de/gmail\"],[\"Meet\",\"/blog/de/meet\"],[\"Chat and Spaces\",\"/blog/de/chat-spaces\"],[\"Drive\",\"/blog/de/drive\"],[\"Docs\",\"/blog/de/docs\"],[\"Sheets\",\"/blog/de/sheets\"]]]]]]],[\"en\",[[[\"Topics\",null,[[[\"Product Announcements\",\"/blog/product-announcements\"],[\"AI and Machine Learning\",\"/blog/ai-machine-learning\"],[\"Productivity and Collaboration\",\"/blog/productivity-collaboration\"],[\"Identity and Security\",\"/blog/identity-and-security\"],[\"Future of Work\",\"/blog/future-of-work\"],[\"Hybrid Work\",\"/blog/hybrid-work\"],[\"Customer Stories\",\"/blog/customer-stories\"],[\"Developers and Practitioners\",\"/blog/developers-practitioners\"],[\"Partners\",\"/blog/partners\"],[\"Events\",\"/blog/events\"],[\"Public Sector\",\"/blog/public-sector\"]]]],[\"Product News\",null,[[[\"Gmail\",\"/blog/gmail\"],[\"Meet\",\"/blog/meet\"],[\"Chat and Spaces\",\"/blog/chat-spaces\"],[\"Drive\",\"/blog/drive\"],[\"Docs\",\"/blog/docs\"],[\"Sheets\",\"/blog/sheets\"]]]]]]],[\"fr\",[[[\"Thèmes\",null,[[[\"Product Announcements\",\"/blog/fr/product-announcements\"],[\"IA et Machine Learning\",\"/blog/fr/ai-machine-learning\"],[\"Productivité et Collaboration\",\"/blog/fr/productivity-collaboration\"],[\"Identité et Sécurité\",\"/blog/fr/identity-and-security\"],[\"L\u0027avenir du travail\",\"/blog/fr/future-of-work\"],[\"Travail hybride\",\"/blog/fr/hybrid-work\"],[\"Témoignages Clients\",\"/blog/fr/customer-stories\"],[\"Développeurs et professionnels\",\"/blog/fr/developers-practitioners\"],[\"Partenaires\",\"/blog/fr/partners\"],[\"Événements\",\"/blog/fr/events\"],[\"Secteur Public\",\"/blog/fr/public-sector\"]]]],[\"Annonces sur les produits\",null,[[[\"Gmail\",\"/blog/fr/gmail\"],[\"Meet\",\"/blog/fr/meet\"],[\"Chat et Spaces\",\"/blog/fr/chat-spaces\"],[\"Drive\",\"/blog/fr/drive\"],[\"Docs\",\"/blog/fr/docs\"],[\"Sheets\",\"/blog/fr/sheets\"]]]]]]],[\"ja\",[[[\"トピック\",null,[[[\"プロダクトの発表\",\"/blog/ja/product-announcements\"],[\"AI \\u0026 機械学習\",\"/blog/ja/ai-machine-learning\"],[\"生産性とコラボレーション\",\"/blog/ja/productivity-collaboration\"],[\"アイデンティティとセキュリティ\",\"/blog/ja/identity-and-security\"],[\"未来の働き方\",\"/blog/ja/future-of-work\"],[\"ハイブリッドな働き方\",\"/blog/ja/hybrid-work\"],[\"顧客事例\",\"/blog/ja/customer-stories\"],[\"デベロッパー\",\"/blog/ja/developers-practitioners\"],[\"パートナー\",\"/blog/ja/partners\"],[\"イベント\",\"/blog/ja/events\"],[\"公共部門\",\"/blog/ja/public-sector\"]]]],[\"製品ニュース\",null,[[[\"Gmail\",\"/blog/ja/gmail\"],[\"Meet\",\"/blog/ja/meet\"],[\"Chat and Spaces\",\"/blog/ja/chat-spaces\"],[\"ドライブ\",\"/blog/ja/drive\"],[\"ドキュメント\",\"/blog/ja/docs\"],[\"スプレッドシート\",\"/blog/ja/sheets\"]]]]]]],[\"ko\",[[[\"주제\",null,[[[\"제품 업데이트\",\"/blog/ko/product-announcements\"],[\"AI 및 머신러닝\",\"/blog/ko/ai-machine-learning\"],[\"생산성 및 공동작업\",\"/blog/ko/productivity-collaboration\"],[\"인증 및 보안 \",\"/blog/ko/identity-and-security\"],[\"Future of Work\",\"/blog/ko/future-of-work\"],[\"하이브리드 업무\",\"/blog/ko/hybrid-work\"],[\"고객 사례\",\"/blog/ko/customer-stories\"],[\"개발자\",\"/blog/ko/developers-practitioners\"],[\"파트너\",\"/blog/ko/partners\"],[\"이벤트\",\"/blog/ko/events\"],[\"공공부문\",\"/blog/ko/public-sector\"]]]],[\"제품 소식\",null,[[[\"Gmail\",\"/blog/ko/gmail\"],[\"Meet\",\"/blog/ko/meet\"],[\"Chat 및 Spaces\",\"/blog/ko/chat-spaces\"],[\"Drive\",\"/blog/ko/drive\"],[\"Docs\",\"/blog/ko/docs\"],[\"Sheets\",\"/blog/ko/sheets\"]]]]]]]],null,[[\"de\",[[[[[\"Enthaltene Anwendungen\",\"https://workspace.google.com/intl/de/features/\",[[[\"Gmail\",\"https://workspace.google.com/intl/de/products/gmail/\"],[\"Meet\",\"https://workspace.google.com/intl/de/products/meet/\"],[\"Chat\",\"https://workspace.google.com/intl/de/products/chat/\"],[\"Kalender\",\"https://workspace.google.com/intl/de/products/calendar/\"],[\"Drive\",\"https://workspace.google.com/intl/de/products/drive/\"],[\"Docs\",\"https://workspace.google.com/intl/de/products/docs/\"],[\"Tabellen\",\"https://workspace.google.com/intl/de/products/sheets/\"],[\"Präsentationen\",\"https://workspace.google.com/intl/de/products/slides/\"],[\"Formulare\",\"https://workspace.google.com/intl/de/products/forms/\"],[\"Sites\",\"https://workspace.google.com/intl/de/products/sites/\"],[\"Notizen\",\"https://workspace.google.com/intl/de/products/keep/\"],[\"Apps Script\",\"https://workspace.google.com/intl/de/products/apps-script/\"]]]]]],[[[\"Sicherheit und Verwaltung\",\"https://workspace.google.com/intl/de/security/\",[[[\"Admin\",\"https://workspace.google.com/intl/de/products/admin/\"],[\"Endpunkt\",\"https://workspace.google.com/intl/de/products/admin/endpoint/\"],[\"Vault\",\"https://workspace.google.com/intl/de/products/vault/\"],[\"Work Insights\",\"https://workspace.google.com/intl/de/products/workinsights/\"]]]],[\"Lösungen\",\"https://workspace.google.com/intl/de/solutions/\",[[[\"Neue Unternehmen\",\"https://workspace.google.com/intl/de/business/new-business/\"],[\"Kleine Unternehmen\",\"https://workspace.google.com/intl/de/business/small-business/\"],[\"Große Unternehmen\",\"https://workspace.google.com/intl/de/solutions/enterprise/\"],[\"Education\",\"https://edu.google.com/products/workspace-for-education/education-fundamentals/\"],[\"Nonprofit-Organisationen\",\"https://www.google.com/nonprofits/\"]]]]]],[[[\"Preise\",\"https://workspace.google.com/intl/de/pricing.html\",[[[\"Version auswählen\",\"https://workspace.google.com/intl/de/pricing.html\"]]]],[\"Add-ons\",null,[[[\"Gemini für Workspace\",\"https://workspace.google.com/solutions/ai/\"],[\"Google Voice\",\"https://workspace.google.com/intl/de/products/voice/\"],[\"AppSheet\",\"https://about.appsheet.com/home/\"]]]]]],[[[\"Ressourcen\",\"https://workspace.google.com/intl/de/faq/\",[[[\"Telearbeit\",\"https://workspace.google.com/intl/de/working-remotely/\"],[\"Sicherheit\",\"https://workspace.google.com/intl/de/security/\"],[\"FAQ\",\"https://workspace.google.com/intl/de/faq/\"],[\"Partner\",\"https://cloud.withgoogle.com/partners/?products\\u003dGOOGLE_WORKSPACE_PRODUCT\"],[\"Google Workspace Marketplace\",\"https://workspace.google.com/marketplace/\"],[\"Integrationen\",\"https://workspace.google.com/intl/de/integrations/\"],[\"Schulung \\u0026 Zertifizierung\",\"https://workspace.google.com/intl/de/training/\"]]]]]],[[[\"Schulung und Support\",\"https://workspace.google.com/intl/de/support/\",[[[\"Admin-Hilfe\",\"https://support.google.com/a/#topic\\u003d29157\"],[\"Einrichtungs- und Bereitstellungscenter\",\"https://workspace.google.com/setup/?hl\\u003dde\"],[\"Schulungscenter für Nutzer\",\"https://workspace.google.com/intl/de/learning-center/\"],[\"Foren für Administratoren\",\"https://productforums.google.com/forum/#!forum/apps\"],[\"Google Workspace-Dashboard\",\"https://www.google.com/appsstatus\"],[\"Presse\",\"https://cloud.google.com/press/\"]]]],[\"Mehr von Google\",null,[[[\"Google Cloud\",\"https://cloud.google.com/?hl\\u003dde\"],[\"Chrome Enterprise\",\"https://chromeenterprise.google/\"],[\"Google Lösungen für Unternehmen\",\"https://www.google.com/intl/de/services/\"],[\"Google Ads\",\"https://ads.google.com/home/?subid\\u003dde-de-xs-aw-z-a-dyn-accounts_wsft!o3\"],[\"Business Messages\",\"https://businessmessages.google/\"],[\"An Nutzerstudien teilnehmen\",\"https://userresearch.google.com/?reserved\\u003d0\\u0026utm_source\\u003dgsuite.google.com\\u0026Q_Language\\u003den\\u0026utm_medium\\u003down_srch\\u0026utm_campaign\\u003dGlobal-GSuite\\u0026utm_term\\u003d0\\u0026utm_content\\u003d0\\u0026productTag\\u003dgafw\\u0026campaignDate\\u003dnov18\\u0026pType\\u003dbprof\\u0026referral_code\\u003dug422768\"]]]]]]]]],[\"en\",[[[[[\"Included applications\",\"https://workspace.google.com/features/\",[[[\"Gmail\",\"https://workspace.google.com/products/gmail/\"],[\"Meet\",\"https://workspace.google.com/products/meet/\"],[\"Chat\",\"https://workspace.google.com/products/chat/\"],[\"Calendar\",\"https://workspace.google.com/products/calendar/\"],[\"Drive\",\"https://workspace.google.com/products/drive/\"],[\"Docs\",\"https://workspace.google.com/products/docs/\"],[\"Sheets\",\"https://workspace.google.com/products/sheets/\"],[\"Slides\",\"https://workspace.google.com/products/slides/\"],[\"Forms\",\"https://workspace.google.com/products/forms/\"],[\"Sites\",\"https://workspace.google.com/products/sites/\"],[\"Keep\",\"https://workspace.google.com/products/keep/\"],[\"Apps Script\",\"https://workspace.google.com/products/apps-script/\"]]]]]],[[[\"Security and management\",\"https://workspace.google.com/security/\",[[[\"Admin\",\"https://workspace.google.com/products/admin/\"],[\"Endpoint\",\"https://workspace.google.com/products/admin/endpoint/\"],[\"Vault\",\"https://workspace.google.com/products/vault/\"],[\"Work Insights\",\"https://workspace.google.com/products/workinsights/\"]]]],[\"Solutions\",\"https://workspace.google.com/solutions/\",[[[\"New Business\",\"https://workspace.google.com/business/new-business/\"],[\"Small Business\",\"https://workspace.google.com/business/small-business/\"],[\"Enterprise\",\"https://workspace.google.com/solutions/enterprise/\"],[\"Retail\",\"https://workspace.google.com/industries/retail/\"],[\"Manufacturing\",\"https://workspace.google.com/industries/manufacturing/\"],[\"Professional Services\",\"https://workspace.google.com/industries/professional-services/\"],[\"Technology\",\"https://workspace.google.com/industries/technology/\"],[\"Healthcare\",\"https://workspace.google.com/industries/healthcare/\"],[\"Government\",\"https://workspace.google.com/industries/government/\"],[\"Education\",\"https://edu.google.com/products/workspace-for-education/education-fundamentals/\"],[\"Nonprofits\",\"https://www.google.com/nonprofits/\"],[\"Artificial Intelligence\",\"https://workspace.google.com/solutions/ai/\"]]]]]],[[[\"Pricing\",\"https://workspace.google.com/pricing.html\",[[[\"Compare pricing plans\",\"https://workspace.google.com/pricing.html\"]]]],[\"Add-ons\",null,[[[\"Gemini for Workspace\",\"https://workspace.google.com/solutions/ai/\"],[\"Meet hardware\",\"https://workspace.google.com/products/meet-hardware/\"],[\"Google Voice\",\"https://workspace.google.com/products/voice/\"],[\"AppSheet\",\"https://about.appsheet.com/home/\"]]]]]],[[[\"Resources\",\"https://workspace.google.com/faq/\",[[[\"Working remotely\",\"https://workspace.google.com/working-remotely/\"],[\"Security\",\"https://workspace.google.com/security/\"],[\"Customer Stories\",\"https://workspace.google.com/customers/\"],[\"FAQs\",\"https://workspace.google.com/faq/\"],[\"Partners\",\"https://cloud.withgoogle.com/partners/?products\\u003dGOOGLE_WORKSPACE_PRODUCT\"],[\"Marketplace\",\"https://workspace.google.com/marketplace/\"],[\"Integrations\",\"https://workspace.google.com/integrations/\"],[\"Training \\u0026 Certification\",\"https://workspace.google.com/training/\"],[\"Refer Google Workspace\",\"https://workspace.google.com/landing/partners/referral/\"]]]]]],[[[\"Learning and support\",\"https://workspace.google.com/support/\",[[[\"Admin Help\",\"https://support.google.com/a/#topic\\u003d29157\"],[\"Setup and Deployment Center\",\"https://workspace.google.com/setup\"],[\"Learning Center for Users\",\"https://workspace.google.com/learning-center/\"],[\"Forums for Admins\",\"https://productforums.google.com/forum/#!forum/apps\"],[\"Google Workspace Dashboard\",\"https://www.google.com/appsstatus\"],[\"What\u0027s New in Google Workspace\",\"https://workspace.google.com/whatsnew/\"],[\"Find a Google Workspace Partner\",\"https://www.google.com/a/partnersearch/\"],[\"Join the community of IT Admins\",\"https://www.googlecloudcommunity.com/gc/Google-Workspace/ct-p/google-workspace\"],[\"Press\",\"https://cloud.google.com/press/\"]]]],[\"More from Google\",null,[[[\"Google Cloud\",\"https://cloud.google.com/\"],[\"Google Domains\",\"https://domains.google.com/about/?utm_source\\u003dgoogleappsforwork\\u0026utm_medium\\u003dreferral\\u0026utm_campaign\\u003dgooglepromos\"],[\"Chrome Enterprise\",\"https://chromeenterprise.google/\"],[\"Google Business Solutions\",\"https://www.google.com/services/\"],[\"Google Ads\",\"https://ads.google.com/home/?subid\\u003dus-en-xs-aw-z-a-dyn-accounts_wsft!o3\"],[\"Business Messages\",\"https://businessmessages.google/\"],[\"Join User Studies\",\"https://userresearch.google.com/?reserved\\u003d0\\u0026utm_source\\u003dgsuite.google.com\\u0026Q_Language\\u003den\\u0026utm_medium\\u003down_srch\\u0026utm_campaign\\u003dGlobal-GSuite\\u0026utm_term\\u003d0\\u0026utm_content\\u003d0\\u0026productTag\\u003dgafw\\u0026campaignDate\\u003dnov18\\u0026pType\\u003dbprof\\u0026referral_code\\u003dug422768\"]]]]]]]]],[\"fr\",[[[[[\"Enthaltene Anwendungen\",\"https://workspace.google.com/intl/fr/features/\",[[[\"Gmail\",\"https://workspace.google.com/intl/fr/products/gmail/\"],[\"Meet\",\"https://workspace.google.com/intl/fr/products/meet/\"],[\"Chat\",\"https://workspace.google.com/intl/fr/products/chat/\"],[\"Google Agenda\",\"https://workspace.google.com/intl/fr/products/calendar/\"],[\"Drive\",\"https://workspace.google.com/intl/fr/products/drive/\"],[\"Docs\",\"https://workspace.google.com/intl/fr/products/docs/\"],[\"Sheets\",\"https://workspace.google.com/intl/fr/products/sheets/\"],[\"Slides\",\"https://workspace.google.com/intl/fr/products/slides/\"],[\"Forms\",\"https://workspace.google.com/intl/fr/products/forms/\"],[\"Google Sites\",\"https://workspace.google.com/intl/fr/products/sites/\"],[\"Keep\",\"https://workspace.google.com/intl/fr/products/keep/\"],[\"Apps Script\",\"https://workspace.google.com/intl/fr/products/apps-script/\"]]]]]],[[[\"Sécurité et gestion\",\"https://workspace.google.com/intl/fr/security/\",[[[\"Console d\u0027administration\",\"https://workspace.google.com/intl/fr/products/admin/\"],[\"Point de terminaison\",\"https://workspace.google.com/intl/fr/products/admin/endpoint/\"],[\"Vault\",\"https://workspace.google.com/intl/fr/products/vault/\"],[\"Work Insights\",\"https://workspace.google.com/intl/fr/products/workinsights/\"]]]],[\"Solutions\",\"https://workspace.google.com/intl/fr/solutions/\",[[[\"Nouvelle entreprise\",\"https://workspace.google.com/intl/fr/business/new-business/\"],[\"PME\",\"https://workspace.google.com/intl/fr/business/small-business/\"],[\"Grande entreprise\",\"https://workspace.google.com/intl/fr/solutions/enterprise/\"],[\"Education\",\"https://edu.google.com/products/workspace-for-education/education-fundamentals/\"],[\"Associations\",\"https://www.google.com/nonprofits/\"]]]]]],[[[\"Tarifs\",\"https://workspace.google.com/intl/fr/pricing.html\",[[[\"Choisissez une édition\",\"https://workspace.google.com/intl/fr/pricing.html\"]]]],[\"Add-ons\",null,[[[\"Gemini pour Workspace\",\"https://workspace.google.com/solutions/ai/\"],[\"Matériel Meet\",\"https://workspace.google.com/intl/fr/products/meet-hardware/\"],[\"Google Voice\",\"https://workspace.google.com/intl/fr/products/voice/\"],[\"AppSheet\",\"https://about.appsheet.com/home/\"]]]]]],[[[\"Ressources\",\"https://workspace.google.com/intl/fr/faq/\",[[[\"Travail à distance\",\"https://workspace.google.com/intl/fr/working-remotely/\"],[\"Sécurité\",\"https://workspace.google.com/intl/fr/security/\"],[\"Questions fréquentes\",\"https://workspace.google.com/intl/fr/faq/\"],[\"Partenaires\",\"https://cloud.withgoogle.com/partners/?products\\u003dGOOGLE_WORKSPACE_PRODUCT\"],[\"Marketplace\",\"https://workspace.google.com/marketplace/\"],[\"Intégrations\",\"https://workspace.google.com/intl/fr/integrations/\"],[\"Formation et certification\",\"https://workspace.google.com/intl/fr/training/\"]]]]]],[[[\"Formation et assistance\",\"https://workspace.google.com/intl/fr/support/\",[[[\"Aide pour les administrateurs\",\"https://support.google.com/a/#topic\\u003d29157\"],[\"Centre de configuration et de déploiement\",\"https://workspace.google.com/setup/?hl\\u003dfr\"],[\"Centre de formation pour les utilisateurs\",\"https://workspace.google.com/intl/fr/learning-center/\"],[\"Forums pour les administrateurs\",\"https://productforums.google.com/forum/#!forum/apps\"],[\"Tableau de bord Google Workspace\",\"https://www.google.com/appsstatus#hl\\u003dfr\"],[\"Rechercher un partenaire Google Workspace\",\"https://www.google.com/a/partnersearch/?hl\\u003dfr#home\"],[\"Presse\",\"https://cloud.google.com/press/\"]]]],[\"Autres ressources Google\",null,[[[\"Google Cloud\",\"https://cloud.google.com/?hl\\u003dfr\"],[\"Chrome Enterprise\",\"https://chromeenterprise.google/\"],[\"Solutions d\u0027entreprise Google\",\"https://www.google.com/intl/fr/services/\"],[\"Google pour les Pros\",\"https://pourlespros.withgoogle.com/?utm_source\\u003dEngagement\\u0026utm_medium\\u003dep\\u0026utm_term\\u003dSMB\\u0026utm_content\\u003dFR%20Apps%20for%20work%20footert\\u0026utm_campaign\\u003dQ4_2015%20FR%20Apps%20for%20work%20footer\"],[\"Google Ads\",\"https://ads.google.com/home/?subid\\u003dfr-fr-xs-aw-z-a-dyn-accounts_wsft!o3\"],[\"Business Messages\",\"https://businessmessages.google/\"],[\"Participer aux études sur l\u0027expérience utilisateur\",\"https://userresearch.google.com/?reserved\\u003d0\\u0026utm_source\\u003dgsuite.google.com\\u0026Q_Language\\u003den\\u0026utm_medium\\u003down_srch\\u0026utm_campaign\\u003dGlobal-GSuite\\u0026utm_term\\u003d0\\u0026utm_content\\u003d0\\u0026productTag\\u003dgafw\\u0026campaignDate\\u003dnov18\\u0026pType\\u003dbprof\\u0026referral_code\\u003dug422768\"]]]]]]]]],[\"ja\",[[[[[\"ご利用いただけるアプリケーション\",\"https://workspace.google.com/intl/ja/features/\",[[[\"Gmail\",\"https://workspace.google.com/intl/ja/products/gmail/\"],[\"Meet\",\"https://workspace.google.com/intl/ja/products/meet/\"],[\"Chat\",\"https://workspace.google.com/intl/ja/products/chat/\"],[\"カレンダー\",\"https://workspace.google.com/intl/ja/products/calendar/\"],[\"ドライブ\",\"https://workspace.google.com/intl/ja/products/drive/\"],[\"ドキュメント\",\"https://workspace.google.com/intl/ja/products/docs/\"],[\"スプレッドシート\",\"https://workspace.google.com/intl/ja/products/sheets/\"],[\"スライド\",\"https://workspace.google.com/intl/ja/products/slides/\"],[\"フォーム\",\"https://workspace.google.com/intl/ja/products/forms/\"],[\"サイト\",\"https://workspace.google.com/intl/ja/products/sites/\"],[\"Keep\",\"https://workspace.google.com/intl/ja/products/keep/\"],[\"Apps Script\",\"https://workspace.google.com/intl/ja/products/apps-script/\"]]]]]],[[[\"セキュリティと管理\",\"https://workspace.google.com/intl/ja/security/\",[[[\"管理コンソール\",\"https://workspace.google.com/intl/ja/products/admin/\"],[\"エンドポイント\",\"https://workspace.google.com/intl/ja/products/admin/endpoint/\"],[\"Vault\",\"https://workspace.google.com/intl/ja/products/vault/\"],[\"Work Insights\",\"https://workspace.google.com/intl/ja/products/workinsights/\"]]]],[\"ソリューション\",\"https://workspace.google.com/intl/ja/solutions/\",[[[\"新規ビジネス\",\"https://workspace.google.com/intl/ja/business/new-business/\"],[\"小規模ビジネス\",\"https://workspace.google.com/intl/ja/business/small-business/\"],[\"大規模ビジネス\",\"https://workspace.google.com/intl/ja/solutions/enterprise/\"],[\"Education\",\"https://edu.google.com/intl/ja/products/workspace-for-education/education-fundamentals/\"],[\"非営利団体\",\"https://www.google.com/intl/ja/nonprofits/\"]]]]]],[[[\"料金\",\"https://workspace.google.com/intl/ja/pricing.html\",[[[\"エディションを選ぶ\",\"https://workspace.google.com/intl/ja/pricing.html\"]]]],[\"Add-ons\",null,[[[\"Gemini for Workspace\",\"https://workspace.google.com/solutions/ai/\"],[\"Meet ハードウェア\",\"https://workspace.google.com/intl/ja/products/meet-hardware/\"],[\"AppSheet\",\"https://about.appsheet.com/home/\"]]]]]],[[[\"関連情報\",\"https://workspace.google.com/intl/ja/faq/\",[[[\"リモートワーク\",\"https://workspace.google.com/intl/ja/working-remotely/\"],[\"セキュリティ\",\"https://workspace.google.com/intl/ja/security/\"],[\"事例紹介\",\"https://workspace.google.com/intl/ja/customers/\"],[\"よくある質問\",\"https://workspace.google.com/intl/ja/faq/\"],[\"パートナー\",\"https://cloud.withgoogle.com/partners/?products\\u003dGOOGLE_WORKSPACE_PRODUCT\"],[\"Marketplace\",\"https://workspace.google.com/intl/ja/marketplace/\"],[\"統合\",\"https://workspace.google.com/intl/ja/integrations/\"],[\"トレーニングと認定資格\",\"https://workspace.google.com/intl/ja/training/\"]]]]]],[[[\"学習とサポート\",\"https://workspace.google.com/intl/ja/support/\",[[[\"管理者用ヘルプ\",\"https://support.google.com/a/#topic\\u003d29157\"],[\"設定と導入のガイド\",\"https://workspace.google.com/setup/?hl\\u003dja\"],[\"ユーザー向けラーニングセンター\",\"https://workspace.google.com/intl/ja/learning-center/\"],[\"管理者向けフォーラム\",\"https://productforums.google.com/forum/#!forum/apps\"],[\"Google Workspace ステータスダッシュボード\",\"https://www.google.com/appsstatus#hl\\u003dja\"],[\"Google Workspace パートナーを探す\",\"https://www.google.com/a/partnersearch/?hl\\u003dja#home\"],[\"プレスリリース\",\"https://cloud.google.com/press/?hl\\u003dja\"]]]],[\"その他の Google サービス\",null,[[[\"Google Cloud\",\"https://cloud.google.com/?hl\\u003dja\"],[\"Chrome Enterprise\",\"https://chromeenterprise.google/\"],[\"Google ビジネスソリューション\",\"https://www.google.com/intl/ja/services/\"],[\"Google 広告\",\"https://ads.google.com/home/?subid\\u003dja-ja-xs-aw-z-a-dyn-accounts_wsft!o3\"],[\"Business Messages\",\"https://businessmessages.google/\"],[\"ユーザー調査に参加する\",\"https://userresearch.google.com/?reserved\\u003d0\\u0026utm_source\\u003dgsuite.google.com\\u0026Q_Language\\u003den\\u0026utm_medium\\u003down_srch\\u0026utm_campaign\\u003dGlobal-GSuite\\u0026utm_term\\u003d0\\u0026utm_content\\u003d0\\u0026productTag\\u003dgafw\\u0026campaignDate\\u003dnov18\\u0026pType\\u003dbprof\\u0026referral_code\\u003dug422768\"]]]]]]]]],[\"ko\",[[[[[\"포함된 애플리케이션\",\"https://workspace.google.com/intl/ko/features/\",[[[\"Gmail\",\"https://workspace.google.com/intl/ko/products/gmail/\"],[\"Meet\",\"https://workspace.google.com/intl/ko/products/meet/\"],[\"Chat\",\"https://workspace.google.com/intl/ko/products/chat/\"],[\"Calendar\",\"https://workspace.google.com/intl/ko/products/calendar/\"],[\"Drive\",\"https://workspace.google.com/intl/ko/products/drive/\"],[\"Docs\",\"https://workspace.google.com/intl/ko/products/docs/\"],[\"Sheets\",\"https://workspace.google.com/intl/ko/products/sheets/\"],[\"Slides\",\"https://workspace.google.com/intl/ko/products/slides/\"],[\"설문지\",\"https://workspace.google.com/intl/ko/products/forms/\"],[\"사이트 도구\",\"https://workspace.google.com/intl/ko/products/sites/\"],[\"Keep\",\"https://workspace.google.com/intl/ko/products/keep/\"],[\"Apps Script\",\"https://workspace.google.com/intl/ko/products/apps-script/\"]]]]]],[[[\"보안 및 관리\",\"https://workspace.google.com/intl/ko/security/\",[[[\"관리\",\"https://workspace.google.com/intl/ko/products/admin/\"],[\"엔드포인트\",\"https://workspace.google.com/intl/ko/products/admin/endpoint/\"],[\"Vault\",\"https://workspace.google.com/intl/ko/products/vault/\"],[\"Work Insights\",\"https://workspace.google.com/intl/ko/products/workinsights/\"]]]],[\"솔루션\",\"https://workspace.google.com/intl/ko/solutions/\",[[[\"신규 업체\",\"https://workspace.google.com/intl/ko/business/new-business/\"],[\"중소기업\",\"https://workspace.google.com/intl/ko/business/small-business/\"],[\"엔터프라이즈\",\"https://workspace.google.com/intl/ko/solutions/enterprise/\"],[\"Education\",\"https://edu.google.com/products/workspace-for-education/education-fundamentals/\"],[\"비영리단체\",\"https://www.google.com/nonprofits/\"]]]]]],[[[\"가격\",\"https://workspace.google.com/intl/ko/pricing.html\",[[[\"버전 선택\",\"https://workspace.google.com/intl/ko/pricing.html\"]]]],[\"Add-ons\",null,[[[\"Workspace를 위한 Gemini\",\"https://workspace.google.com/solutions/ai/\"],[\"AppSheet\",\"https://about.appsheet.com/home/\"]]]]]],[[[\"리소스\",\"https://workspace.google.com/intl/ko/faq/\",[[[\"원격 근무\",\"https://workspace.google.com/intl/ko/working-remotely/\"],[\"보안\",\"https://workspace.google.com/intl/ko/security/\"],[\"FAQ\",\"https://workspace.google.com/intl/ko/faq/\"],[\"파트너\",\"https://cloud.withgoogle.com/partners/?products\\u003dGOOGLE_WORKSPACE_PRODUCT\"],[\"Marketplace\",\"https://workspace.google.com/intl/ko/marketplace/\"],[\"통합\",\"https://workspace.google.com/intl/ko/integrations/\"],[\"교육 및 인증\",\"https://workspace.google.com/intl/ko/training/\"]]]]]],[[[\"학습 및 지원\",\"https://workspace.google.com/intl/ko/support/\",[[[\"관리자 도움말\",\"https://support.google.com/a/#topic\\u003d29157\"],[\"설치 및 배포 센터\",\"https://workspace.google.com/setup/?hl\\u003dko\"],[\"사용자를 위한 학습 센터\",\"https://workspace.google.com/intl/ko/learning-center/\"],[\"관리자 포럼\",\"https://productforums.google.com/forum/#!forum/apps\"],[\"Google Workspace 대시보드\",\"https://www.google.com/appsstatus#hl\\u003dko\"],[\"Google Workspace 파트너 찾기\",\"https://www.google.com/a/partnersearch/?hl\\u003dko#home\"],[\"보도자료\",\"https://cloud.google.com/press/\"]]]],[\"Google의 다른 제품\",null,[[[\"Google Cloud\",\"https://cloud.google.com/?hl\\u003dko\"],[\"Chrome Enterprise\",\"https://chromeenterprise.google/\"],[\"Google 비즈니스 솔루션\",\"https://www.google.com/intl/ko_kr/business/\"],[\"Google Ads\",\"https://ads.google.com/home/?subid\\u003dkr-ko-xs-aw-z-a-dyn-accounts_wsft!o3\"],[\"Business Messages\",\"https://businessmessages.google/\"],[\"사용자 연구 참여\",\"https://userresearch.google.com/?reserved\\u003d0\\u0026utm_source\\u003dgsuite.google.com\\u0026Q_Language\\u003den\\u0026utm_medium\\u003down_srch\\u0026utm_campaign\\u003dGlobal-GSuite\\u0026utm_term\\u003d0\\u0026utm_content\\u003d0\\u0026productTag\\u003dgafw\\u0026campaignDate\\u003dnov18\\u0026pType\\u003dbprof\\u0026referral_code\\u003dug422768\"]]]]]]]]]]]","w2btAe":"%.@.null,null,\"\",false,null,null,true,false]","xn5OId":false,"xnI9P":true,"xwAfE":true,"y2FhP":"prod","yFnxrf":1884,"zChJod":"%.@.]"};</script><script nonce="5dAgjnjZnWn0wEH1uLTSYA">(function(){'use strict';var a=window,d=a.performance,l=k();a.cc_latency_start_time=d&&d.now?0:d&&d.timing&&d.timing.navigationStart?d.timing.navigationStart:l;function k(){return d&&d.now?d.now():(new Date).getTime()}function n(e){if(d&&d.now&&d.mark){var g=d.mark(e);if(g)return g.startTime;if(d.getEntriesByName&&(e=d.getEntriesByName(e).pop()))return e.startTime}return k()}a.onaft=function(){n("aft")};a._isLazyImage=function(e){return e.hasAttribute("data-src")||e.hasAttribute("data-ils")||e.getAttribute("loading")==="lazy"}; a.l=function(e){function g(b){var c={};c[b]=k();a.cc_latency.push(c)}function m(b){var c=n("iml");b.setAttribute("data-iml",c);return c}a.cc_aid=e;a.iml_start=a.cc_latency_start_time;a.css_size=0;a.cc_latency=[];a.ccTick=g;a.onJsLoad=function(){g("jsl")};a.onCssLoad=function(){g("cssl")};a._isVisible=function(b,c){if(!c||c.style.display=="none")return!1;var f=b.defaultView;if(f&&f.getComputedStyle&&(f=f.getComputedStyle(c),f.height=="0px"||f.width=="0px"||f.visibility=="hidden"))return!1;if(!c.getBoundingClientRect)return!0; var h=c.getBoundingClientRect();c=h.left+a.pageXOffset;f=h.top+a.pageYOffset;if(f+h.height<0||c+h.width<0||h.height<=0||h.width<=0)return!1;b=b.documentElement;return f<=(a.innerHeight||b.clientHeight)&&c<=(a.innerWidth||b.clientWidth)};a._recordImlEl=m;document.documentElement.addEventListener("load",function(b){b=b.target;var c;b.tagName!="IMG"||b.hasAttribute("data-iid")||a._isLazyImage(b)||b.hasAttribute("data-noaft")||(c=m(b));if(a.aft_counter&&(b=a.aft_counter.indexOf(b),b!==-1&&(b=a.aft_counter.splice(b, 1).length===1,a.aft_counter.length===0&&b&&c)))a.onaft(c)},!0);a.prt=-1;a.wiz_tick=function(){var b=n("prt");a.prt=b}};}).call(this); l('DK1zsb')</script><script nonce="5dAgjnjZnWn0wEH1uLTSYA">var _F_cssRowKey = 'boq-cloudx-web-blog.TransformBlogUi.kBvWwdAt86U.L.X.O';var _F_combinedSignature = 'AHrnUqUMne414GLMZipCdLurIRsd0ykfYQ';function _DumpException(e) {throw e;}</script><link rel="stylesheet" href="https://www.gstatic.com/_/mss/boq-cloudx-web-blog/_/ss/k=boq-cloudx-web-blog.TransformBlogUi.kBvWwdAt86U.L.X.O/am=OBgwCw/d=1/ed=1/rs=AHrnUqUdHr1ILLldbe8xmK4BOgod6WRp4g/m=articleview,_b,_tp" data-id="_cl" nonce="o4N8v0zrwhDVSCCR3FZNIg"><script nonce="5dAgjnjZnWn0wEH1uLTSYA">onCssLoad();</script><style nonce="o4N8v0zrwhDVSCCR3FZNIg">@font-face{font-family:'Product Sans';font-style:normal;font-weight:400;src:url(https://fonts.gstatic.com/s/productsans/v9/pxiDypQkot1TnFhsFMOfGShVF9eK.eot);}@font-face{font-family:'Google Sans';font-style:normal;font-weight:400;src:url(https://fonts.gstatic.com/s/googlesans/v58/4Ua_rENHsxJlGDuGo1OIlJfC6l_24rlCK1Yo_Iqcsih3SAyH6cAwhX9RFD48TE63OOYKtrwEIJllpy0.eot);}@font-face{font-family:'Google Sans';font-style:normal;font-weight:500;src:url(https://fonts.gstatic.com/s/googlesans/v58/4Ua_rENHsxJlGDuGo1OIlJfC6l_24rlCK1Yo_Iqcsih3SAyH6cAwhX9RFD48TE63OOYKtrw2IJllpy0.eot);}@font-face{font-family:'Google Sans';font-style:normal;font-weight:700;src:url(https://fonts.gstatic.com/s/googlesans/v58/4Ua_rENHsxJlGDuGo1OIlJfC6l_24rlCK1Yo_Iqcsih3SAyH6cAwhX9RFD48TE63OOYKtrzjJ5llpy0.eot);}@font-face{font-family:'Google Sans Display';font-style:normal;font-weight:400;src:url(https://fonts.gstatic.com/s/googlesansdisplay/v13/ea8FacM9Wef3EJPWRrHjgE4B6CnlZxHVDv79pQ.eot);}@font-face{font-family:'Google Sans Display';font-style:normal;font-weight:500;src:url(https://fonts.gstatic.com/s/googlesansdisplay/v13/ea8IacM9Wef3EJPWRrHjgE4B6CnlZxHVBg3etBD7SA.eot);}@font-face{font-family:'Google Sans Display';font-style:normal;font-weight:700;src:url(https://fonts.gstatic.com/s/googlesansdisplay/v13/ea8IacM9Wef3EJPWRrHjgE4B6CnlZxHVBkXYtBD7SA.eot);}</style><script nonce="5dAgjnjZnWn0wEH1uLTSYA">(function(){'use strict';function e(){var a=g,b=0;return function(){return b<a.length?{done:!1,value:a[b++]}:{done:!0}}};/* Copyright The Closure Library Authors. SPDX-License-Identifier: Apache-2.0 */ var l=this||self;/* Copyright 2024 Google, Inc SPDX-License-Identifier: MIT */ var m=["focus","blur","error","load","toggle"];function n(a){return a==="mouseenter"?"mouseover":a==="mouseleave"?"mouseout":a==="pointerenter"?"pointerover":a==="pointerleave"?"pointerout":a};function p(a){this.l={};this.m={};this.i=null;this.g=[];this.o=a}p.prototype.handleEvent=function(a,b,c){q(this,{eventType:a,event:b,targetElement:b.target,eic:c,timeStamp:Date.now(),eia:void 0,eirp:void 0,eiack:void 0})};function q(a,b){if(a.i)a.i(b);else{b.eirp=!0;var c;(c=a.g)==null||c.push(b)}} function r(a,b,c){if(!(b in a.l)&&a.o){var d=function(h,f,B){a.handleEvent(h,f,B)};a.l[b]=d;c=n(c||b);if(c!==b){var k=a.m[c]||[];k.push(b);a.m[c]=k}a.o.addEventListener(c,function(h){return function(f){d(b,f,h)}},void 0)}}p.prototype.j=function(a){return this.l[a]};p.prototype.ecrd=function(a){this.i=a;var b;if((b=this.g)==null?0:b.length){for(a=0;a<this.g.length;a++)q(this,this.g[a]);this.g=null}};var t=typeof navigator!=="undefined"&&/iPhone|iPad|iPod/.test(navigator.userAgent);function u(a){this.g=a;this.i=[]}u.prototype.addEventListener=function(a,b,c){t&&(this.g.style.cursor="pointer");var d=this.i,k=d.push,h=this.g;b=b(this.g);var f=!1;m.indexOf(a)>=0&&(f=!0);h.addEventListener(a,b,typeof c==="boolean"?{capture:f,passive:c}:f);k.call(d,{eventType:a,j:b,capture:f,passive:c})};var g="click dblclick focus focusin blur error focusout keydown keyup keypress load mouseover mouseout mouseenter mouseleave submit toggle touchstart touchend touchmove touchcancel auxclick change compositionstart compositionupdate compositionend beforeinput input select textinput copy cut paste mousedown mouseup wheel contextmenu dragover dragenter dragleave drop dragstart dragend pointerdown pointermove pointerup pointercancel pointerenter pointerleave pointerover pointerout gotpointercapture lostpointercapture ended loadedmetadata pagehide pageshow visibilitychange beforematch".split(" "); if(!(g instanceof Array)){var v;var w=typeof Symbol!="undefined"&&Symbol.iterator&&g[Symbol.iterator];if(w)v=w.call(g);else if(typeof g.length=="number")v={next:e()};else throw Error(String(g)+" is not an iterable or ArrayLike");for(var x,y=[];!(x=v.next()).done;)y.push(x.value)};var z=function(a){return{trigger:function(b){var c=a.j(b.type);c||(r(a,b.type),c=a.j(b.type));var d=b.target||b.srcElement;c&&c(b.type,b,d.ownerDocument.documentElement)},configure:function(b){b(a)}}}(function(){var a=window,b=new u(a.document.documentElement),c=new p(b);g.forEach(function(h){return r(c,h)});var d,k;"onwebkitanimationend"in a&&(d="webkitAnimationEnd");r(c,"animationend",d);"onwebkittransitionend"in a&&(k="webkitTransitionEnd");r(c,"transitionend",k);return{s:c,u:b}}().s),A=["BOQ_wizbind"], C=window||l;A[0]in C||typeof C.execScript=="undefined"||C.execScript("var "+A[0]);for(var D;A.length&&(D=A.shift());)A.length||z===void 0?C[D]&&C[D]!==Object.prototype[D]?C=C[D]:C=C[D]={}:C[D]=z;}).call(this); </script><script noCollect src="https://www.gstatic.com/_/mss/boq-cloudx-web-blog/_/js/k=boq-cloudx-web-blog.TransformBlogUi.en_US.gC3IVRdc-js.es5.O/am=OBgwCw/d=1/excm=_b,_tp,articleview/ed=1/dg=0/wt=2/ujg=1/rs=AHrnUqUC0U47L_N8kMcLkQijaVUP_3FZOw/m=_b,_tp" defer id="base-js" fetchpriority="high" nonce="5dAgjnjZnWn0wEH1uLTSYA"></script><script nonce="5dAgjnjZnWn0wEH1uLTSYA">if (window.BOQ_loadedInitialJS) {onJsLoad();} else {document.getElementById('base-js').addEventListener('load', onJsLoad, false);}</script><script nonce="5dAgjnjZnWn0wEH1uLTSYA"> window['_wjdc'] = function (d) {window['_wjdd'] = d}; </script><title>Your ultimate guide to the latest in generative AI on Vertex AI | Google Cloud Blog</title><meta name="description" content="Learn about the latest AI advancements on Google Cloud Vertex AI. This covers new models, features, and enterprise tools to unlock generative AI."><meta name="robots" content="max-image-preview:large"><meta property="og:title" content="Your ultimate guide to the latest in generative AI on Vertex AI | Google Cloud Blog"><meta property="og:type" content="website"><meta property="og:url" content="https://cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai"><meta property="og:image" content="https://storage.googleapis.com/gweb-cloudblog-publish/images/ultimate_guide_82924.max-2500x2500.jpg"><meta property="og:description" content="Learn about the latest AI advancements on Google Cloud Vertex AI. This covers new models, features, and enterprise tools to unlock generative AI."><meta property="og:site_name" content="Google Cloud Blog"><meta name="twitter:card" content="summary_large_image"><meta name="twitter:url" content="https://cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai"><meta name="twitter:title" content="Your ultimate guide to the latest in generative AI on Vertex AI | Google Cloud Blog"><meta name="twitter:description" content="Learn about the latest AI advancements on Google Cloud Vertex AI. This covers new models, features, and enterprise tools to unlock generative AI."><meta name="twitter:image" content="https://storage.googleapis.com/gweb-cloudblog-publish/images/ultimate_guide_82924.max-2500x2500.jpg"><meta name="twitter:site" content="@googlecloud"><script type="application/ld+json">{"@context":"https://schema.org","@type":"BlogPosting","@id":"https://cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai","headline":"Your ultimate guide to the latest in generative AI on Vertex AI","description":"Learn about the latest AI advancements on Google Cloud Vertex AI. This covers new models, features, and enterprise tools to unlock generative AI.","image":"https://storage.googleapis.com/gweb-cloudblog-publish/images/ultimate_guide_82924.max-2500x2500.jpg","author":[{"@type":"Person","name":"Warren Barkley","url":""},{"@type":"Person","name":"Stephanie Wong","url":""}],"datePublished":"2024-09-27","publisher":{"@type":"Organization","name":"Google Cloud","logo":{"@type":"ImageObject","url":"https://www.gstatic.com/devrel-devsite/prod/v8bb8fa0afe9a8c3a776ebeb25d421bb443344d789b3607754dfabea418b8c4be/cloud/images/cloud-logo.svg"}},"url":"https://cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai","keywords":["AI \u0026 Machine Learning","Google Cloud"],"timeRequired":"PT24M"}</script><link rel="canonical" href="https://cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai"><meta name="track-metadata-page_post_title" content="Your ultimate guide to the latest in generative AI on Vertex AI"><meta name="track-metadata-page_post_labels" content="AI & Machine Learning"><meta name="track-metadata-page_first_published" content="2024-08-30 07:08:00"><meta name="track-metadata-page_last_published" content="2024-09-27 08:09:00"><meta name="track-metadata-page_post_author" content="Warren Barkley"><meta name="track-metadata-page_post_author_role" content="Sr. Director of Product Management"><header jsaction="rcuQ6b:npT2md" jscontroller="o60eef" class="glue-header nRhiJb-tJHJj-OWXEXe-kFx1Ae" id="kO001e"><a href="./#content" class="glue-header__link glue-header__skip-content">Jump to Content</a><div class="glue-header__bar glue-header__bar--mobile DFb9Jf" track-metadata-module="header"><div class="nRhiJb-mb9u9d"><div class="glue-header__container JF2WI"><div class="nRhiJb-o2XRw-yHKmmc lUwpmd"><div class="nRhiJb-rSCjMe"><a class="nRhiJb-rSCjMe-hSRGPd" href="https://cloud.google.com/" title="Google Cloud" track-name="google cloud"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/"track-metadata-module="header"><div class="nRhiJb-rSCjMe-haAclf"><svg class="glue-header__logo-svg" viewBox="0 0 74 24" role="presentation" aria-hidden="true"><path fill="#4285F4" d="M9.24 8.19v2.46h5.88c-.18 1.38-.64 2.39-1.34 3.1-.86.86-2.2 1.8-4.54 1.8-3.62 0-6.45-2.92-6.45-6.54s2.83-6.54 6.45-6.54c1.95 0 3.38.77 4.43 1.76L15.4 2.5C13.94 1.08 11.98 0 9.24 0 4.28 0 .11 4.04.11 9s4.17 9 9.13 9c2.68 0 4.7-.88 6.28-2.52 1.62-1.62 2.13-3.91 2.13-5.75 0-.57-.04-1.1-.13-1.54H9.24z"></path><path fill="#EA4335" d="M25 6.19c-3.21 0-5.83 2.44-5.83 5.81 0 3.34 2.62 5.81 5.83 5.81s5.83-2.46 5.83-5.81c0-3.37-2.62-5.81-5.83-5.81zm0 9.33c-1.76 0-3.28-1.45-3.28-3.52 0-2.09 1.52-3.52 3.28-3.52s3.28 1.43 3.28 3.52c0 2.07-1.52 3.52-3.28 3.52z"></path><path fill="#4285F4" d="M53.58 7.49h-.09c-.57-.68-1.67-1.3-3.06-1.3C47.53 6.19 45 8.72 45 12c0 3.26 2.53 5.81 5.43 5.81 1.39 0 2.49-.62 3.06-1.32h.09v.81c0 2.22-1.19 3.41-3.1 3.41-1.56 0-2.53-1.12-2.93-2.07l-2.22.92c.64 1.54 2.33 3.43 5.15 3.43 2.99 0 5.52-1.76 5.52-6.05V6.49h-2.42v1zm-2.93 8.03c-1.76 0-3.1-1.5-3.1-3.52 0-2.05 1.34-3.52 3.1-3.52 1.74 0 3.1 1.5 3.1 3.54.01 2.03-1.36 3.5-3.1 3.5z"></path><path fill="#FBBC05" d="M38 6.19c-3.21 0-5.83 2.44-5.83 5.81 0 3.34 2.62 5.81 5.83 5.81s5.83-2.46 5.83-5.81c0-3.37-2.62-5.81-5.83-5.81zm0 9.33c-1.76 0-3.28-1.45-3.28-3.52 0-2.09 1.52-3.52 3.28-3.52s3.28 1.43 3.28 3.52c0 2.07-1.52 3.52-3.28 3.52z"></path><path fill="#34A853" d="M58 .24h2.51v17.57H58z"></path><path fill="#EA4335" d="M68.26 15.52c-1.3 0-2.22-.59-2.82-1.76l7.77-3.21-.26-.66c-.48-1.3-1.96-3.7-4.97-3.7-2.99 0-5.48 2.35-5.48 5.81 0 3.26 2.46 5.81 5.76 5.81 2.66 0 4.2-1.63 4.84-2.57l-1.98-1.32c-.66.96-1.56 1.6-2.86 1.6zm-.18-7.15c1.03 0 1.91.53 2.2 1.28l-5.25 2.17c0-2.44 1.73-3.45 3.05-3.45z"></path></svg></div><span class="nRhiJb-rSCjMe-OWXEXe-UBMNlb khBwGd">Cloud</span></a></div></div><div class="glue-header__hamburger s6BfRd"><button class="glue-header__drawer-toggle-btn" aria-label="Open the navigation drawer"><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-xgZe3c" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="M3 18h18v-2H3v2zm0-5h18v-2H3v2zm0-7v2h18V6H3z"></path></svg></button></div><div class="nRhiJb-o2XRw-yHKmmc UrjqX"><div class="nRhiJb-rSCjMe"><a class="nRhiJb-rSCjMe-hSRGPd" href="https://cloud.google.com/blog" title="Google Cloud Blog" track-name="blog"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog"track-metadata-module="header"><span class="nRhiJb-rSCjMe-OWXEXe-UBMNlb khBwGd">Blog</span></a></div></div></div><div class="glue-header__container ca6rub"><div class="nRhiJb-GUI8l"><a class="nRhiJb-LgbsSe nRhiJb-LgbsSe-OWXEXe-pSzOP-o6Shpd " href="https://cloud.google.com/contact/" track-name="contact sales"track-type="blog nav"track-metadata-eventdetail="cloud.google.com/contact/"track-metadata-module="header" track-name="contact sales"track-type="button"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/contact/">Contact sales </a><a class="nRhiJb-LgbsSe nRhiJb-LgbsSe-OWXEXe-CNusmb-o6Shpd " href="https://console.cloud.google.com/freetrial/" track-name="get started for free"track-type="blog nav"track-metadata-eventdetail="console.cloud.google.com/freetrial/"track-metadata-module="header" track-name="get started for free"track-type="button"track-metadata-position="nav"track-metadata-eventdetail="console.cloud.google.com/freetrial/">Get started for free </a></div><div class="GKI4ub"><div class="Jhiezd"><form action="/blog/search/" class="A2C6Ob"><input class="BAhdXd" jsname="oJAbI" name="query" type="text" placeholder="Find an article..."><input type="hidden" name="language" value=en hidden><input type="hidden" name="category" value=article hidden><input type="hidden" name="paginate" value="25" hidden><input type="hidden" name="order" value="newest" hidden><input type="hidden" name="hl" value=en hidden><span class="A0lwXc" jsname="D8MWrd" aria-label="Show the search input field." role="button" jsaction="click:jUF4E"><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-xgZe3c" viewBox="0 0 24 24" role="presentation" aria-hidden="true" width="40" height="22"><path d="M20.49 19l-5.73-5.73C15.53 12.2 16 10.91 16 9.5A6.5 6.5 0 1 0 9.5 16c1.41 0 2.7-.47 3.77-1.24L19 20.49 20.49 19zM5 9.5C5 7.01 7.01 5 9.5 5S14 7.01 14 9.5 11.99 14 9.5 14 5 11.99 5 9.5z"></path></svg></span></form></div></div></div></div></div><div class="glue-header__bar glue-header__bar--desktop glue-header__drawer YcctDe" track-metadata-module="header"><div class="nRhiJb-mb9u9d M7RUq"><div class="glue-header__container JF2WI"><div class="nRhiJb-o2XRw-yHKmmc lUwpmd"><div class="nRhiJb-rSCjMe"><a class="nRhiJb-rSCjMe-hSRGPd" href="https://cloud.google.com/" title="Google Cloud" track-name="google cloud"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/"track-metadata-module="header"><div class="nRhiJb-rSCjMe-haAclf"><svg class="glue-header__logo-svg" viewBox="0 0 74 24" role="presentation" aria-hidden="true"><path fill="#4285F4" d="M9.24 8.19v2.46h5.88c-.18 1.38-.64 2.39-1.34 3.1-.86.86-2.2 1.8-4.54 1.8-3.62 0-6.45-2.92-6.45-6.54s2.83-6.54 6.45-6.54c1.95 0 3.38.77 4.43 1.76L15.4 2.5C13.94 1.08 11.98 0 9.24 0 4.28 0 .11 4.04.11 9s4.17 9 9.13 9c2.68 0 4.7-.88 6.28-2.52 1.62-1.62 2.13-3.91 2.13-5.75 0-.57-.04-1.1-.13-1.54H9.24z"></path><path fill="#EA4335" d="M25 6.19c-3.21 0-5.83 2.44-5.83 5.81 0 3.34 2.62 5.81 5.83 5.81s5.83-2.46 5.83-5.81c0-3.37-2.62-5.81-5.83-5.81zm0 9.33c-1.76 0-3.28-1.45-3.28-3.52 0-2.09 1.52-3.52 3.28-3.52s3.28 1.43 3.28 3.52c0 2.07-1.52 3.52-3.28 3.52z"></path><path fill="#4285F4" d="M53.58 7.49h-.09c-.57-.68-1.67-1.3-3.06-1.3C47.53 6.19 45 8.72 45 12c0 3.26 2.53 5.81 5.43 5.81 1.39 0 2.49-.62 3.06-1.32h.09v.81c0 2.22-1.19 3.41-3.1 3.41-1.56 0-2.53-1.12-2.93-2.07l-2.22.92c.64 1.54 2.33 3.43 5.15 3.43 2.99 0 5.52-1.76 5.52-6.05V6.49h-2.42v1zm-2.93 8.03c-1.76 0-3.1-1.5-3.1-3.52 0-2.05 1.34-3.52 3.1-3.52 1.74 0 3.1 1.5 3.1 3.54.01 2.03-1.36 3.5-3.1 3.5z"></path><path fill="#FBBC05" d="M38 6.19c-3.21 0-5.83 2.44-5.83 5.81 0 3.34 2.62 5.81 5.83 5.81s5.83-2.46 5.83-5.81c0-3.37-2.62-5.81-5.83-5.81zm0 9.33c-1.76 0-3.28-1.45-3.28-3.52 0-2.09 1.52-3.52 3.28-3.52s3.28 1.43 3.28 3.52c0 2.07-1.52 3.52-3.28 3.52z"></path><path fill="#34A853" d="M58 .24h2.51v17.57H58z"></path><path fill="#EA4335" d="M68.26 15.52c-1.3 0-2.22-.59-2.82-1.76l7.77-3.21-.26-.66c-.48-1.3-1.96-3.7-4.97-3.7-2.99 0-5.48 2.35-5.48 5.81 0 3.26 2.46 5.81 5.76 5.81 2.66 0 4.2-1.63 4.84-2.57l-1.98-1.32c-.66.96-1.56 1.6-2.86 1.6zm-.18-7.15c1.03 0 1.91.53 2.2 1.28l-5.25 2.17c0-2.44 1.73-3.45 3.05-3.45z"></path></svg></div><span class="nRhiJb-rSCjMe-OWXEXe-UBMNlb khBwGd">Cloud</span></a></div></div><div class="nRhiJb-o2XRw-yHKmmc UrjqX"><div class="nRhiJb-rSCjMe"><a class="nRhiJb-rSCjMe-hSRGPd" href="https://cloud.google.com/blog" title="Google Cloud Blog" track-name="blog"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog"track-metadata-module="header"><span class="nRhiJb-rSCjMe-OWXEXe-UBMNlb khBwGd">Blog</span></a></div></div></div><div class="glue-header__container glue-header__stepped-nav LKvi8b" role="navigation"><div class="glue-header__stepped-nav-controls-container"><div class="glue-header__stepped-nav-controls"><div class="glue-header__stepped-nav-controls-arrow"><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-SFi8G" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="M16.41 5.41L15 4l-8 8 8 8 1.41-1.41L9.83 12"></path></svg><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-SFi8G glue-header__stepped-nav-subnav-icon" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="M7.59 18.59L9 20l8-8-8-8-1.41 1.41L14.17 12"></path></svg></div><div class="glue-header__stepped-nav-controls-title glue-header__link"></div></div></div><div class="glue-header__stepped-nav-menus"></div></div><div class="glue-header__container nRhiJb-J6KYL-OWXEXe-Q4irje"><nav class="glue-header__link-bar"><ul class="glue-header__list glue-header__list--nested glue-header__deep-nav URiJfb"><li class="glue-header__item "><a class="glue-header__link">Solutions & technology<svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-SFi8G" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="M5.41 7.59L4 9l8 8 8-8-1.41-1.41L12 14.17"></path></svg></a><ul class="glue-header__list NDdrcc"><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/ai-machine-learning" track-name="ai & machine learning"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/ai-machine-learning"track-metadata-module="header"><span>AI & Machine Learning</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/api-management" track-name="api management"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/api-management"track-metadata-module="header"><span>API Management</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/application-development" track-name="application development"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/application-development"track-metadata-module="header"><span>Application Development</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/application-modernization" track-name="application modernization"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/application-modernization"track-metadata-module="header"><span>Application Modernization</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/chrome-enterprise" track-name="chrome enterprise"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/chrome-enterprise"track-metadata-module="header"><span>Chrome Enterprise</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/compute" track-name="compute"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/compute"track-metadata-module="header"><span>Compute</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/containers-kubernetes" track-name="containers & kubernetes"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/containers-kubernetes"track-metadata-module="header"><span>Containers & Kubernetes</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/data-analytics" track-name="data analytics"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/data-analytics"track-metadata-module="header"><span>Data Analytics</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/databases" track-name="databases"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/databases"track-metadata-module="header"><span>Databases</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/devops-sre" track-name="devops & sre"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/devops-sre"track-metadata-module="header"><span>DevOps & SRE</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/maps-geospatial" track-name="maps & geospatial"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/maps-geospatial"track-metadata-module="header"><span>Maps & Geospatial</span></a></li><li class="glue-header__item "><a class="glue-header__link janap">Security<svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-SFi8G" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="M7.59 18.59L9 20l8-8-8-8-1.41 1.41L14.17 12"></path></svg></a><ul class="glue-header__list NDdrcc"><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/identity-security" track-name="security & identity"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/identity-security"track-metadata-module="header"><span>Security & Identity</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/threat-intelligence" track-name="threat intelligence"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/threat-intelligence"track-metadata-module="header"><span>Threat Intelligence</span></a></li></ul></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/infrastructure" track-name="infrastructure"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/infrastructure"track-metadata-module="header"><span>Infrastructure</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/infrastructure-modernization" track-name="infrastructure modernization"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/infrastructure-modernization"track-metadata-module="header"><span>Infrastructure Modernization</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/networking" track-name="networking"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/networking"track-metadata-module="header"><span>Networking</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/productivity-collaboration" track-name="productivity & collaboration"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/productivity-collaboration"track-metadata-module="header"><span>Productivity & Collaboration</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/sap-google-cloud" track-name="sap on google cloud"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/sap-google-cloud"track-metadata-module="header"><span>SAP on Google Cloud</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/storage-data-transfer" track-name="storage & data transfer"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/storage-data-transfer"track-metadata-module="header"><span>Storage & Data Transfer</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/sustainability" track-name="sustainability"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/sustainability"track-metadata-module="header"><span>Sustainability</span></a></li></ul></li><li class="glue-header__item "><a class="glue-header__link">Ecosystem<svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-SFi8G" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="M5.41 7.59L4 9l8 8 8-8-1.41-1.41L12 14.17"></path></svg></a><ul class="glue-header__list NDdrcc"><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/transform" track-name="it leaders"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/transform"track-metadata-module="header"><span>IT Leaders</span></a></li><li class="glue-header__item "><a class="glue-header__link janap">Industries<svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-SFi8G" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="M7.59 18.59L9 20l8-8-8-8-1.41 1.41L14.17 12"></path></svg></a><ul class="glue-header__list NDdrcc"><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/financial-services" track-name="financial services"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/financial-services"track-metadata-module="header"><span>Financial Services</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/healthcare-life-sciences" track-name="healthcare & life sciences"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/healthcare-life-sciences"track-metadata-module="header"><span>Healthcare & Life Sciences</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/manufacturing" track-name="manufacturing"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/manufacturing"track-metadata-module="header"><span>Manufacturing</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/products/media-entertainment" track-name="media & entertainment"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/products/media-entertainment"track-metadata-module="header"><span>Media & Entertainment</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/public-sector" track-name="public sector"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/public-sector"track-metadata-module="header"><span>Public Sector</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/retail" track-name="retail"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/retail"track-metadata-module="header"><span>Retail</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/supply-chain-logistics" track-name="supply chain"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/supply-chain-logistics"track-metadata-module="header"><span>Supply Chain</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/telecommunications" track-name="telecommunications"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/telecommunications"track-metadata-module="header"><span>Telecommunications</span></a></li></ul></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/partners" track-name="partners"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/partners"track-metadata-module="header"><span>Partners</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/startups" track-name="startups & smb"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/startups"track-metadata-module="header"><span>Startups & SMB</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/training-certifications" track-name="training & certifications"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/training-certifications"track-metadata-module="header"><span>Training & Certifications</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/inside-google-cloud" track-name="inside google cloud"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/inside-google-cloud"track-metadata-module="header"><span>Inside Google Cloud</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://cloud.google.com/blog/topics/google-cloud-next" track-name="google cloud next & events"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/google-cloud-next"track-metadata-module="header"><span>Google Cloud Next & Events</span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://mapsplatform.google.com/resources/blog/" track-name="google maps platform"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="mapsplatform.google.com/resources/blog/"track-metadata-module="header" target="_blank"><span>Google Maps Platform<svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-SFi8G FsOzib nRhiJb-tHaKme-AipIyc" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="m8.9 16.075 5.4-5.4v2.675h1.4V8.3h-5.05v1.4h2.65l-5.375 5.375ZM12 21.3q-1.925 0-3.625-.738-1.7-.737-2.95-1.987-1.25-1.25-1.987-2.95Q2.7 13.925 2.7 12t.738-3.625q.737-1.7 1.987-2.95 1.25-1.25 2.95-1.988Q10.075 2.7 12 2.7t3.625.737q1.7.738 2.95 1.988 1.25 1.25 1.987 2.95.738 1.7.738 3.625t-.738 3.625q-.737 1.7-1.987 2.95-1.25 1.25-2.95 1.987-1.7.738-3.625.738Z"></path></svg></span></a></li><li class="glue-header__item "><a class="glue-header__link janap " href="https://workspace.google.com/blog" track-name="google workspace"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="workspace.google.com/blog"track-metadata-module="header" target="_blank"><span>Google Workspace<svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-SFi8G FsOzib nRhiJb-tHaKme-AipIyc" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="m8.9 16.075 5.4-5.4v2.675h1.4V8.3h-5.05v1.4h2.65l-5.375 5.375ZM12 21.3q-1.925 0-3.625-.738-1.7-.737-2.95-1.987-1.25-1.25-1.987-2.95Q2.7 13.925 2.7 12t.738-3.625q.737-1.7 1.987-2.95 1.25-1.25 2.95-1.988Q10.075 2.7 12 2.7t3.625.737q1.7.738 2.95 1.988 1.25 1.25 1.987 2.95.738 1.7.738 3.625t-.738 3.625q-.737 1.7-1.987 2.95-1.25 1.25-2.95 1.987-1.7.738-3.625.738Z"></path></svg></span></a></li></ul></li><li class="glue-header__item "><a class="glue-header__link " href="https://cloud.google.com/blog/topics/developers-practitioners" track-name="developers & practitioners"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/blog/topics/developers-practitioners"track-metadata-module="header"><span>Developers & Practitioners</span></a></li><li class="glue-header__item "><a class="glue-header__link " href="https://cloud.google.com/transform" track-name="transform with google cloud"track-type="blog nav"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/transform"track-metadata-module="header"><span>Transform with Google Cloud</span></a></li></ul></nav></div><div class="glue-header__container ca6rub nRhiJb-J6KYL-OWXEXe-SU0ZEf"><div class="nRhiJb-GUI8l"><a class="nRhiJb-LgbsSe nRhiJb-LgbsSe-OWXEXe-pSzOP-o6Shpd " href="https://cloud.google.com/contact/" track-name="contact sales"track-type="blog nav"track-metadata-eventdetail="cloud.google.com/contact/"track-metadata-module="header" track-name="contact sales"track-type="button"track-metadata-position="nav"track-metadata-eventdetail="cloud.google.com/contact/">Contact sales </a><a class="nRhiJb-LgbsSe nRhiJb-LgbsSe-OWXEXe-CNusmb-o6Shpd " href="https://console.cloud.google.com/freetrial/" track-name="get started for free"track-type="blog nav"track-metadata-eventdetail="console.cloud.google.com/freetrial/"track-metadata-module="header" track-name="get started for free"track-type="button"track-metadata-position="nav"track-metadata-eventdetail="console.cloud.google.com/freetrial/">Get started for free </a></div><div class="GKI4ub"><div class="Jhiezd"><form action="/blog/search/" class="A2C6Ob"><input class="BAhdXd" jsname="oJAbI" name="query" type="text" placeholder="Find an article..."><input type="hidden" name="language" value=en hidden><input type="hidden" name="category" value=article hidden><input type="hidden" name="paginate" value="25" hidden><input type="hidden" name="order" value="newest" hidden><input type="hidden" name="hl" value=en hidden><span class="A0lwXc" jsname="D8MWrd" aria-label="Show the search input field." role="button" jsaction="click:jUF4E"><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-xgZe3c" viewBox="0 0 24 24" role="presentation" aria-hidden="true" width="40" height="22"><path d="M20.49 19l-5.73-5.73C15.53 12.2 16 10.91 16 9.5A6.5 6.5 0 1 0 9.5 16c1.41 0 2.7-.47 3.77-1.24L19 20.49 20.49 19zM5 9.5C5 7.01 7.01 5 9.5 5S14 7.01 14 9.5 11.99 14 9.5 14 5 11.99 5 9.5z"></path></svg></span></form></div></div></div></div></div><div class="glue-header__drawer-backdrop"></div></header><script nonce="5dAgjnjZnWn0wEH1uLTSYA">var AF_initDataKeys = ["ds:0"]; var AF_dataServiceRequests = {'ds:0' : {id:'nInjGe',request:["cloudblog","products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai","en"]}}; var AF_initDataChunkQueue = []; var AF_initDataCallback; var AF_initDataInitializeCallback; if (AF_initDataInitializeCallback) {AF_initDataInitializeCallback(AF_initDataKeys, AF_initDataChunkQueue, AF_dataServiceRequests);}if (!AF_initDataCallback) {AF_initDataCallback = function(chunk) {AF_initDataChunkQueue.push(chunk);};}</script></head><body id="yDmH0d" jscontroller="pjICDe" jsaction="rcuQ6b:npT2md; click:FAbpgf; auxclick:FAbpgf" class="tQj5Y ghyPEc IqBfM ecJEib EWZcud nRhiJb-qJTHM" data-has-header="true" data-has-footer="true"><script aria-hidden="true" nonce="5dAgjnjZnWn0wEH1uLTSYA">window.wiz_progress&&window.wiz_progress();</script><div class="VUoKZ" aria-hidden="true"><div class="TRHLAc"></div></div><c-wiz jsrenderer="zPZHOe" class="SSPGKf" jsdata="deferred-i1" data-p="%.@."cloudblog","products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai","en"]" data-node-index="0;0" jsmodel="hc6Ubd" view c-wiz data-ogpc><div class="T4LgNb " jsname="a9kxte"><div jsname="qJTHM" class="kFwPee"><article class="nRhiJb-qJTHM" jsaction="rcuQ6b:npT2md" jscontroller="kxO7ab"><section class="nRhiJb-DARUcf"><div class="Wdmc0c nRhiJb-DbgRPb-wNfPc-cGMI2b"><div class="Qwf2Db-MnozTc Qwf2Db-MnozTc-OWXEXe-MnozTc-qWD73c nRhiJb-BFbNVe-r8s4j-bMElCd dIsJJe" track-name="ai & machine learning"track-type="tag">AI & Machine Learning</div><div class="nRhiJb-ObfsIf"><div class="nRhiJb-kR0ZEf-OWXEXe-GV1x9e-R6PoUb"></div><div class="nRhiJb-kR0ZEf-OWXEXe-GV1x9e-EehZO nRhiJb-fmcmS-oXtfBe"><h1 class="Qwf2Db-MnozTc Qwf2Db-MnozTc-OWXEXe-MnozTc-ibL1re"><div class="Qwf2Db-MnozTc Qwf2Db-MnozTc-OWXEXe-MnozTc-ibL1re"><span class="FewWi"></span>Your ultimate guide to the latest in generative AI on Vertex AI</div></h1></div></div><div class="nRhiJb-fmcmS-oXtfBe dEogG">September 27, 2024</div></div></section><div class="EKklye"><div class="nRhiJb-DARUcf ZWw7T"><div class="npzWPc"><div class="dzoHJ"><div class="nRhiJb-DX2B6 nRhiJb-DX2B6-OWXEXe-h30Snd"><div class="nRhiJb-j5y3u"><ul class="nRhiJb-Qijihe phRaUe" role="list"><li class="hpHPGf"><a class="nRhiJb-ARYxNe" href="https://x.com/intent/tweet?text=Your%20ultimate%20guide%20to%20the%20latest%20in%20generative%20AI%20on%20Vertex%20AI%20@googlecloud&url=https://cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai" track-name="x"track-type="social share"track-metadata-eventdetail="x.com/intent/tweet?text=Your ultimate guide to the latest in generative AI on Vertex AI%20@googlecloud&url=cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai"track-metadata-module="social icons" target="_blank" rel="noopener"><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-DX2B6 nRhiJb-Bz112c-OWXEXe-nSuQf" viewBox="0 0 24 24" role="presentation" aria-hidden="true" role="presentation" aria-hidden="true"><path d="M13.9,10.5L21.1,2h-1.7l-6.3,7.4L8,2H2.2l7.6,11.1L2.2,22h1.7l6.7-7.8L16,22h5.8L13.9,10.5L13.9,10.5z M11.5,13.2l-0.8-1.1 L4.6,3.3h2.7l5,7.1l0.8,1.1l6.5,9.2h-2.7L11.5,13.2L11.5,13.2z"></path></svg></a></li><li class="hpHPGf"><a class="nRhiJb-ARYxNe" href="https://www.linkedin.com/shareArticle?mini=true&url=https://cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai&title=Your%20ultimate%20guide%20to%20the%20latest%20in%20generative%20AI%20on%20Vertex%20AI" track-name="linkedin"track-type="social share"track-metadata-eventdetail="www.linkedin.com/shareArticle?mini=true&url=cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai&title=Your ultimate guide to the latest in generative AI on Vertex AI"track-metadata-module="social icons" target="_blank" rel="noopener"><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-DX2B6 nRhiJb-Bz112c-OWXEXe-nSuQf" viewBox="0 0 24 24" role="presentation" aria-hidden="true" role="presentation" aria-hidden="true"><path d="M20 2H4c-1.1 0-1.99.9-1.99 2L2 20c0 1.1.9 2 2 2h16c1.1 0 2-.9 2-2V4c0-1.1-.9-2-2-2zM8 19H5v-9h3v9zM6.5 8.31c-1 0-1.81-.81-1.81-1.81S5.5 4.69 6.5 4.69s1.81.81 1.81 1.81S7.5 8.31 6.5 8.31zM19 19h-3v-5.3c0-.83-.67-1.5-1.5-1.5s-1.5.67-1.5 1.5V19h-3v-9h3v1.2c.52-.84 1.59-1.4 2.5-1.4 1.93 0 3.5 1.57 3.5 3.5V19z"></path></svg></a></li><li class="hpHPGf"><a class="nRhiJb-ARYxNe" href="https://www.facebook.com/sharer/sharer.php?caption=Your%20ultimate%20guide%20to%20the%20latest%20in%20generative%20AI%20on%20Vertex%20AI&u=https://cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai" track-name="facebook"track-type="social share"track-metadata-eventdetail="www.facebook.com/sharer/sharer.php?caption=Your ultimate guide to the latest in generative AI on Vertex AI&u=cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai"track-metadata-module="social icons" target="_blank" rel="noopener"><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-DX2B6 nRhiJb-Bz112c-OWXEXe-nSuQf" viewBox="0 0 24 24" role="presentation" aria-hidden="true" role="presentation" aria-hidden="true"><path d="M20 2H4c-1.1 0-1.99.9-1.99 2L2 20c0 1.1.9 2 2 2h16c1.1 0 2-.9 2-2V4c0-1.1-.9-2-2-2zm-1 2v3h-2c-.55 0-1 .45-1 1v2h3v3h-3v7h-3v-7h-2v-3h2V7.5C13 5.57 14.57 4 16.5 4H19z"></path></svg></a></li><li class="hpHPGf"><a class="nRhiJb-ARYxNe" href="mailto:?subject=Your%20ultimate%20guide%20to%20the%20latest%20in%20generative%20AI%20on%20Vertex%20AI&body=Check%20out%20this%20article%20on%20the%20Cloud%20Blog:%0A%0AYour%20ultimate%20guide%20to%20the%20latest%20in%20generative%20AI%20on%20Vertex%20AI%0A%0ALearn%20about%20the%20latest%20AI%20advancements%20on%20Google%20Cloud%20Vertex%20AI.%20This%20covers%20new%20models,%20features,%20and%20enterprise%20tools%20to%20unlock%20generative%20AI.%0A%0Ahttps://cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai" track-name="email"track-type="social share"track-metadata-eventdetail="mailto:?subject=Your ultimate guide to the latest in generative AI on Vertex AI&body=Check%20out%20this%20article%20on%20the%20Cloud%20Blog:%0A%0AYour ultimate guide to the latest in generative AI on Vertex AI%0A%0ALearn about the latest AI advancements on Google Cloud Vertex AI. This covers new models, features, and enterprise tools to unlock generative AI.%0A%0Acloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai"track-metadata-module="social icons" target="_blank" rel="noopener"><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-DX2B6 nRhiJb-Bz112c-OWXEXe-nSuQf" viewBox="0 0 24 24" role="presentation" aria-hidden="true" role="presentation" aria-hidden="true"><path d="M20 4H4c-1.1 0-2 .9-2 2v12c0 1.1.9 2 2 2h16c1.1 0 2-.9 2-2V6c0-1.1-.9-2-2-2zm-.8 2L12 10.8 4.8 6h14.4zM4 18V7.87l8 5.33 8-5.33V18H4z"></path></svg></a></li></ul></div></div></div></div></div><div><section class="nRhiJb-RWrDld WWjeSb"><div class="nRhiJb-DbgRPb-wNfPc-ma6Yeb nRhiJb-DbgRPb-wNfPc-cGMI2b"><div class="nRhiJb-DARUcf"><div class="VI2oYd"><section class="PBkdHd "><img class=" rFf1Dd" src="https://storage.googleapis.com/gweb-cloudblog-publish/images/ultimate_guide_82924.max-2500x2500.jpg" alt="https://storage.googleapis.com/gweb-cloudblog-publish/images/ultimate_guide_82924.max-2500x2500.jpg" loading="lazy"/></section></div></div></div></section><section class="nRhiJb-DARUcf"><div class="nRhiJb-DbgRPb-wNfPc-ma6Yeb nRhiJb-DbgRPb-wNfPc-cGMI2b"><section class="DA9Qj nRhiJb-ObfsIf nRhiJb-fmcmS-oXtfBe"><div class="nRhiJb-kR0ZEf-OWXEXe-GV1x9e-ibL1re"></div><div class="nRhiJb-kR0ZEf-OWXEXe-GV1x9e-II5mzb kWSSdd"><h5 class="cHE8Ub Qwf2Db-MnozTc Qwf2Db-MnozTc-OWXEXe-MnozTc-qWD73c">Warren Barkley</h5><p class="nRhiJb-qJTHM khCp7b">Sr. Director of Product Management</p></div><div class="nRhiJb-kR0ZEf-OWXEXe-GV1x9e-II5mzb kWSSdd"><h5 class="cHE8Ub Qwf2Db-MnozTc Qwf2Db-MnozTc-OWXEXe-MnozTc-qWD73c">Stephanie Wong</h5><p class="nRhiJb-qJTHM khCp7b">Head of Technical Storytelling</p></div></section></div></section><div class="nRhiJb-DARUcf"><div class="nRhiJb-ObfsIf nRhiJb-DbgRPb-wNfPc-ma6Yeb nRhiJb-DbgRPb-qWD73c-cGMI2b"><div class="nRhiJb-kR0ZEf-OWXEXe-GV1x9e-ibL1re dzoHJ"><div class="aLW4J" track-metadata-module="left rail"><h5 class="qZDXV Qwf2Db-MnozTc Qwf2Db-MnozTc-OWXEXe-MnozTc-wNfPc">Google Cloud Summit Series</h5><p class="nRhiJb-cHYyed Mrfygc nRhiJb-BP2Omd-ma6Yeb-KE6vqe nRhiJb-DbgRPb-R6PoUb-cGMI2b">Discover the latest in AI, Security, Workspace, App Dev, & more.</p><a class="nRhiJb-LgbsSe nRhiJb-LgbsSe-OWXEXe-CNusmb-o6Shpd " href="https://cloudonair.withgoogle.com/summit_series_24?utm_source=cgc-blog&utm_medium=blog&utm_campaign=summit-series-2024&utm_content=summit-series-left-hand-rail-cta&utm_term=-" track-metadata-module="left rail"track-metadata-module_headline="google cloud summit series" track-name="register"track-type="button"track-metadata-position="cta"track-metadata-eventdetail="cloudonair.withgoogle.com/summit_series_24?utm_source=cgc-blog&utm_medium=blog&utm_campaign=summit-series-2024&utm_content=summit-series-left-hand-rail-cta&utm_term=-">Register </a></div></div><div class="OYL9D nRhiJb-kR0ZEf-OWXEXe-GV1x9e-OiUrBf" jsname="tx2NYc"><section class="Wy08Ac nRhiJb-qJTHM-OWXEXe-hJDwNd nRhiJb-DbgRPb-II5mzb-cGMI2b"><span class="dQQu7c" jsaction="rcuQ6b:npT2md" jscontroller="YSybTb" data-track-type="" soy-skip ssk='5:kbe95'><p><span style="vertical-align:baseline">The world of generative AI is evolving at a pace that's nothing short of mind-blowing. It feels like just yesterday we were marveling at AI-generated images, and now we're having full-fledged conversations with AI chatbots that can write code, craft poetry, and even serve our customers (check out our </span><a href="https://cloud.google.com/transform/101-real-world-generative-ai-use-cases-from-industry-leaders"><span style="text-decoration:underline;vertical-align:baseline">list of 101 real-world gen AI use cases</span></a><span style="vertical-align:baseline"> from the world's leading organizations).</span></p> <p><span style="vertical-align:baseline">The pace of innovation can be hard to keep up with — in 2023 we introduced over 500 new features in Vertex AI and we’re not slowing down this year. We put this blog together to help you keep track of the biggest announcements and make sense of what they mean for your business. We’ll keep it updated as new announcements come out, so bookmark this link and check out our new video series below also covering new announcements. </span></p> <h3><strong style="vertical-align:baseline">Catch up on the latest announcements</strong></h3> <p><span style="vertical-align:baseline">As part of our </span><a href="https://cloudonair.withgoogle.com/events/gemini-at-work-24?utm_source=the_keyword&utm_medium=blog&utm_campaign=FY24-Q3-global-EXP134-onlineevent-er-gemini-at-work-2024-mc&utm_content=tk-gaw-blog&utm_term=-" rel="noopener" target="_blank"><span style="text-decoration:underline;vertical-align:baseline">Gemini at Work</span></a><span style="vertical-align:baseline"> global event, we showcased </span><a href="https://cloud.google.com/blog/products/ai-machine-learning/how-customers-are-putting-gemini-to-work?e=48754805"><span style="text-decoration:underline;vertical-align:baseline">nearly 50 new customer stories</span></a><span style="vertical-align:baseline"> from organizations around the world to highlight just how impactful generative AI can be when you put it to work at scale. </span></p> <p><span style="vertical-align:baseline">We’re inspired by what customers are building and excited to announce a few exciting updates to our models and platform, designed to help move gen AI from </span><a href="https://cloud.google.com/blog/products/ai-machine-learning/experimentation-to-production-with-gemini-and-vertex-ai?e=48754805"><span style="text-decoration:underline;vertical-align:baseline">experimentation into production with Vertex AI</span></a><strong style="vertical-align:baseline">.</strong></p></span></section><section class="k6ctOd"><aside class="IwVNTb"><div class="ecJG2e nRhiJb-ObfsIf"><div class="nRhiJb-kR0ZEf-OWXEXe-GV1x9e-OiUrBf nRhiJb-snVHke-ibL1re-X66g3b nRhiJb-snVHke-R6PoUb-UFsB2c"><h4 class="Qwf2Db-MnozTc Qwf2Db-MnozTc-OWXEXe-MnozTc-qWD73c">$300 in free credit to try Google Cloud AI and ML</h4><p class="nRhiJb-qJTHM nRhiJb-DbgRPb-R6PoUb-ma6Yeb"><span class="dQQu7c" jsaction="rcuQ6b:npT2md" jscontroller="YSybTb" data-track-type="" soy-skip ssk='5:kbe95'><p>Build and test your proof of concept with $300 in free credit for new customers. Plus, all customers get free monthly usage of 20+ products, including AI APIs.</p></span></p><a class="nRhiJb-LgbsSe nRhiJb-LgbsSe-OWXEXe-MNynB-o6Shpd LZTd1c" href="http://console.cloud.google.com/freetrial?redirectPath=/vertex-ai/" target="_blank" rel="noopener" track-name="start building for free"track-type="button"track-metadata-position="body"track-metadata-eventdetail="http://console.cloud.google.com/freetrial?redirectPath=/vertex-ai/"track-metadata-module="aside"track-metadata-module_headline="$300 in free credit to try google cloud ai and ml" track-name="start building for free"track-type="button"track-metadata-position="body"track-metadata-eventdetail="http://console.cloud.google.com/freetrial?redirectPath=/vertex-ai/">Start building for free </a></div></div></aside></section><section class="YNV64d"><section><div jsaction="rcuQ6b:npT2md" jscontroller="wJu6E" class="nRhiJb-aTv5jf glue-video__preview-container glue-video__preview-container--inline" data-video-url="https://www.youtube.com/watch?v=xN5q77t5hdI"><div class="glue-video__preview-container p7j5vb vgZZI glue-video__preview-container--inline"><picture class="nRhiJb-zTg1Jd"><section class="PBkdHd "><img class=" glue-video__preview-image" src="https://storage.googleapis.com/gweb-cloudblog-publish/images/maxresdefault_pBw7HU9.max-1300x1300.jpg" alt="https://storage.googleapis.com/gweb-cloudblog-publish/images/maxresdefault_pBw7HU9.max-1300x1300.jpg" loading="lazy"/></section></picture><div class="nRhiJb-hEKMR"><svg class="nRhiJb-Bz112c nRhiJb-euxe5d-LgbsSe" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path fill="#f00" d="M23.74 7.1s-.23-1.65-.95-2.37c-.91-.96-1.93-.96-2.4-1.02C17.04 3.47 12 3.5 12 3.5s-5.02-.03-8.37.21c-.46.06-1.48.06-2.39 1.02C.52 5.45.28 7.1.28 7.1S.04 9.05 0 10.98V13c.04 1.94.28 3.87.28 3.87s.24 1.65.96 2.38c.91.95 2.1.92 2.64 1.02 1.88.18 7.91.22 8.12.22 0 0 5.05.01 8.4-.23.46-.06 1.48-.06 2.39-1.02.72-.72.96-2.37.96-2.37s.24-1.94.25-3.87v-2.02c-.02-1.93-.26-3.88-.26-3.88zM9.57 15.5V8.49L16 12.13 9.57 15.5z"></path><polygon fill="#fff" points="9.6,15.5 9.6,8.5 16,12.1 "></polygon></svg></div></div><div class="glue-video__container nRhiJb-LilHSb-OWXEXe-TzA9Ye vgZZI" data-glue-yt-video-height="100%" data-glue-yt-video-width="100%"></div></div></section></section><section class="Wy08Ac nRhiJb-qJTHM-OWXEXe-hJDwNd nRhiJb-DbgRPb-II5mzb-cGMI2b"><span class="dQQu7c" jsaction="rcuQ6b:npT2md" jscontroller="YSybTb" data-track-type="" soy-skip ssk='5:kbe95'><p><strong style="vertical-align:baseline">Updates to Gemini Models</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: </span><span style="vertical-align:baseline">The newly updated versions of </span><a href="https://console.cloud.google.com/vertex-ai/studio/freeform?model=gemini-1.5-pro-002"><span style="text-decoration:underline;vertical-align:baseline">Gemini 1.5 Pro</span></a><span style="vertical-align:baseline"> and </span><a href="https://console.cloud.google.com/vertex-ai/studio/freeform?model=gemini-1.5-flash-002"><span style="text-decoration:underline;vertical-align:baseline">Flash</span></a><span style="vertical-align:baseline"> models, both GA, deliver quality improvements in math, long context understanding, and vision.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: Our objective is to bring you the best models suited for enterprise use cases, by pushing the boundaries across performance, latency, and costs. From a latency standpoint, the new version of Gemini 1.5 Flash is nearly 2.5x faster than GPT-4o mini. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: </span><span style="vertical-align:baseline">Access </span><a href="https://console.cloud.google.com/vertex-ai/studio/freeform?model=gemini-1.5-pro-002"><span style="text-decoration:underline;vertical-align:baseline">Gemini 1.5 Pro</span></a><span style="vertical-align:baseline"> and </span><a href="https://console.cloud.google.com/vertex-ai/studio/freeform?model=gemini-1.5-flash-002"><span style="text-decoration:underline;vertical-align:baseline">Flash</span></a><span style="vertical-align:baseline"> in the Google Cloud console. </span></p> </li> </ul> <p><strong style="vertical-align:baseline">Reduced Gemini 1.5 Pro Pricing </strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: We are reducing costs of Gemini 1.5 Pro by </span><span style="vertical-align:baseline">50%</span><span style="vertical-align:baseline"> across both input and output tokens, effective on Vertex AI on October 7, 2024. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: We are committed to making AI accessible for every enterprise. </span><span style="vertical-align:baseline">In August, we improved Gemini 1.5 Flash to reduce costs by up to 80% (see below). </span><span style="vertical-align:baseline">These world class models can be coupled with capabilities like context caching to even further reduce the cost and latency of your long context queries. Using Batch API instead of standard requests can further optimize costs for latency insensitive tasks. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Visit the </span><a href="https://cloud.google.com/vertex-ai/generative-ai/pricing"><span style="text-decoration:underline;vertical-align:baseline">pricing page</span></a><span style="vertical-align:baseline"> to learn more. </span></p> </li> </ul> <p><strong style="vertical-align:baseline">Updates to Imagen 3</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Google’s latest image generation model, delivering outstanding image quality, multi-language support, built-in safety features like Google DeepMind’s SynthID digital watermarking, and support for multiple aspect ratios.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: There are several improvements over Imagen 2 — including over 40% faster generation for rapid prototyping and iteration; better prompt understanding and instruction-following; photo-realistic generations, including of groups of people; and greater control over text rendering within an image. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: </span><a href="https://docs.google.com/forms/d/e/1FAIpQLSdMHAK_KJygnvV2Psga7FIzKAhAqIBS_bHYzfgf_Y2h7fsoGA/viewform" rel="noopener" target="_blank"><span style="text-decoration:underline;vertical-align:baseline">Apply</span></a><span style="vertical-align:baseline"> for access to Imagen 3 on Vertex AI. </span></p> </li> </ul> <p><strong style="vertical-align:baseline">Controlled generation is now GA</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Controlled generation lets customers define Gemini model outputs according to specific formats or schemas. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: Most models cannot guarantee the format and syntax of their outputs, even with specified instructions. Vertex AI controlled generation lets customers choose the desired output format via pre-built options like JSON and ENUM, or by defining custom formats. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Visit </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/control-generated-output"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline"> to learn more. </span></p> </li> </ul> <p><strong style="vertical-align:baseline">Batch API</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Batch API (currently in preview) is a super-efficient way to send large numbers of non-latency sensitive text prompt requests, supporting use cases such as classification and sentiment analysis, data extraction, and description generation. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: It helps speed up developer workflows and reduces costs by enabling multiple prompts to be sent to models in a single request.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: View </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/batch-prediction-gemini"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline"> to get started.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Supervised fine tuning (SFT) for Gemini 1.5 Flash and Pro</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: SFT for Gemini 1.5 Flash and Pro is now generally available. SFT adapts model behavior with a labeled dataset, adjusting the model's weights to minimize the difference between its predictions and the actual labels. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: SFT allows you to tune the model to be more precise for your enterprise task. It's particularly effective for domain-specific applications where the language or content significantly differs from the data the large model was originally trained on. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Visit </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/models/gemini-supervised-tuning"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline"> to learn more. </span></p> </li> </ul> <p><strong style="vertical-align:baseline">Distillation techniques in Vertex AI</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Train smaller, specialized models that inherit the knowledge of the larger Gemini model, achieving comparable performance with the flexibility of self-hosting your custom model on Vertex AI. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: Deploying large language models can be a resource-intensive challenge. With distillation techniques in Vertex AI, you can leverage the power of those large models while keeping your deployments lean and efficient. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Fill out </span><a href="https://docs.google.com/forms/d/e/1FAIpQLSdsew3X0NCdsZb7sBYpFlXwPyRKK8XFuVX8EqDF5Xr_XJCRAA/viewform?resourcekey=0-pxT7SeEQJCxzLc0FtiBSvQ" rel="noopener" target="_blank"><span style="text-decoration:underline;vertical-align:baseline">this form</span></a><span style="vertical-align:baseline"> for early access.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Prompt Optimizer, now in preview </strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Based on Google Research’s publication on automatic prompt optimization (APO) methods, Prompt Optimizer adapts your prompts using the optimal instructions and examples to elicit the best performance from your chosen model. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: Vertex AI’s Prompt Optimizer helps you avoid the tedious trial-and-error of prompt engineering. Plus, our </span><a href="https://ai.google.dev/gemini-api/docs/prompting-strategies" rel="noopener" target="_blank"><span style="text-decoration:underline;vertical-align:baseline">prompt strategies guide</span></a><span style="vertical-align:baseline"> helps you make the models more verbose and conversational.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Learn more in </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline">.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Prompt Management SDK</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Vertex AI’s Prompt Management SDK allows users to retrieve and organize prompts. It lets you version prompts, restore old prompts, and generate suggestions to improve performance. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: This makes it easier for you to get the best performance from gen AI models at scale, and to iterate more quickly from experimentation to production. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: The prompt management SDK will be generally available in the coming weeks.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Multimodal function calling</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Function calling is a built-in feature of the Gemini API that translates natural language into structured data and back. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: Now, with multimodal function calling, your agents can also execute functions where your user can provide images, along with text, to help the model pick the right function and function parameters to call.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Learn more in </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/function-calling"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline">.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Org policy for models in Model Garden</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: You can now govern the models available in Model Garden. This includes limiting access to gen AI features, to only specific vetted models, or to tuning and other advanced capabilities. Org policies can be applied to all models in Model Garden as well as those imported from Hugging Face through Model Garden. These policies can be set on an organization, folder or project resource to enforce the constraint on that resource and any child resources.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: The ability to control access to the models made available through the Model Garden has been a top priority for many customers looking for governance and control tooling. Org Policies allows granular access control of models and enhances Google Cloud’s enterprise readiness in an age of many models from many providers.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Learn more in </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/control-model-access" style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen,Ubuntu,Cantarell,'Open Sans','Helvetica Neue',sans-serif"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline">.</span></p> </li> </ul></span></section><section class="k6ctOd"><aside class="IwVNTb"><div class="ecJG2e nRhiJb-ObfsIf"><div class="nRhiJb-kR0ZEf-OWXEXe-GV1x9e-OiUrBf nRhiJb-snVHke-ibL1re-X66g3b nRhiJb-snVHke-R6PoUb-UFsB2c"><h4 class="Qwf2Db-MnozTc Qwf2Db-MnozTc-OWXEXe-MnozTc-qWD73c">Build with the latest generative AI models for free</h4><p class="nRhiJb-qJTHM nRhiJb-DbgRPb-R6PoUb-ma6Yeb"><span class="dQQu7c" jsaction="rcuQ6b:npT2md" jscontroller="YSybTb" data-track-type="" soy-skip ssk='5:kbe95'><p>Explore what powerful models like Gemini and Imagen can do for you with $300 in free credit for new customers on signup.</p></span></p><a class="nRhiJb-LgbsSe nRhiJb-LgbsSe-OWXEXe-MNynB-o6Shpd LZTd1c" href="http://console.cloud.google.com/freetrial?redirectPath=/welcome" target="_blank" rel="noopener" track-name="get started for free"track-type="button"track-metadata-position="body"track-metadata-eventdetail="http://console.cloud.google.com/freetrial?redirectPath=/welcome"track-metadata-module="aside"track-metadata-module_headline="build with the latest generative ai models for free" track-name="get started for free"track-type="button"track-metadata-position="body"track-metadata-eventdetail="http://console.cloud.google.com/freetrial?redirectPath=/welcome">Get started for free </a></div></div></aside></section><section class="Wy08Ac nRhiJb-qJTHM-OWXEXe-hJDwNd nRhiJb-DbgRPb-II5mzb-cGMI2b"><span class="dQQu7c" jsaction="rcuQ6b:npT2md" jscontroller="YSybTb" data-track-type="" soy-skip ssk='5:kbe95'><h3><strong style="vertical-align:baseline">Previous Announcements</strong></h3></span></section><section class="Wy08Ac nRhiJb-qJTHM-OWXEXe-hJDwNd nRhiJb-DbgRPb-II5mzb-cGMI2b"><span class="dQQu7c" jsaction="rcuQ6b:npT2md" jscontroller="YSybTb" data-track-type="" soy-skip ssk='5:kbe95'><h3><strong style="vertical-align:baseline">Best models from Google and the industry</strong></h3> <p><span style="vertical-align:baseline">We’re committed to providing the best model for enterprises to use - Vertex AI Model Garden provides access to 150+ models from Google, Partners and the open community so customers can select the model for the right price, performance, and latency considerations.</span></p> <p><span style="vertical-align:baseline">No matter what foundation model you use, it comes with enterprise ready tooling and integration to our end to end platform. </span></p> <p><strong style="vertical-align:baseline">Gemini 1.5 Flash is GA</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is:</span><strong style="vertical-align:baseline"> </strong><span style="vertical-align:baseline">Gemini 1.5 Flash combines low latency, highly competitive pricing, and our 1 million-token context window.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: Gemini 1.5 Flash is an excellent option for a wide variety of use cases at scale, from retail chat agents, to document processing, to research agents that can synthesize entire repositories.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: </span><span style="vertical-align:baseline">Click </span><a href="https://console.cloud.google.com/vertex-ai/generative/multimodal/create/text"><span style="text-decoration:underline;vertical-align:baseline">here</span></a><span style="vertical-align:baseline"> to get started now with Gemini 1.5 Flash on Vertex AI. </span></p> </li> </ul> <p><strong style="vertical-align:baseline">Lower pricing for Gemini 1.5 Flash</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: We've updated Gemini 1.5 Flash to reduce the input costs by up to ~85% and output costs by up to ~80%, starting August 12th, 2024. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: This is a big price drop on Gemini Flash, a world-class model with a 1 million context window and multi-modal inputs. Plus, coupled with capabilities like context caching you can significantly reduce the cost and latency of your long context queries. Using Batch API instead of standard requests can further optimize costs for latency insensitive tasks. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: View </span><a href="https://cloud.google.com/vertex-ai/generative-ai/pricing"><span style="text-decoration:underline;vertical-align:baseline">pricing</span></a><span style="vertical-align:baseline"> to learn more and try </span><span style="vertical-align:baseline">out </span><a href="https://console.cloud.google.com/vertex-ai/generative/multimodal/create/text"><span style="text-decoration:underline;vertical-align:baseline">Gemini 1.5 Flash</span></a><span style="vertical-align:baseline"> today.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Gemini 1.5 Pro, GA with 2-million -token context capabilities </strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Now available with an industry-leading context window of up to 2 million tokens, Gemini 1.5 Pro is equipped to unlock unique multimodal use cases that no other model can handle.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: Processing just six minutes of video requires over 100,000 tokens and large code bases can exceed 1 million tokens — so whether the use case involves finding bugs across countless lines of code, locating the right information across libraries of research, or analyzing hours of audio or video, Gemini 1.5 Pro’s expanded context window is helping organizations break new ground. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: </span><span style="vertical-align:baseline">Click </span><a href="https://console.cloud.google.com/vertex-ai/generative/multimodal/create/text?model=gemini-1.5-pro-001"><span style="text-decoration:underline;vertical-align:baseline">here</span></a><span style="vertical-align:baseline"> to get started now </span></p> </li> </ul> <p><strong style="vertical-align:baseline">More Languages for Gemini</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: We're enabling Gemini 1.5 Flash and Gemini 1.5 Pro to understand and respond in 100+ languages. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: We’re making it easier for our global community to prompt and receive responses in their native languages.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: View </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#languages-gemini"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline"> to learn more.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Gemma 2</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: The next generation in Google’s family of open models built to give developers and researchers the ability to share and commercialize their innovations, using the same technologies used to create Gemini. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: Available in both 9-billion (9B) and 27-billion (27B) parameter sizes, Gemma 2 is much more powerful and efficient than the first generation, with significant safety advancements built in. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Access Gemma 2 on Vertex AI </span><a href="https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335"><span style="text-decoration:underline;vertical-align:baseline">here</span></a><span style="vertical-align:baseline">.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Meta’s Llama 3.1 </strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: </span><a href="https://cloud.google.com/blog/products/ai-machine-learning/llama-3-1-on-vertex-ai?e=48754805"><span style="text-decoration:underline;vertical-align:baseline">Llama 3.1 models</span></a><span style="vertical-align:baseline"> are now available on Vertex AI as a pay as you go API, this includes 405B, 70B and 8B (coming in early September). </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: 405B is the largest openly available foundation model to date. 8B and 70B are also new versions that excel at understanding language nuances, grasping context, and performing complex tasks such as translation and dialogue generation. You can access the new models in just a few clicks using Model-as-a-Service, without any setup or infrastructure hassles. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: To access Llama 3.1, visit </span><a href="https://pantheon.corp.google.com/vertex-ai/publishers/meta/model-garden/llama3-405b-instruct-maas" rel="noopener" target="_blank"><span style="text-decoration:underline;vertical-align:baseline">Model Garden</span></a></p> </li> </ul> <p><strong style="vertical-align:baseline">Mistral AI’s latest models</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: We added Mistral Large 2, Nemo and Codestral (Google Cloud is the first hyperscaler to introduce Codestral). </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: Mistral Large 2 is their flagship model which offers their best performance and versatility to date and Mistral Nemo is a 12B model that delivers exceptional performance at a fraction of the cost. Codestral is Mistral AI’s first open-weight generative AI model explicitly designed for code generation tasks. You can access the new models in just a few clicks using Model-as-a-Service, without any setup or infrastructure hassles. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: </span><span style="vertical-align:baseline">To access the Mistral AI models, visit Model Garden (</span><a href="https://console.cloud.google.com/vertex-ai/publishers/mistralai/model-garden/codestral"><span style="text-decoration:underline;vertical-align:baseline">Codestral</span></a><span style="vertical-align:baseline">, </span><a href="https://console.cloud.google.com/vertex-ai/publishers/mistralai/model-garden/mistral-large"><span style="text-decoration:underline;vertical-align:baseline">Large 2</span></a><span style="vertical-align:baseline">, </span><a href="https://console.cloud.google.com/vertex-ai/publishers/mistralai/model-garden/mistral-nemo"><span style="text-decoration:underline;vertical-align:baseline">Nemo</span></a><span style="vertical-align:baseline">) or check out the </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/mistral"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a></p> </li> </ul> <p><strong style="vertical-align:baseline">Jamba 1.5 Model Family from AI21 Labs</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Jamba 1.5 Model Family — AI21 Labs’ new family of open models — is in public preview on Vertex AI Model Garden, including: </span></p> </li> <ul> <li style="list-style-type:circle;vertical-align:baseline"> <p><span style="vertical-align:baseline">Jamba 1.5 Mini: AI21’s most efficient and lightweight model, engineered for speed and efficiency in tasks including customer support, document summarization, and text generation.</span></p> </li> <li style="list-style-type:circle;vertical-align:baseline"> <p><span style="vertical-align:baseline">Jamba 1.5 Large: AI21’s most advanced and largest model that can handle advanced reasoning tasks — such as financial analysis — with exceptional speed and efficiency. </span></p> </li> </ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: AI21’s new models join over 150 models already available on Vertex AI Model Garden, further expanding your choice and flexibility to choose the best models for your needs and budget, and to keep pace with the continued rapid pace of innovation. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: </span><span style="vertical-align:baseline">Select the </span><a href="https://console.cloud.google.com/vertex-ai/publishers/ai21/model-garden/jamba-1.5-mini"><strong style="text-decoration:underline;vertical-align:baseline">Jamba 1.5 Mini</strong></a><span style="vertical-align:baseline"> or </span><a href="https://console.cloud.google.com/vertex-ai/publishers/ai21/model-garden/jamba-1.5-large"><strong style="text-decoration:underline;vertical-align:baseline">Jamba 1.5 Large</strong></a><strong style="vertical-align:baseline"> </strong><span style="vertical-align:baseline">model tile in Vertex AI Model Garden. </span></p> </li> </ul> <p><strong style="vertical-align:baseline">Anthropic’s Claude 3.5 Sonnet</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: We recently added Anthropic’s newly released model, Claude 3.5 Sonnet, to Vertex AI. This expands the set of Anthropic models we offer, including Claude 3 Opus, Claude 3 Sonnet, Claude 3 Haiku. You can access the new models in just a few clicks using Model-as-a-Service, without any setup or infrastructure hassles. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: We're committed to empowering customer choice and innovation through our curated collection of first-party, open, and third-party models available on Vertex AI. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: </span><span style="vertical-align:baseline">Begin experimenting with or deploying in production </span><a href="https://console.cloud.google.com/vertex-ai/publishers/anthropic/model-garden/claude-3-5-sonnet" style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen,Ubuntu,Cantarell,'Open Sans','Helvetica Neue',sans-serif"><span style="text-decoration:underline;vertical-align:baseline">Claude 3.5 Sonnet on Vertex AI</span></a><span style="vertical-align:baseline">.</span></p> </li> </ul></span></section><section class="Wy08Ac nRhiJb-qJTHM-OWXEXe-hJDwNd nRhiJb-DbgRPb-II5mzb-cGMI2b"><span class="dQQu7c" jsaction="rcuQ6b:npT2md" jscontroller="YSybTb" data-track-type="" soy-skip ssk='5:kbe95'><h3><strong style="vertical-align:baseline">End-to-end model building platform with choice at every level</strong></h3> <p><span style="vertical-align:baseline">Vertex AI Model Builder enables you to build or customize your own models, with all the capabilities you need to move from prototype to production.</span></p> <p><strong style="vertical-align:baseline">Lower cost with context caching for both Gemini 1.5 Pro and Flash</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Context caching is a technique that involves storing previous parts of a conversation or interaction (the "context") in memory so that the model can refer back to it when generating new responses</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: As context length increases, it can be expensive and slow to get responses for long-context applications, making it difficult to deploy to production. Vertex AI context caching helps customers significantly reduce input costs, by 75 percent, leveraging cached data of frequently-used context. Today, Google is the only provider to offer a context caching API. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Learn more in </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/context-cache/context-cache-overview"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><strong style="vertical-align:baseline">.</strong></p> </li> </ul> <p><strong style="vertical-align:baseline">New model monitoring capabilities</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: The new Vertex AI Model Monitoring includes</span></p> </li> <ul> <li style="list-style-type:circle;vertical-align:baseline"> <p><span style="vertical-align:baseline">Support for models hosted outside of Vertex AI (e.g. GKE, Cloud Run, even multi-cloud & hybrid-cloud)</span></p> </li> <li style="list-style-type:circle;vertical-align:baseline"> <p><span style="vertical-align:baseline">Unified monitoring job management for both online and batch prediction</span></p> </li> <li style="list-style-type:circle;vertical-align:baseline"> <p><span style="vertical-align:baseline">Simplified configuration and metrics visualization attached to the model, not the endpoint</span></p> </li> </ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: Vertex AI’s new model monitoring features provide a more flexible, extensible, and consistent monitoring solution for models deployed on any serving infrastructure (even outside of Vertex AI, e.g. Google Kubernetes Engine, Cloud Run, Google Compute Engine and more).</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Learn more in this </span><a href="https://cloud.google.com/blog/products/ai-machine-learning/get-to-know-vertex-ai-model-monitoring"><span style="text-decoration:underline;vertical-align:baseline">blog</span></a><span style="vertical-align:baseline">.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Ray on Vertex AI is GA</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Ray provides a comprehensive and easy-to-use Python distributed framework. With Ray, you configure a scalable cluster of computational resources and utilize a collection of domain-specific libraries to efficiently distribute common AI/ML tasks like training, serving, and tuning. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: This integration empowers AI developers to effortlessly scale their AI workloads on Vertex AI's versatile infrastructure, which unlocks the full potential of machine learning, data processing, and distributed computing.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Ready the </span><a href="https://cloud.google.com/blog/products/ai-machine-learning/ray-on-vertex-ai"><span style="text-decoration:underline;vertical-align:baseline">blog</span></a><span style="vertical-align:baseline"> to learn more.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Prompt Management</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Vertex AI Prompt Management, now in preview, provides a library of prompts for use among teams, including versioning, the option to restore old prompts, and AI-generated suggestions to improve prompt performance. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: This feature makes it easier for organizations to get the best performance from gen AI models at scale, and to iterate more quickly from experimentation to production. Customers can compare prompt iterations side by side to assess how small changes impact outputs, and the service offers features like notes and tagging to boost collaboration. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Visit </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/start/quickstarts/quickstart#compare_prompt_output_by_model"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline"> to learn more.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Gen AI Evaluation Services </strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: We now support Gen AI Evaluation in GA to help users evaluate any generative model or application. While leaderboards and reports offer insights into overall model performance, they don't reveal how a model handles your specific needs. The Gen AI Evaluation Service helps you define your own evaluation criteria, ensuring a clear understanding of how well generative AI models and applications align with your unique use case. Users can define their own evaluation metrics and also access our templates for metrics with various criteria (e.g. text quality, instruction following, fluency). </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p>Why it matters: Evaluation is important at every step of your gen AI development process including model selection, prompt engineering, and model customization. Evaluating gen AI is integrated within Vertex AI to help you launch and reuse evaluations as needed.</p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Learn more in </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/models/evaluation-overview" style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen,Ubuntu,Cantarell,'Open Sans','Helvetica Neue',sans-serif"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline">.</span></p> </li> </ul></span></section><section class="Wy08Ac nRhiJb-qJTHM-OWXEXe-hJDwNd nRhiJb-DbgRPb-II5mzb-cGMI2b"><span class="dQQu7c" jsaction="rcuQ6b:npT2md" jscontroller="YSybTb" data-track-type="" soy-skip ssk='5:kbe95'><h3><strong style="vertical-align:baseline">Develop and deploy agents faster, grounded in your enterprise truth</strong></h3> <p><span style="vertical-align:baseline">Vertex AI Agent Builder allows you to easily and quickly build and customize AI Agents - for any skill level. A core component of the Vertex AI Agent Builder is Vertex AI Search, enabling you to ground the models in your data or the web. </span></p> <p><strong style="vertical-align:baseline">Grounding at Vertex</strong></p> <p><span style="vertical-align:baseline">You have many options for Grounding and RAG at Vertex. These capabilities address some of the most significant hurdles limiting the adoption of generative AI in the enterprise: the fact that models do not know information outside their training data, and the tendency of foundation models to “hallucinate,” or generate convincing yet factually inaccurate information. Retrieval Augmented Generation (</span><a href="https://cloud.google.com/use-cases/retrieval-augmented-generation?e=48754805&hl=en"><span style="text-decoration:underline;vertical-align:baseline">RAG</span></a><span style="vertical-align:baseline">), a technique developed to mitigate these challenges, first “retrieves” facts about a question, then provides those facts to the model before it “generates” an answer – this is what we mean by </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/grounding/overview?hl=en"><span style="text-decoration:underline;vertical-align:baseline">grounding</span></a><span style="vertical-align:baseline">. Getting relevant facts quickly to augment a model's knowledge is ultimately a search problem. </span></p> <p><span style="vertical-align:baseline">Read more at </span><a href="https://cloud.google.com/blog/products/ai-machine-learning/rag-and-grounding-on-vertex-ai?e=48754805"><span style="text-decoration:underline;vertical-align:baseline">this blog post</span></a><span style="vertical-align:baseline">.</span></p> <p><strong style="vertical-align:baseline">Grounding with Google Search is GA</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: When customers select Grounding with Google Search for their Gemini model, Gemini will use Google Search, and generate an output that is grounded with the relevant internet search results. Grounding with Google Search also offers dynamic retrieval, a new capability to help customers balance quality with cost efficiency by intelligently selecting when to use Google Search results and when to use the model’s training data. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: Grounding with Google Search is simple to use and makes the world’s knowledge available to Gemini. Dynamic retrieval will save you money and will save your users time, only grounding when needed.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Read </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/ground-gemini"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline"> to learn more about how to get started.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Grounding with third-party datasets</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Vertex AI will offer a new service that lets customers ground their models and AI agents with specialized third-party data. We are working with providers like Moody's, MSCI, Thomson Reuters and Zoominfo to enable access to their datasets.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: These capabilities will help customers build AI agents and applications that offer more accurate and helpful responses. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Coming soon, </span><a href="https://inthecloud.withgoogle.com/global-gen-ai-contact-sales/cs-bsm.html" rel="noopener" target="_blank"><span style="text-decoration:underline;vertical-align:baseline">contact sales</span></a><span style="vertical-align:baseline"> to learn more. </span></p> </li> </ul> <p><strong style="vertical-align:baseline">Grounding with high-fidelity mode </strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: High-fidelity mode is powered by a version of Gemini 1.5 Flash that’s been fine-tuned to only use customer-provided content to generate answers and ensures high levels of factuality in response. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: In data-intensive industries like financial services, healthcare, and insurance, generative AI use cases often require the generated response to be sourced from only the provided context, not the model’s world knowledge. Grounding with high-fidelity, announced in experimental preview, is purpose-built to support such grounding use cases, including summarization across multiple documents, data extraction against a set corpus of financial data, or processing across a predefined set of documents.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: </span><a href="https://inthecloud.withgoogle.com/global-gen-ai-contact-sales/cs-bsm.html" rel="noopener" target="_blank"><span style="text-decoration:underline;vertical-align:baseline">Contact sales</span></a><span style="vertical-align:baseline"> to learn more. </span></p> </li> </ul> <p><strong style="vertical-align:baseline">Expanding Vector Search to support hybrid search</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Vector Search, the ultra high performance vector database powering Vertex AI Search, DIY RAG, and other embedding use cases at global scale, now offers hybrid search in Public Preview. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: Embeddings are numerical representations that capture semantic relationships across complex data (text, images, etc.). Embeddings power multiple use cases, including recommendation systems, ad serving, and semantic search for RAG. Hybrid search combines vector-based and keyword-based search techniques to ensure the most relevant and accurate responses for users. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Visit </span><a href="https://cloud.google.com/vertex-ai/docs/vector-search/overview"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline"> to learn more about Vector Search.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">LangChain on Vertex</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: An agent development SDK and container runtime for LangChain. With LangChain on Vertex AI you can select the model you want to work with, define tools to access external APIs, structure the interface between the user and the system components in an orchestration framework, and deploy the framework to a managed runtime.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: LangChain on Vertex AI simplifies and speeds up deployment while being secure, private and scalable. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Visit </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/reasoning-engine/overview"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline"> to learn more. </span></p> </li> </ul> <p><strong style="vertical-align:baseline">Vertex AI extensions, function calling and data connectors </strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: </span></p> </li> <ul> <li style="list-style-type:circle;vertical-align:baseline"> <p><span style="vertical-align:baseline">Vertex AI extensions are pre-built reusable modules to connect a foundation model to a specific API or tool. For example, our new code interpreter extension enables models to execute tasks that entail running Python code, such as data analysis, data visualization, and mathematical operations. </span></p> </li> <li style="list-style-type:circle;vertical-align:baseline"> <p><span style="vertical-align:baseline">Vertex AI function calling enables a user to describe a set of functions or APIs and have Gemini models intelligently select, for a given query, the right API or function to call, along with the appropriate API parameters.</span></p> </li> <li style="list-style-type:circle;vertical-align:baseline"> <p><span style="vertical-align:baseline">Vertex AI data connectors help ingest data from enterprise and third-party applications like ServiceNow, Hadoop, and Salesforce, connecting generative applications to commonly-used enterprise systems.</span></p> </li> </ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: With these capabilities, Vertex AI Agent Builder makes it easy to augment grounding outputs and take action on your user’s behalf. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Visit documentation to learn more about Vertex AI </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/extensions/overview"><span style="text-decoration:underline;vertical-align:baseline">extensions</span></a><span style="vertical-align:baseline">, </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/function-calling"><span style="text-decoration:underline;vertical-align:baseline">function calling</span></a><span style="vertical-align:baseline"> and </span><a href="https://cloud.google.com/integration-connectors/docs/connectors/gsc_vertex_ai/configure"><span style="text-decoration:underline;vertical-align:baseline">data connectors</span></a><span style="vertical-align:baseline">.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Firebase Genkit </strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Genkit is an open-source TypeScript/JavaScript and Go framework designed by Firebase to simplify the development, deployment, and monitoring of production-ready AI applications.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: With the Vertex AI plugin for Genkit, developers can now take advantage of Google models like Gemini and Imagen 2, as well as text embeddings. Additionally Vertex Eval Service is baked into the Genkit local development experience along with OpenTelemetry tracing.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Learn more in </span><a href="https://firebase.google.com/docs/genkit" rel="noopener" target="_blank"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline">.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">LlamaIndex on Vertex AI</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: LlamaIndex on Vertex AI simplifies building your own search engine for retrieval-augmented generation (RAG), from data ingestion and transformation to embedding, indexing, retrieval, and generation.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: Vertex AI customers can leverage Google’s models and AI-optimized infrastructure alongside LlamaIndex’s simple, flexible, open-source data framework, to connect custom data sources to generative models. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Visit </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/llamaindex-on-vertexai" style="font-family:-apple-system,BlinkMacSystemFont,'Segoe UI',Roboto,Oxygen,Ubuntu,Cantarell,'Open Sans','Helvetica Neue',sans-serif"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline"> to learn more.</span></p> </li> </ul></span></section><section class="Wy08Ac nRhiJb-qJTHM-OWXEXe-hJDwNd nRhiJb-DbgRPb-II5mzb-cGMI2b"><span class="dQQu7c" jsaction="rcuQ6b:npT2md" jscontroller="YSybTb" data-track-type="" soy-skip ssk='5:kbe95'><h3><strong style="vertical-align:baseline">Built on a foundation of scale & enterprise readiness</strong></h3> <p><span style="vertical-align:baseline">The revolutionary nature of generative AI requires a platform that offers privacy, security, control, and compliance capabilities organizations can rely on. Google Cloud is committed to helping our customers leverage the full potential of generative AI with privacy, security, and compliance capabilities. Our goal is to build trust by protecting systems, enabling transparency, and offering flexible, always-available infrastructure, all while grounding efforts in our </span><a href="https://ai.google/responsibility/principles/" rel="noopener" target="_blank"><span style="text-decoration:underline;vertical-align:baseline">AI principles</span></a><span style="vertical-align:baseline">.</span></p> <p><strong style="vertical-align:baseline">Dynamic Shared Quota</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: With Dynamic Shared Quota, we offer increasing the quota limits for a model (online serving) to the maximum allowed per region. This way we limit the number of queries per second (QPS) that customers can run by the shared capacity of all the queries running on a Servo station (multi-region), instead of limiting a customer’s QPS by a quota. Dynamic Shared Quota is only applicable to Pay-as-you-go Online Serving. For customers that require a consistent or more predictable service level, including SLAs, we offer Provision Throughput.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: By dynamically distributing on-demand capacity among all queries being processed for Pay-as-you-go customers, Google Cloud has eliminated the need to submit quota increase requests (QIRs). Customers can still set a self-imposed quota called a consumer quota override to control cost and prevent budget overruns.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Learn more in </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/quotas#dynamic-shared-quota"><span style="text-decoration:underline;vertical-align:baseline">documentation</span></a><span style="vertical-align:baseline">.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Provisioned Throughput is GA </strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: Provisioned throughput lets customers responsibly scale their usage of Google’s first-party models, like 1.5 Flash, providing assurances for both capacity and price. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: This Vertex AI feature brings predictability and reliability to customer production workloads, giving them the assurance required to scale gen AI workloads aggressively. </span><span style="vertical-align:baseline"> We have also made it easier than ever for customers to set up PT via a Self Service flow. Customers can now </span><a href="http://console.cloud.google.com/vertex-ai/provisioned-throughput"><span style="text-decoration:underline;vertical-align:baseline">estimate their needs and purchase</span></a><span style="vertical-align:baseline"> Provisioned Throughput for Google’s 1P foundation models via the console, bringing the E2E experience down from weeks to minutes for pre-approved orders subject to available capacity and removing the need for manual order forms.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Follow </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/provisioned-throughput#place-an-order"><span style="text-decoration:underline;vertical-align:baseline">these steps</span></a><span style="vertical-align:baseline"> to purchase a Provisioned Throughput subscription.</span></p> </li> </ul> <p><strong style="vertical-align:baseline">Data residency for data stored at-rest guarantees in more countries</strong></p> <ul> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">What it is: We have data residency for data stored at-rest guarantees in 23 countries (13 of which were added in 2024), with additional guarantees around limiting related ML processing to the US and EU. We are also working on expanding our ML processing commitments to eight more countries, starting with four countries in 2024.</span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Why it matters: Customers, especially those from regulated industries, demand control over where their data is stored and processed when using generative AI capabilities. </span></p> </li> <li style="list-style-type:disc;vertical-align:baseline"> <p><span style="vertical-align:baseline">Get started: Learn more </span><a href="https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations"><span style="text-decoration:underline;vertical-align:baseline">here</span></a><span style="vertical-align:baseline">.</span></p> </li> </ul> <p><span style="vertical-align:baseline">To keep up with all of the latest releases, don’t forget to check our </span><a href="https://cloud.google.com/vertex-ai/docs/release-notes"><span style="text-decoration:underline;vertical-align:baseline">Vertex AI release notes</span></a><span style="vertical-align:baseline">. </span></p> <p><span style="vertical-align:baseline">All of these enhancements are a direct response to what you, our customers, have been asking for. We believe an enterprise AI platform is key to success in production and our goal is to not just build the best platform, but to provide an AI ecosystem that makes enterprise-scale AI accessible.</span></p> <p><span style="vertical-align:baseline">To learn about how Vertex AI can help you, </span><a href="https://inthecloud.withgoogle.com/global-gen-ai-contact-sales/cs-bsm.html?utm_source=cgc-blog&utm_medium=blog&utm_campaign=FY23-Q3-global-ENDM228-website-sm-gen-ai-contact-us-lp&utm_content=vertex-ai-evergreen-announcements&utm_term=-" rel="noopener" target="_blank"><span style="text-decoration:underline;vertical-align:baseline">contact us</span></a><span style="vertical-align:baseline"> for a free consultation.</span></p></span></section><section class="kcBhad"><section class="Fabbec"><span class="WrMNjb">Posted in</span><ul class="FzXI4e"><li class="I4B51b"><a href="https://cloud.google.com/blog/products/ai-machine-learning" track-metadata-position="body"track-metadata-eventdetail="cloud.google.com/blog/products/ai-machine-learning"track-metadata-module="tag list"track-metadata-module_headline="posted in">AI & Machine Learning</a></li><li class="I4B51b"><a href="https://cloud.google.com/blog/products/gcp" track-metadata-position="body"track-metadata-eventdetail="cloud.google.com/blog/products/gcp"track-metadata-module="tag list"track-metadata-module_headline="posted in">Google Cloud</a></li></ul></section></section></div></div></div></div></div><section class="nRhiJb-DARUcf " track-metadata-module="related articles" track-metadata-module_headline="related articles"><div class="nRhiJb-DbgRPb-c5RTEf-ma6Yeb nRhiJb-DbgRPb-wNfPc-cGMI2b"><h5 class="Qwf2Db-MnozTc Qwf2Db-MnozTc-OWXEXe-MnozTc-wNfPc nRhiJb-DbgRPb-II5mzb-cGMI2b">Related articles</h5><section class="m9cUGf HGev3 nJD2Qe nRhiJb-ObfsIf"><div class=" QaGyvd nRhiJb-kR0ZEf-OWXEXe-GV1x9e-c5RTEf nRhiJb-kR0ZEf-OWXEXe-GV1x9e-qWD73c-V2iZpe"><div class="mA0uBe"><a href="https://cloud.google.com/blog/topics/developers-practitioners/boost-your-continuous-delivery-pipeline-with-generative-ai" class="lD2oe" track-name="boost your continuous delivery pipeline with generative ai"track-type="card"track-metadata-eventdetail="cloud.google.com/blog/topics/developers-practitioners/boost-your-continuous-delivery-pipeline-with-generative-ai"><div class="AhkbS "><div class="hqnDEf"><section class="PBkdHd "><img class=" D5RK8d" src="https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg" alt="https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg" loading="lazy"/></section></div><div class="JUOx5b"><div class="Qwf2Db-MnozTc Qwf2Db-MnozTc-OWXEXe-MnozTc-qWD73c nRhiJb-DbgRPb-c5RTEf-ma6Yeb nRhiJb-BFbNVe-r8s4j-bMElCd FI6Gl nRhiJb-fmcmS-oXtfBe" track-name="developers & practitioners"track-type="tag">Developers & Practitioners</div><h3 class="Qwf2Db-MnozTc HGFKtc Qwf2Db-MnozTc-OWXEXe-MnozTc-wNfPc">Boost your Continuous Delivery pipeline with Generative AI</h3><p class="nRhiJb-cHYyed dTIXyb nRhiJb-DbgRPb-R6PoUb-ma6Yeb">By Giovanni Galloro • 7-minute read</p></div></div></a></div></div><div class=" QaGyvd nRhiJb-kR0ZEf-OWXEXe-GV1x9e-c5RTEf nRhiJb-kR0ZEf-OWXEXe-GV1x9e-qWD73c-V2iZpe"><div class="mA0uBe"><a href="https://cloud.google.com/blog/topics/developers-practitioners/learn-how-to-create-an-ai-agent-for-trip-planning-with-gemini-1-5-pro" class="lD2oe" track-name="build an ai agent for trip planning with gemini 15 pro: a step-by-step guide"track-type="card"track-metadata-eventdetail="cloud.google.com/blog/topics/developers-practitioners/learn-how-to-create-an-ai-agent-for-trip-planning-with-gemini-1-5-pro"><div class="AhkbS "><div class="hqnDEf"><section class="PBkdHd "><img class=" D5RK8d" src="https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg" alt="https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg" loading="lazy"/></section></div><div class="JUOx5b"><div class="Qwf2Db-MnozTc Qwf2Db-MnozTc-OWXEXe-MnozTc-qWD73c nRhiJb-DbgRPb-c5RTEf-ma6Yeb nRhiJb-BFbNVe-r8s4j-bMElCd FI6Gl nRhiJb-fmcmS-oXtfBe" track-name="developers & practitioners"track-type="tag">Developers & Practitioners</div><h3 class="Qwf2Db-MnozTc HGFKtc Qwf2Db-MnozTc-OWXEXe-MnozTc-wNfPc">Build an AI agent for trip planning with Gemini 1.5 Pro: A step-by-step guide</h3><p class="nRhiJb-cHYyed dTIXyb nRhiJb-DbgRPb-R6PoUb-ma6Yeb">By Kelci Mensah • 5-minute read</p></div></div></a></div></div><div class=" QaGyvd nRhiJb-kR0ZEf-OWXEXe-GV1x9e-c5RTEf nRhiJb-kR0ZEf-OWXEXe-GV1x9e-qWD73c-V2iZpe"><div class="mA0uBe"><a href="https://cloud.google.com/blog/topics/developers-practitioners/create-a-self-escalating-chatbot-in-conversational-agents" class="lD2oe" track-name="create a self-escalating chatbot in conversational agents using webhook and generators"track-type="card"track-metadata-eventdetail="cloud.google.com/blog/topics/developers-practitioners/create-a-self-escalating-chatbot-in-conversational-agents"><div class="AhkbS "><div class="hqnDEf"><section class="PBkdHd "><img class=" D5RK8d" src="https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg" alt="https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg" loading="lazy"/></section></div><div class="JUOx5b"><div class="Qwf2Db-MnozTc Qwf2Db-MnozTc-OWXEXe-MnozTc-qWD73c nRhiJb-DbgRPb-c5RTEf-ma6Yeb nRhiJb-BFbNVe-r8s4j-bMElCd FI6Gl nRhiJb-fmcmS-oXtfBe" track-name="developers & practitioners"track-type="tag">Developers & Practitioners</div><h3 class="Qwf2Db-MnozTc HGFKtc Qwf2Db-MnozTc-OWXEXe-MnozTc-wNfPc">Create a self-escalating chatbot in Conversational Agents using Webhook and Generators</h3><p class="nRhiJb-cHYyed dTIXyb nRhiJb-DbgRPb-R6PoUb-ma6Yeb">By Aniket Agrawal • 9-minute read</p></div></div></a></div></div><div class=" QaGyvd nRhiJb-kR0ZEf-OWXEXe-GV1x9e-c5RTEf nRhiJb-kR0ZEf-OWXEXe-GV1x9e-qWD73c-V2iZpe"><div class="mA0uBe"><a href="https://cloud.google.com/blog/products/ai-machine-learning/how-commerzbank-is-transforming-financial-advisory-workflows-with-gen-ai" class="lD2oe" track-name="how commerzbank is transforming financial advisory workflows with gen ai"track-type="card"track-metadata-eventdetail="cloud.google.com/blog/products/ai-machine-learning/how-commerzbank-is-transforming-financial-advisory-workflows-with-gen-ai"><div class="AhkbS "><div class="hqnDEf"><section class="PBkdHd "><img class=" D5RK8d" src="https://storage.googleapis.com/gweb-cloudblog-publish/original_images/Commerzbank-v3.gif" alt="https://storage.googleapis.com/gweb-cloudblog-publish/original_images/Commerzbank-v3.gif" loading="lazy"/></section></div><div class="JUOx5b"><div class="Qwf2Db-MnozTc Qwf2Db-MnozTc-OWXEXe-MnozTc-qWD73c nRhiJb-DbgRPb-c5RTEf-ma6Yeb nRhiJb-BFbNVe-r8s4j-bMElCd FI6Gl nRhiJb-fmcmS-oXtfBe" track-name="ai & machine learning"track-type="tag">AI & Machine Learning</div><h3 class="Qwf2Db-MnozTc HGFKtc Qwf2Db-MnozTc-OWXEXe-MnozTc-wNfPc">How Commerzbank is transforming financial advisory workflows with gen AI</h3><p class="nRhiJb-cHYyed dTIXyb nRhiJb-DbgRPb-R6PoUb-ma6Yeb">By Tolga Bastürk • 5-minute read</p></div></div></a></div></div></section></div></section></article></div></div><c-data id="i1" jsdata=" n2jFB;_;1"></c-data></c-wiz><script aria-hidden="true" nonce="5dAgjnjZnWn0wEH1uLTSYA">window.wiz_progress&&window.wiz_progress();window.wiz_tick&&window.wiz_tick('zPZHOe');</script><script nonce="5dAgjnjZnWn0wEH1uLTSYA">(function(){'use strict';var c=window,d=[];c.aft_counter=d;var e=[],f=0;function _recordIsAboveFold(a){if(!c._isLazyImage(a)&&!a.hasAttribute("data-noaft")&&a.src){var b=(c._isVisible||function(){})(c.document,a);a.setAttribute("data-atf",b);b&&(e.indexOf(a)!==-1||d.indexOf(a)!==-1||a.complete||d.push(a),a.hasAttribute("data-iml")&&(a=Number(a.getAttribute("data-iml")),a>f&&(f=a)))}} c.initAft=function(){f=0;e=Array.prototype.slice.call(document.getElementsByTagName("img")).filter(function(a){return!!a.getAttribute("data-iml")});[].forEach.call(document.getElementsByTagName("img"),function(a){try{_recordIsAboveFold(a)}catch(b){throw b.message=a.hasAttribute("data-iid")?b.message+"\nrecordIsAboveFold error for defer inlined image":b.message+("\nrecordIsAboveFold error for img element with <src: "+a.src+">"),b;}});if(d.length===0)c.onaft(f)};}).call(this); initAft()</script><script id="_ij" nonce="5dAgjnjZnWn0wEH1uLTSYA">window.IJ_values = [[null,null,"",false,null,null,true,false],'0','https:\/\/cloud.google.com\/blog\/',["cloudblog","products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai",["en","de","fr","ko","ja"],"en",null,"https://cloud.google.com/blog","blog_article","cloud.google.com",["https://console.cloud.google.com/freetrial/","https://cloud.google.com/contact/","https://cloud.google.com/","https://cloud.google.com/blog","https://cloud.google.com/","https://www.google.com/","https://cloud.google.com/products/","https://about.google.com/products/","https://about.google/intl/en/","https://support.google.com"],["googlecloud","googlecloud","showcase/google-cloud","googlecloud/","googlecloud/"],true], null ,'boq_cloudx-web-blog-uiserver_20241121.08_p0','cloud.google.com',["SG",1],[[["bigquery_ftv",["bigquery_ftv",[["control",["control",[97716263,97716264],["/bigquery"]]],["variantA",["variantA",[97716265,97716266],["/bigquery"]]],["variantB",["variantB",[97716267,97716268],["/bigquery"]]],["variantC",["variantC",[97716269,97716270],["/bigquery"]]]]]],["jss",["jss",[["control",["control",[93803230,93804391],["/products/ai","/products/compute","/solutions/web-hosting"]]],["variantA",["variantA",[93803231,93804392],["/products/ai","/products/compute","/solutions/web-hosting"]]],["variantB",["variantB",[93803232,93804393],["/products/ai","/products/compute","/solutions/web-hosting"]]],["variantC",["variantC",[93803233,93804394],["/products/ai","/products/compute","/solutions/web-hosting"]]]]]]]], 0.0 ,["GTM-5CVQBG",[["en","\u202aEnglish\u202c",true,"en"],["de","\u202aDeutsch\u202c",true,"de"],["es","\u202aEspañol\u202c",true,"es"],["es-419","\u202aEspañol (Latinoamérica)\u202c",true,"es-419"],["fr","\u202aFrançais\u202c",true,"fr"],["id","\u202aIndonesia\u202c",true,"id"],["it","\u202aItaliano\u202c",true,"it"],["pt-BR","\u202aPortuguês (Brasil)\u202c",true,"pt-BR"],["zh-CN","\u202a简体中文\u202c",true,"zh-Hans"],["zh-TW","\u202a繁體中文\u202c",true,"zh-Hant"],["ja","\u202a日本語\u202c",true,"ja"],["ko","\u202a한국어\u202c",true,"ko"]],["83405","AIzaSyD3LJeW4Q6gtdgJlyeFZUp-GhpIoc6EUeg"],"en",null,null,[],[["https://cloud.google.com/innovators","https://cloud.google.com/innovators/plus/activate","https://cloud.google.com/innovators/innovatorsplus"],["https://workspace.google.com/pricing","https://www.x.com/googleworkspace","https://www.facebook.com/googleworkspace","https://www.youtube.com/channel/UCBmwzQnSoj9b6HzNmFrg_yw","https://www.instagram.com/googleworkspace","https://www.linkedin.com/showcase/googleworkspace","https://about.google/?utm_source\u003dworkspace.google.com\u0026utm_medium\u003dreferral\u0026utm_campaign\u003dgsuite-footer-en","https://about.google/products/?tip\u003dexplore","https://workspace.google.com","https://workspace.google.com/contact/?source\u003dgafb-form-globalnav-en","https://workspace.google.com/business/signup/welcome?hl\u003den\u0026source\u003dgafb-form-globalnav-en","https://workspace.google.com/blog"],["https://www.cloudskillsboost.google","https://www.cloudskillsboost.google?utm_source\u003dcgc\u0026utm_medium\u003dwebsite\u0026utm_campaign\u003devergreen","https://www.cloudskillsboost.google/subscriptions?utm_source\u003dcgc\u0026utm_medium\u003dwebsite\u0026utm_campaign\u003devergreenlaunchpromo","https://www.cloudskillsboost.google/subscriptions?utm_source\u003dcgc\u0026utm_medium\u003dwebsite\u0026utm_campaign\u003devergreen","https://www.cloudskillsboost.google/catalog?utm_source\u003dcgc\u0026utm_medium\u003dwebsite\u0026utm_campaign\u003devergreen","https://www.cloudskillsboost.google/paths?utm_source\u003dcgc\u0026utm_medium\u003dwebsite\u0026utm_campaign\u003devergreen"],["https://mapsplatform.google.com"],["https://cloud.google.com/developers","https://cloud.google.com/developers/settings?utm_source\u003dinnovators"],["https://console.cloud.google.com/freetrial","https://console.cloud.google.com/","https://console.cloud.google.com/freetrial?redirectPath\u003dhttps://cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai"],["https://aitestkitchen.withgoogle.com/signup","https://blog.google/technology/ai/join-us-in-the-ai-test-kitchen/","https://cloud.google.com/ai"],["https://googlecloudplatform.blogspot.com/","https://github.com/GoogleCloudPlatform","https://www.linkedin.com/company/google-cloud","https://twitter.com/GoogleCloud_sg","https://www.facebook.com/googlecloud","https://www.youtube.com/GoogleCloudAPAC"]],[2024,11,27],[["en","x-default"],"x-default"],[null,true],null,"/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai?hl\u003den",["6LcsrxUqAAAAAFhpR1lXsPN2j2nsTwy6JTbRKzJr"]],[],'','5dAgjnjZnWn0wEH1uLTSYA','o4N8v0zrwhDVSCCR3FZNIg','DEFAULT','\/blog', 2024.0 ,'https:\/\/cloud.google.com\/blog\/products\/ai-machine-learning\/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai', null ,'ltr', false ,'https:\/\/accounts.google.com\/AccountChooser?continue\x3dhttps:\/\/cloud.google.com\/blog\/products\/ai-machine-learning\/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai\x26hl\x3den-US','https:\/\/accounts.google.com\/ServiceLogin?hl\x3den-US\x26continue\x3dhttps:\/\/cloud.google.com\/blog\/products\/ai-machine-learning\/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai','https:\/\/accounts.google.com\/SignOutOptions?continue\x3dhttps:\/\/cloud.google.com\/blog\/products\/ai-machine-learning\/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai',[[[1]]], false , false , false ,'en','en-US','en_US','https:\/\/goto2.corp.google.com\/mdtredirect?data_id_filter\x3dcloud.google.com\x26system_name\x3dcloudx-web-blog-uiserver', null , null ,'https:\/\/myaccount.google.com\/privacypolicy?hl\x3den-US', false , null ,'https:\/\/www.gstatic.com\/_\/boq-cloudx-web-blog\/_\/r\/','https:\/\/myaccount.google.com\/termsofservice?hl\x3den-US',[[[["Solutions \u0026 technology",null,[[["AI \u0026 Machine Learning","/blog/products/ai-machine-learning"],["API Management","/blog/products/api-management"],["Application Development","/blog/products/application-development"],["Application Modernization","/blog/products/application-modernization"],["Chrome Enterprise","/blog/products/chrome-enterprise"],["Compute","/blog/products/compute"],["Containers \u0026 Kubernetes","/blog/products/containers-kubernetes"],["Data Analytics","/blog/products/data-analytics"],["Databases","/blog/products/databases"],["DevOps \u0026 SRE","/blog/products/devops-sre"],["Maps \u0026 Geospatial","/blog/topics/maps-geospatial"],["Security",null,[[["Security \u0026 Identity","/blog/products/identity-security"],["Threat Intelligence","/blog/topics/threat-intelligence"]]]],["Infrastructure","/blog/products/infrastructure"],["Infrastructure Modernization","/blog/products/infrastructure-modernization"],["Networking","/blog/products/networking"],["Productivity \u0026 Collaboration","/blog/products/productivity-collaboration"],["SAP on Google Cloud","/blog/products/sap-google-cloud"],["Storage \u0026 Data Transfer","/blog/products/storage-data-transfer"],["Sustainability","/blog/topics/sustainability"]]]],["Ecosystem",null,[[["IT Leaders","/transform"],["Industries",null,[[["Financial Services","/blog/topics/financial-services"],["Healthcare \u0026 Life Sciences","/blog/topics/healthcare-life-sciences"],["Manufacturing","/blog/topics/manufacturing"],["Media \u0026 Entertainment","/blog/products/media-entertainment"],["Public Sector","/blog/topics/public-sector"],["Retail","/blog/topics/retail"],["Supply Chain","/blog/topics/supply-chain-logistics"],["Telecommunications","/blog/topics/telecommunications"]]]],["Partners","/blog/topics/partners"],["Startups \u0026 SMB","/blog/topics/startups"],["Training \u0026 Certifications","/blog/topics/training-certifications"],["Inside Google Cloud","/blog/topics/inside-google-cloud"],["Google Cloud Next \u0026 Events","/blog/topics/google-cloud-next"],["Google Maps Platform","https://mapsplatform.google.com/resources/blog/"],["Google Workspace","https://workspace.google.com/blog"]]]],["Developers \u0026 Practitioners","/blog/topics/developers-practitioners"],["Transform with Google Cloud","/transform"]]],[["de",[[["Neuigkeiten","/blog/de/topics/whats-new/aktuelles-auf-dem-google-cloud-blog"],["Lösungen \u0026 Technologien",null,[[["Anwendungsentwicklung","/blog/de/products/application-development"],["Anwendungsmodernisierung","/blog/de/products/anwendungsmodernisierung"],["API-Verwaltung","/blog/de/products/api-management"],["Chrome Enterprise","/blog/de/products/chrome-enterprise"],["Computing","/blog/de/products/compute"],["Containers \u0026 Kubernetes","/blog/de/products/containers-kubernetes"],["Datenanalysen","/blog/de/products/data-analytics"],["Datenbanken","/blog/de/products/databases"],["DevOps \u0026 SRE","/blog/de/products/devops-sre"],["Infrastruktur","/blog/de/products/infrastructure"],["KI \u0026 Machine Learning","/blog/de/products/ai-machine-learning"],["Maps \u0026 Geospatial","/blog/de/topics/maps-geospatial"],["Modernisierung der Infrastruktur","/blog/de/products/modernisierung-der-infrastruktur"],["Nachhaltigkeit","/blog/de/topics/nachhaltigkeit"],["Netzwerk","/blog/de/products/networking"],["Produktivität und Zusammenarbeit","/blog/de/products/produktivitaet-und-kollaboration"],["SAP in Google Cloud","/blog/de/products/sap-google-cloud"],["Sicherheit \u0026 Identität","/blog/de/products/identity-security"],["Speicher und Datentransfer","/blog/de/products/storage-data-transfer"]]]],["Ökosystem",null,[[["IT Leader","/transform/de"],["Industrien",null,[[["Behörden und öffentlicher Sektor","/blog/de/topics/public-sector"],["Einzelhandel","/blog/de/topics/retail"],["Fertigung","/blog/de/topics/fertigung"],["Finanzdienstleistungen","/blog/de/topics/financial-services"],["Gesundheitswesen und Biowissenschaften","/blog/de/topics/healthcare-life-sciences"],["Lieferkette und Logistik","/blog/de/topics/lieferkette-und-logistik"],["Medien und Unterhaltung","/blog/de/products/media-entertainment"],["Telekommunikation","/blog/de/topics/telecommunications"]]]],["Entwickler*innen \u0026 Fachkräfte","/blog/de/topics/developers-practitioners"],["Google Cloud Next \u0026 Events","/blog/de/topics/events"],["Google Maps Platform","/blog/de/products/maps-platform"],["Google Workspace","https://workspace.google.com/blog/de"],["Inside Google Cloud","/blog/de/topics/inside-google-cloud"],["Kunden","/blog/de/topics/kunden"],["Partner","/blog/de/topics/partners"],["Start-ups und KMU","/blog/de/topics/startups"],["Training und Zertifizierung","/blog/de/topics/training-certifications"]]]],["Transformation mit Google Cloud","/transform/de"]]]],["en",[[["Solutions \u0026 technology",null,[[["AI \u0026 Machine Learning","/blog/products/ai-machine-learning"],["API Management","/blog/products/api-management"],["Application Development","/blog/products/application-development"],["Application Modernization","/blog/products/application-modernization"],["Chrome Enterprise","/blog/products/chrome-enterprise"],["Compute","/blog/products/compute"],["Containers \u0026 Kubernetes","/blog/products/containers-kubernetes"],["Data Analytics","/blog/products/data-analytics"],["Databases","/blog/products/databases"],["DevOps \u0026 SRE","/blog/products/devops-sre"],["Maps \u0026 Geospatial","/blog/topics/maps-geospatial"],["Security",null,[[["Security \u0026 Identity","/blog/products/identity-security"],["Threat Intelligence","/blog/topics/threat-intelligence"]]]],["Infrastructure","/blog/products/infrastructure"],["Infrastructure Modernization","/blog/products/infrastructure-modernization"],["Networking","/blog/products/networking"],["Productivity \u0026 Collaboration","/blog/products/productivity-collaboration"],["SAP on Google Cloud","/blog/products/sap-google-cloud"],["Storage \u0026 Data Transfer","/blog/products/storage-data-transfer"],["Sustainability","/blog/topics/sustainability"]]]],["Ecosystem",null,[[["IT Leaders","/transform"],["Industries",null,[[["Financial Services","/blog/topics/financial-services"],["Healthcare \u0026 Life Sciences","/blog/topics/healthcare-life-sciences"],["Manufacturing","/blog/topics/manufacturing"],["Media \u0026 Entertainment","/blog/products/media-entertainment"],["Public Sector","/blog/topics/public-sector"],["Retail","/blog/topics/retail"],["Supply Chain","/blog/topics/supply-chain-logistics"],["Telecommunications","/blog/topics/telecommunications"]]]],["Partners","/blog/topics/partners"],["Startups \u0026 SMB","/blog/topics/startups"],["Training \u0026 Certifications","/blog/topics/training-certifications"],["Inside Google Cloud","/blog/topics/inside-google-cloud"],["Google Cloud Next \u0026 Events","/blog/topics/google-cloud-next"],["Google Maps Platform","https://mapsplatform.google.com/resources/blog/"],["Google Workspace","https://workspace.google.com/blog"]]]],["Developers \u0026 Practitioners","/blog/topics/developers-practitioners"],["Transform with Google Cloud","/transform"]]]],["fr",[[["Les tendances","/blog/fr/topics/les-tendances/quelles-sont-les-nouveautes-de-google-cloud"],["Solutions et Technologie",null,[[["Analyse de données","/blog/fr/products/analyse-de-donnees/"],["Bases de données","/blog/fr/products/databases"],["Calcul","/blog/fr/products/calcul/"],["Chrome Entreprise","/blog/fr/products/chrome-enterprise/"],["Conteneurs et Kubernetes","/blog/fr/products/conteneurs-et-kubernetes/"],["Développement d'Applications","/blog/fr/products/application-development"],["Développement durable","/blog/fr/topics/developpement-durable"],["DevOps et ingénierie SRE","/blog/fr/products/devops-sre"],["Gestion des API","/blog/fr/products/api-management"],["IA et Machine Learning","/blog/fr/products/ai-machine-learning"],["Infrastructure","/blog/fr/products/infrastructure"],["Maps et Géospatial","/blog/fr/topics/maps-geospatial"],["Modernisation d'Applications","/blog/fr/products/modernisation-dapplications/"],["Modernisation d'Infrastructure","/blog/fr/products/modernisation-dinfrastructure/"],["Networking","/blog/fr/products/networking"],["Productivité et Collaboration","/blog/fr/products/productivite-et-collaboration"],["SAP sur Google Cloud","/blog/fr/products/sap-google-cloud"],["Sécurité et Identité","/blog/fr/products/identity-security"],["Stockage et transfert de données","/blog/fr/products/storage-data-transfer"]]]],["Écosystème",null,[[["Responsables IT","/transform/fr"],["Industries",null,[[["Commerce","/blog/fr/topics/retail"],["Manufacturing","/blog/fr/topics/manufacturing"],["Médias et Divertissement","/blog/fr/products/media-entertainment"],["Santé","/blog/fr/topics/healthcare-life-sciences"],["Secteur Public","/blog/fr/topics/public-sector"],["Services Financiers","/blog/fr/topics/financial-services"],["Supply Chain","/blog/fr/topics/supply-chain/"],["Telecommunications","/blog/fr/topics/telecommunications"]]]],["Clients","/blog/fr/topics/clients/"],["Développeurs et professionnels","/blog/fr/topics/developers-practitioners"],["Formations et certifications","/blog/fr/topics/training-certifications"],["Google Cloud Next et Événements","/blog/fr/topics/evenements"],["Google Maps Platform","/blog/fr/products/maps-platform"],["Google Workspace","https://workspace.google.com/blog/fr"],["Inside Google Cloud","/blog/fr/topics/inside-google-cloud"],["Partenaires","/blog/fr/topics/partners"],["Start-ups et PME","/blog/fr/topics/startups"]]]],["Transformer avec Google Cloud","/transform/fr"]]]],["ja",[[["ソリューションとテクノロジー",null,[[["AI \u0026 機械学習","/blog/ja/products/ai-machine-learning"],["API 管理","/blog/ja/products/api-management"],["アプリケーション開発","/blog/ja/products/application-development"],["アプリケーションモダナイゼーション","/blog/ja/products/application-modernization"],["Chrome Enterprise","/blog/ja/products/chrome-enterprise"],["コンピューティング","/blog/ja/products/compute"],["Containers \u0026 Kubernetes","/blog/ja/products/containers-kubernetes"],["データ分析","/blog/ja/products/data-analytics"],["データベース","/blog/ja/products/databases"],["DevOps \u0026 SRE","/blog/ja/products/devops-sre"],["Maps \u0026 Geospatial","/blog/ja/products/maps-platform"],["セキュリティ",null,[[["セキュリティ \u0026 アイデンティティ","/blog/ja/products/identity-security"],["脅威インテリジェンス","/blog/ja/topics/threat-intelligence"]]]],["インフラストラクチャ","/blog/ja/products/infrastructure"],["インフラモダナイゼーション","/blog/ja/products/infrastructure-modernization"],["ネットワーキング","/blog/ja/products/networking"],["生産性とコラボレーション","/blog/ja/products/productivity-collaboration"],["Google Cloud での SAP","/blog/ja/products/sap-google-cloud"],["ストレージとデータ転送","/blog/ja/products/storage-data-transfer"],["サステナビリティ","/blog/ja/topics/sustainability"]]]],["エコシステム",null,[[["ITリーダー","/transform/ja"],["業種",null,[[["金融サービス","/blog/ja/topics/financial-services"],["ヘルスケア、ライフサイエンス","/blog/ja/topics/healthcare-life-sciences"],["製造","/blog/ja/topics/manufacturing"],["メディア、エンターテイメント","/blog/ja/products/media-entertainment"],["公共部門","/blog/ja/topics/public-sector"],["小売業","/blog/ja/topics/retail"],["サプライチェーン","/blog/ja/topics/supply-chain-logistics"],["通信","/blog/ja/topics/telecommunications"]]]],["顧客事例","/blog/ja/topics/customers"],["パートナー","/blog/ja/topics/partners"],["スタートアップ \u0026 SMB","/blog/ja/topics/startups"],["トレーニングと認定","/blog/ja/topics/training-certifications"],["Inside Google Cloud","/blog/ja/topics/inside-google-cloud"],["Google Cloud Next とイベント","/blog/ja/topics/google-cloud-next"],["Google Maps Platform","/blog/ja/products/maps-platform"],["Google Workspace","https://workspace.google.com/blog/ja"]]]],["デベロッパー","/blog/ja/topics/developers-practitioners"],["Transform with Google Cloud","/transform/ja"]]]],["ko",[[["솔루션 및 기술",null,[[["AI 및 머신러닝","/blog/ko/products/ai-machine-learning"],["API 관리","/blog/ko/products/api-management"],["애플리케이션 개발","/blog/ko/products/application-development"],["애플리케이션 현대화","/blog/ko/products/application-modernization"],["Chrome Enterprise","/blog/products/chrome-enterprise"],["컴퓨팅","/blog/ko/products/compute"],["컨테이너 \u0026 Kubernetes","/blog/ko/products/containers-kubernetes"],["데이터 분석","/blog/ko/products/data-analytics"],["데이터베이스","/blog/ko/products/databases"],["DevOps 및 SRE","/blog/ko/products/devops-sre"],["Maps \u0026 Geospatial","/blog/ko/products/maps-platform"],["보안",null,[[["보안 \u0026 아이덴티티","/blog/ko/products/identity-security"],["위협 인텔리전스","/blog/ko/topics/threat-intelligence"]]]],["인프라","/blog/ko/products/infrastructure"],["Infrastructure Modernization","/blog/ko/products/infrastructure-modernization"],["네트워킹","/blog/ko/products/networking"],["생산성 및 공동작업","/blog/ko/products/productivity-collaboration"],["SAP on Google Cloud","/blog/ko/products/sap-google-cloud"],["스토리지 및 데이터 전송","/blog/ko/products/storage-data-transfer"],["지속가능성","/blog/ko/topics/sustainability"]]]],["에코시스템",null,[[["IT Leaders","/transform/ko"],["업종",null,[[["금융 서비스","/blog/ko/topics/financial-services"],["의료 및 생명과학","/blog/ko/topics/healthcare-life-sciences"],["제조업","/blog/ko/topics/manufacturing"],["미디어 및 엔터테인먼트","/blog/ko/products/media-entertainment"],["공공부문","/blog/ko/topics/public-sector"],["소매업","/blog/ko/topics/retail"],["공급망","/blog/topics/supply-chain-logistics"],["통신","/blog/ko/topics/telecommunications"]]]],["고객 사례","/blog/ko/topics/customers"],["파트너","/blog/ko/topics/partners"],["스타트업 \u0026 SMB","/blog/ko/topics/startups"],["교육 \u0026 인증","/blog/ko/topics/training-certifications"],["Inside Google Cloud","/blog/ko/topics/inside-google-cloud"],["Google Cloud Next 및 이벤트","/blog/ko/topics/google-cloud-next"],["Google Maps Platform","/blog/ko/products/maps-platform"],["Google Workspace","https://workspace.google.com/blog/ko"]]]],["개발 및 IT운영","/blog/ko/topics/developers-practitioners"],["Google Cloud와 함께 하는 디지털 혁신","/transform/ko"]]]]]],'cloud.google.com','https', null , false , null ,[[97656899,97863170,97517172,97535270,48887082,93778619,97442199,48554500,1706538,97785988,1714240,93874004,97684535,97863042,48830069,97716267,48489819,97656881,97517154,48887064,97442181,97785970,93873986,97684517],null,null,null,null,true],]; window.IJ_valuesCb && window.IJ_valuesCb();</script><script class="ds:0" nonce="5dAgjnjZnWn0wEH1uLTSYA">AF_initDataCallback({key: 'ds:0', hash: '1', data:[["Your ultimate guide to the latest in generative AI on Vertex AI","Learn about the latest AI advancements on Google Cloud Vertex AI. This covers new models, features, and enterprise tools to unlock generative AI.",[1727395200],"https://storage.googleapis.com/gweb-cloudblog-publish/images/ultimate_guide_82924.max-2500x2500.jpg","https://cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai",[1724972404,344005000]],[["Warren Barkley","Sr. Director of Product Management"],["Stephanie Wong","Head of Technical Storytelling"]],[null,"\u003cscript type\u003d\"application/ld+json\"\u003e{\"@context\":\"https://schema.org\",\"@type\":\"BlogPosting\",\"@id\":\"https://cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai\",\"headline\":\"Your ultimate guide to the latest in generative AI on Vertex AI\",\"description\":\"Learn about the latest AI advancements on Google Cloud Vertex AI. This covers new models, features, and enterprise tools to unlock generative AI.\",\"image\":\"https://storage.googleapis.com/gweb-cloudblog-publish/images/ultimate_guide_82924.max-2500x2500.jpg\",\"author\":[{\"@type\":\"Person\",\"name\":\"Warren Barkley\",\"url\":\"\"},{\"@type\":\"Person\",\"name\":\"Stephanie Wong\",\"url\":\"\"}],\"datePublished\":\"2024-09-27\",\"publisher\":{\"@type\":\"Organization\",\"name\":\"Google Cloud\",\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https://www.gstatic.com/devrel-devsite/prod/v8bb8fa0afe9a8c3a776ebeb25d421bb443344d789b3607754dfabea418b8c4be/cloud/images/cloud-logo.svg\"}},\"url\":\"https://cloud.google.com/blog/products/ai-machine-learning/your-ultimate-guide-to-the-latest-in-generative-ai-on-vertex-ai\",\"keywords\":[\"AI \\u0026 Machine Learning\",\"Google Cloud\"],\"timeRequired\":\"PT24M\"}\u003c/script\u003e"],["Your ultimate guide to the latest in generative AI on Vertex AI"],["https://storage.googleapis.com/gweb-cloudblog-publish/images/ultimate_guide_82924.max-2500x2500.jpg","https://storage.googleapis.com/gweb-cloudblog-publish/images/ultimate_guide_82924.max-1300x1300.jpg 1288w, https://storage.googleapis.com/gweb-cloudblog-publish/images/ultimate_guide_82924.max-2500x2500.jpg 2436w"," 1288px, 2436px","https://storage.googleapis.com/gweb-cloudblog-publish/images/ultimate_guide_82924.max-2500x2500.jpg"],null,[[null,null,[null,[null,"\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eThe world of generative AI is evolving at a pace that's nothing short of mind-blowing. It feels like just yesterday we were marveling at AI-generated images, and now we're having full-fledged conversations with AI chatbots that can write code, craft poetry, and even serve our customers (check out our \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/transform/101-real-world-generative-ai-use-cases-from-industry-leaders\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003elist of 101 real-world gen AI use cases\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e from the world's leading organizations).\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eThe pace of innovation can be hard to keep up with \u2014 in 2023 we introduced over 500 new features in Vertex AI and we\u2019re not slowing down this year. We put this blog together to help you keep track of the biggest announcements and make sense of what they mean for your business. We\u2019ll keep it updated as new announcements come out, so bookmark this link and check out our new video series below also covering new announcements.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003ch3\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eCatch up on the latest announcements\u003c/strong\u003e\u003c/h3\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eAs part of our \u003c/span\u003e\u003ca href\u003d\"https://cloudonair.withgoogle.com/events/gemini-at-work-24?utm_source\u003dthe_keyword\u0026amp;utm_medium\u003dblog\u0026amp;utm_campaign\u003dFY24-Q3-global-EXP134-onlineevent-er-gemini-at-work-2024-mc\u0026amp;utm_content\u003dtk-gaw-blog\u0026amp;utm_term\u003d-\" rel\u003d\"noopener\" target\u003d\"_blank\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eGemini at Work\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e global event, we showcased \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/blog/products/ai-machine-learning/how-customers-are-putting-gemini-to-work?e\u003d48754805\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003enearly 50 new customer stories\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e from organizations around the world to highlight just how impactful generative AI can be when you put it to work at scale.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWe\u2019re inspired by what customers are building and excited to announce a few exciting updates to our models and platform, designed to help move gen AI from \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/blog/products/ai-machine-learning/experimentation-to-production-with-gemini-and-vertex-ai?e\u003d48754805\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eexperimentation into production with Vertex AI\u003c/span\u003e\u003c/a\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003e.\u003c/strong\u003e\u003c/p\u003e"]]],[null,["$300 in free credit to try Google Cloud AI and ML",null,"Start building for free","http://console.cloud.google.com/freetrial?redirectPath\u003d/vertex-ai/",[null,"\u003cp\u003eBuild and test your proof of concept with $300 in free credit for new customers. Plus, all customers get free monthly usage of 20+ products, including AI APIs.\u003c/p\u003e"]]],[null,null,null,null,null,null,["https://www.youtube.com/watch?v\u003dxN5q77t5hdI",[null,""],null,["https://storage.googleapis.com/gweb-cloudblog-publish/images/maxresdefault_pBw7HU9.max-1300x1300.jpg","https://storage.googleapis.com/gweb-cloudblog-publish/images/maxresdefault_pBw7HU9.max-1100x1100.jpg 1060w, https://storage.googleapis.com/gweb-cloudblog-publish/images/maxresdefault_pBw7HU9.max-1300x1300.jpg 1280w"," 1060px, 1280px","https://storage.googleapis.com/gweb-cloudblog-publish/images/maxresdefault_pBw7HU9.max-1300x1300.jpg"]]],[null,null,[null,[null,"\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eUpdates to Gemini Models\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: \u003c/span\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eThe newly updated versions of \u003c/span\u003e\u003ca href\u003d\"https://console.cloud.google.com/vertex-ai/studio/freeform?model\u003dgemini-1.5-pro-002\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eGemini 1.5 Pro\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e and \u003c/span\u003e\u003ca href\u003d\"https://console.cloud.google.com/vertex-ai/studio/freeform?model\u003dgemini-1.5-flash-002\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eFlash\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e models, both GA, deliver quality improvements in math, long context understanding, and vision.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: Our objective is to bring you the best models suited for enterprise use cases, by pushing the boundaries across performance, latency, and costs. From a latency standpoint, the new version of Gemini 1.5 Flash is nearly 2.5x faster than GPT-4o mini.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: \u003c/span\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eAccess \u003c/span\u003e\u003ca href\u003d\"https://console.cloud.google.com/vertex-ai/studio/freeform?model\u003dgemini-1.5-pro-002\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eGemini 1.5 Pro\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e and \u003c/span\u003e\u003ca href\u003d\"https://console.cloud.google.com/vertex-ai/studio/freeform?model\u003dgemini-1.5-flash-002\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eFlash\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e in the Google Cloud console.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eReduced Gemini 1.5 Pro Pricing\u00a0\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: We are reducing costs of Gemini 1.5 Pro by \u003c/span\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e50%\u003c/span\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e across both input and output tokens, effective on Vertex AI on October 7, 2024.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: We are committed to making AI accessible for every enterprise.\u00a0 \u003c/span\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eIn August, we improved Gemini 1.5 Flash to reduce costs by up to 80% (see below). \u003c/span\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eThese world class models can be coupled with capabilities like context caching to even further reduce the cost and latency of your long context queries. Using Batch API instead of standard requests can further optimize costs for latency insensitive tasks.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Visit the \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/pricing\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003epricing page\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to learn more.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eUpdates to Imagen 3\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Google\u2019s latest image generation model, delivering outstanding image quality, multi-language support, built-in safety features like Google DeepMind\u2019s SynthID digital watermarking, and support for multiple aspect ratios.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: There are several improvements over Imagen 2 \u2014 including over 40% faster generation for rapid prototyping and iteration; better prompt understanding and instruction-following; photo-realistic generations, including of groups of people; and greater control over text rendering within an image.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: \u003c/span\u003e\u003ca href\u003d\"https://docs.google.com/forms/d/e/1FAIpQLSdMHAK_KJygnvV2Psga7FIzKAhAqIBS_bHYzfgf_Y2h7fsoGA/viewform\" rel\u003d\"noopener\" target\u003d\"_blank\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eApply\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e for access to Imagen 3 on Vertex AI.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eControlled generation is now GA\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Controlled generation lets customers define Gemini model outputs according to specific formats or schemas.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: Most models cannot guarantee the format and syntax of their outputs, even with specified instructions. Vertex AI controlled generation lets customers choose the desired output format via pre-built options like JSON and ENUM, or by defining custom formats.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Visit \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/control-generated-output\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to learn more.\u00a0\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eBatch API\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Batch API (currently in preview) is a super-efficient way to send large numbers of non-latency sensitive text prompt requests, supporting use cases such as classification and sentiment analysis, data extraction, and description generation.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: It helps speed up developer workflows and reduces costs by enabling multiple prompts to be sent to models in a single request.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: View \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/batch-prediction-gemini\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to get started.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eSupervised fine tuning (SFT) for Gemini 1.5 Flash and Pro\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: SFT for Gemini 1.5 Flash and Pro is now generally available. SFT adapts model behavior with a labeled dataset, adjusting the model's weights to minimize the difference between its predictions and the actual labels.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: SFT allows you to tune the model to be more precise for your enterprise task. It's particularly effective for domain-specific applications where the language or content significantly differs from the data the large model was originally trained on.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Visit \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/models/gemini-supervised-tuning\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to learn more.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eDistillation techniques in Vertex AI\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Train smaller, specialized models that inherit the knowledge of the larger Gemini model, achieving comparable performance with the flexibility of self-hosting your custom model on Vertex AI.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: Deploying large language models can be a resource-intensive challenge. With distillation techniques in Vertex AI, you can leverage the power of those large models while keeping your deployments lean and efficient.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Fill out \u003c/span\u003e\u003ca href\u003d\"https://docs.google.com/forms/d/e/1FAIpQLSdsew3X0NCdsZb7sBYpFlXwPyRKK8XFuVX8EqDF5Xr_XJCRAA/viewform?resourcekey\u003d0-pxT7SeEQJCxzLc0FtiBSvQ\" rel\u003d\"noopener\" target\u003d\"_blank\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003ethis form\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e for early access.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003ePrompt Optimizer, now in preview\u00a0\u00a0\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Based on Google Research\u2019s publication on automatic prompt optimization (APO) methods, Prompt Optimizer adapts your prompts using the optimal instructions and examples to elicit the best performance from your chosen model.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: Vertex AI\u2019s Prompt Optimizer helps you avoid the tedious trial-and-error of prompt engineering. Plus, our \u003c/span\u003e\u003ca href\u003d\"https://ai.google.dev/gemini-api/docs/prompting-strategies\" rel\u003d\"noopener\" target\u003d\"_blank\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eprompt strategies guide\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e helps you make the models more verbose and conversational.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Learn more in \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/prompts/prompt-optimizer\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003ePrompt Management SDK\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Vertex AI\u2019s Prompt Management SDK allows users to retrieve and organize prompts. It lets you version prompts, restore old prompts, and generate suggestions to improve performance.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: This makes it easier for you to get the best performance from gen AI models at scale, and to iterate more quickly from experimentation to production.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: The prompt management SDK will be generally available in the coming weeks.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eMultimodal function calling\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Function calling is a built-in feature of the Gemini API that translates natural language into structured data and back.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: Now, with multimodal function calling, your agents can also execute functions where your user can provide images, along with text, to help the model pick the right function and function parameters to call.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Learn more in \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/function-calling\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eOrg policy for models in Model Garden\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: You can now govern the models available in Model Garden. This includes limiting access to gen AI features, to only specific vetted models, or to tuning and other advanced capabilities. Org policies can be applied to all models in Model Garden as well as those imported from Hugging Face through Model Garden. These policies can be set on an organization, folder or project resource to enforce the constraint on that resource and any child resources.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: The ability to control access to the models made available through the Model Garden has been a top priority for many customers looking for governance and control tooling. Org Policies allows granular access control of models and enhances Google Cloud\u2019s enterprise readiness in an age of many models from many providers.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Learn more in \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/control-model-access\" style\u003d\"font-family:-apple-system,BlinkMacSystemFont,\u0026#39;Segoe UI\u0026#39;,Roboto,Oxygen,Ubuntu,Cantarell,\u0026#39;Open Sans\u0026#39;,\u0026#39;Helvetica Neue\u0026#39;,sans-serif\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e"]]],[null,["Build with the latest generative AI models for free",null,"Get started for free","http://console.cloud.google.com/freetrial?redirectPath\u003d/welcome",[null,"\u003cp\u003eExplore what powerful models like Gemini and Imagen can do for you with $300 in free credit for new customers on signup.\u003c/p\u003e"]]],[null,null,[null,[null,"\u003ch3\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003ePrevious Announcements\u003c/strong\u003e\u003c/h3\u003e"]]],[null,null,[null,[null,"\u003ch3\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eBest models from Google and the industry\u003c/strong\u003e\u003c/h3\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWe\u2019re committed to providing the best model for enterprises to use - Vertex AI Model Garden provides access to 150+ models from Google, Partners and the open community so customers can select the model for the right price, performance, and latency considerations.\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eNo matter what foundation model you use, it comes with enterprise ready tooling and integration to our end to end platform.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eGemini 1.5 Flash is GA\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is:\u003c/span\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003e \u003c/strong\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGemini 1.5 Flash combines low latency, highly competitive pricing, and our 1 million-token context window.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: Gemini 1.5 Flash is an excellent option for a wide variety of use cases at scale, from retail chat agents, to document processing, to research agents that can synthesize entire repositories.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: \u003c/span\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eClick \u003c/span\u003e\u003ca href\u003d\"https://console.cloud.google.com/vertex-ai/generative/multimodal/create/text\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003ehere\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to get started now with Gemini 1.5 Flash on Vertex AI.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eLower pricing for Gemini 1.5 Flash\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: We've updated Gemini 1.5 Flash to reduce the input costs by up to ~85% and output costs by up to ~80%, starting August 12th, 2024.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: This is a big price drop on Gemini Flash, a world-class model with a 1 million context window and multi-modal inputs. Plus, coupled with capabilities like context caching you can significantly reduce the cost and latency of your long context queries. Using Batch API instead of standard requests can further optimize costs for latency insensitive tasks.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: View \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/pricing\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003epricing\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to learn more and try \u003c/span\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eout \u003c/span\u003e\u003ca href\u003d\"https://console.cloud.google.com/vertex-ai/generative/multimodal/create/text\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eGemini 1.5 Flash\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e today.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eGemini 1.5 Pro, GA with 2-million -token context capabilities\u00a0\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Now available with an industry-leading context window of up to 2 million tokens, Gemini 1.5 Pro is equipped to unlock unique multimodal use cases that no other model can handle.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: Processing just six minutes of video requires over 100,000 tokens and large code bases can exceed 1 million tokens \u2014 so whether the use case involves finding bugs across countless lines of code, locating the right information across libraries of research, or analyzing hours of audio or video, Gemini 1.5 Pro\u2019s expanded context window is helping organizations break new ground.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: \u003c/span\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eClick \u003c/span\u003e\u003ca href\u003d\"https://console.cloud.google.com/vertex-ai/generative/multimodal/create/text?model\u003dgemini-1.5-pro-001\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003ehere\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to get started now\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eMore Languages for Gemini\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: We're enabling Gemini 1.5 Flash and Gemini 1.5 Pro to understand and respond in 100+ languages.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: We\u2019re making it easier for our global community to prompt and receive responses in their native languages.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: View \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#languages-gemini\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to learn more.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eGemma 2\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: The next generation in Google\u2019s family of open models built to give developers and researchers the ability to share and commercialize their innovations, using the same technologies used to create Gemini.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: Available in both 9-billion (9B) and 27-billion (27B) parameter sizes, Gemma 2 is much more powerful and efficient than the first generation, with significant safety advancements built in.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Access Gemma 2 on Vertex AI \u003c/span\u003e\u003ca href\u003d\"https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003ehere\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eMeta\u2019s Llama 3.1\u00a0\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/blog/products/ai-machine-learning/llama-3-1-on-vertex-ai?e\u003d48754805\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eLlama 3.1 models\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e are now available on Vertex AI as a pay as you go API, this includes 405B, 70B and 8B (coming in early September).\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: 405B is the largest openly available foundation model to date. 8B and 70B are also new versions that excel at understanding language nuances, grasping context, and performing complex tasks such as translation and dialogue generation. You can access the new models in just a few clicks using Model-as-a-Service, without any setup or infrastructure hassles.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: To access Llama 3.1, visit \u003c/span\u003e\u003ca href\u003d\"https://pantheon.corp.google.com/vertex-ai/publishers/meta/model-garden/llama3-405b-instruct-maas\" rel\u003d\"noopener\" target\u003d\"_blank\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eModel Garden\u003c/span\u003e\u003c/a\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eMistral AI\u2019s latest models\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: We added Mistral Large 2, Nemo and Codestral (Google Cloud is the first hyperscaler to introduce Codestral).\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: Mistral Large 2 is their flagship model which offers their best performance and versatility to date and Mistral Nemo is a 12B model that delivers exceptional performance at a fraction of the cost. Codestral is Mistral AI\u2019s first open-weight generative AI model explicitly designed for code generation tasks. You can access the new models in just a few clicks using Model-as-a-Service, without any setup or infrastructure hassles.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: \u003c/span\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eTo access the Mistral AI models, visit Model Garden (\u003c/span\u003e\u003ca href\u003d\"https://console.cloud.google.com/vertex-ai/publishers/mistralai/model-garden/codestral\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eCodestral\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e, \u003c/span\u003e\u003ca href\u003d\"https://console.cloud.google.com/vertex-ai/publishers/mistralai/model-garden/mistral-large\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eLarge 2\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e, \u003c/span\u003e\u003ca href\u003d\"https://console.cloud.google.com/vertex-ai/publishers/mistralai/model-garden/mistral-nemo\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eNemo\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e) or check out the \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/mistral\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eJamba 1.5 Model Family from AI21 Labs\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Jamba 1.5 Model Family\u00a0 \u2014 AI21 Labs\u2019 new family of open models \u2014 is in public preview on Vertex AI Model Garden, including:\u00a0\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:circle;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eJamba 1.5 Mini: AI21\u2019s most efficient and lightweight model, engineered for speed and efficiency in tasks including customer support, document summarization, and text generation.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:circle;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eJamba 1.5 Large: AI21\u2019s most advanced and largest model that can handle advanced reasoning tasks \u2014 such as financial analysis \u2014 with exceptional speed and efficiency.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: AI21\u2019s new models join over 150 models already available on Vertex AI Model Garden, further expanding your choice and flexibility to choose the best models for your needs and budget, and to keep pace with the continued rapid pace of innovation.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: \u003c/span\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eSelect the \u003c/span\u003e\u003ca href\u003d\"https://console.cloud.google.com/vertex-ai/publishers/ai21/model-garden/jamba-1.5-mini\"\u003e\u003cstrong style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eJamba 1.5 Mini\u003c/strong\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e or \u003c/span\u003e\u003ca href\u003d\"https://console.cloud.google.com/vertex-ai/publishers/ai21/model-garden/jamba-1.5-large\"\u003e\u003cstrong style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eJamba 1.5 Large\u003c/strong\u003e\u003c/a\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003e \u003c/strong\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003emodel tile in Vertex AI Model Garden.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eAnthropic\u2019s Claude 3.5 Sonnet\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: We recently added Anthropic\u2019s newly released model, Claude 3.5 Sonnet, to Vertex AI. This expands the set of Anthropic models we offer, including Claude 3 Opus, Claude 3 Sonnet, Claude 3 Haiku. You can access the new models in just a few clicks using Model-as-a-Service, without any setup or infrastructure hassles.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: We're committed to empowering customer choice and innovation through our curated collection of first-party, open, and third-party models available on Vertex AI. \u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: \u003c/span\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eBegin experimenting with or deploying in production \u003c/span\u003e\u003ca href\u003d\"https://console.cloud.google.com/vertex-ai/publishers/anthropic/model-garden/claude-3-5-sonnet\" style\u003d\"font-family:-apple-system,BlinkMacSystemFont,\u0026#39;Segoe UI\u0026#39;,Roboto,Oxygen,Ubuntu,Cantarell,\u0026#39;Open Sans\u0026#39;,\u0026#39;Helvetica Neue\u0026#39;,sans-serif\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eClaude 3.5 Sonnet on Vertex AI\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e"]]],[null,null,[null,[null,"\u003ch3\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eEnd-to-end model building platform with choice at every level\u003c/strong\u003e\u003c/h3\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eVertex AI Model Builder enables you to build or customize your own models, with all the capabilities you need to move from prototype to production.\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eLower cost with context caching for both Gemini 1.5 Pro and Flash\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Context caching is a technique that involves storing previous parts of a conversation or interaction (the \"context\") in memory so that the model can refer back to it when generating new responses\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: As context length increases, it can be expensive and slow to get responses for long-context applications, making it difficult to deploy to production. Vertex AI context caching helps customers significantly reduce input costs, by 75 percent, leveraging cached data of frequently-used context. Today, Google is the only provider to offer a context caching API.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Learn more in \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/context-cache/context-cache-overview\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003e.\u003c/strong\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eNew model monitoring capabilities\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: The new Vertex AI Model Monitoring includes\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:circle;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eSupport for models hosted outside of Vertex AI (e.g. GKE, Cloud Run, even multi-cloud \u0026amp; hybrid-cloud)\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:circle;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eUnified monitoring job management for both online and batch prediction\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:circle;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eSimplified configuration and metrics visualization attached to the model, not the endpoint\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: Vertex AI\u2019s new model monitoring features provide a more flexible, extensible, and consistent monitoring solution for models deployed on any serving infrastructure (even outside of Vertex AI, e.g. Google Kubernetes Engine, Cloud Run, Google Compute Engine and more).\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Learn more in this \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/blog/products/ai-machine-learning/get-to-know-vertex-ai-model-monitoring\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eblog\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eRay on Vertex AI is GA\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Ray provides a comprehensive and easy-to-use Python distributed framework. With Ray, you configure a scalable cluster of computational resources and utilize a collection of domain-specific libraries to efficiently distribute common AI/ML tasks like training, serving, and tuning.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: This integration empowers AI developers to effortlessly scale their AI workloads on Vertex AI's versatile infrastructure, which unlocks the full potential of machine learning, data processing, and distributed computing.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Ready the \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/blog/products/ai-machine-learning/ray-on-vertex-ai\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eblog\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to learn more.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003ePrompt Management\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Vertex AI Prompt Management, now in preview, provides a library of prompts for use among teams, including versioning, the option to restore old prompts, and AI-generated suggestions to improve prompt performance.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: This feature makes it easier for organizations to get the best performance from gen AI models at scale, and to iterate more quickly from experimentation to production. Customers can compare prompt iterations side by side to assess how small changes impact outputs, and the service offers features like notes and tagging to boost collaboration.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Visit \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/start/quickstarts/quickstart#compare_prompt_output_by_model\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to learn more.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eGen AI Evaluation Services\u00a0\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: We now support Gen AI Evaluation in GA to help users evaluate any generative model or application. While leaderboards and reports offer insights into overall model performance, they don't reveal how a model handles your specific needs. The Gen AI Evaluation Service helps you define your own evaluation criteria, ensuring a clear understanding of how well generative AI models and applications align with your unique use case. Users can define their own evaluation metrics and also access our templates for metrics with various criteria (e.g. text quality, instruction following, fluency).\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003eWhy it matters: Evaluation is important at every step of your gen AI development process including model selection, prompt engineering, and model customization. Evaluating gen AI is integrated within Vertex AI to help you launch and reuse evaluations as needed.\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Learn more in \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/models/evaluation-overview\" style\u003d\"font-family:-apple-system,BlinkMacSystemFont,\u0026#39;Segoe UI\u0026#39;,Roboto,Oxygen,Ubuntu,Cantarell,\u0026#39;Open Sans\u0026#39;,\u0026#39;Helvetica Neue\u0026#39;,sans-serif\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e"]]],[null,null,[null,[null,"\u003ch3\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eDevelop and deploy agents faster, grounded in your enterprise truth\u003c/strong\u003e\u003c/h3\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eVertex AI Agent Builder allows you to easily and quickly build and customize AI Agents - for any skill level. A core component of the Vertex AI Agent Builder is Vertex AI Search, enabling you to ground the models in your data or the web.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eGrounding at Vertex\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eYou have many options for Grounding and RAG at Vertex. These capabilities address some of the most significant hurdles limiting the adoption of generative AI in the enterprise: the fact that models do not know information outside their training data, and the tendency of foundation models to \u201challucinate,\u201d or generate convincing yet factually inaccurate information. Retrieval Augmented Generation (\u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/use-cases/retrieval-augmented-generation?e\u003d48754805\u0026amp;hl\u003den\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eRAG\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e), a technique developed to mitigate these challenges, first \u201cretrieves\u201d facts about a question, then provides those facts to the model before it \u201cgenerates\u201d an answer \u2013 this is what we mean by \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/grounding/overview?hl\u003den\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003egrounding\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e. Getting relevant facts quickly to augment a model's knowledge is ultimately a search problem.\u00a0\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eRead more at \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/blog/products/ai-machine-learning/rag-and-grounding-on-vertex-ai?e\u003d48754805\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003ethis blog post\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e.\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eGrounding with Google Search is GA\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: When customers select Grounding with Google Search for their Gemini model, Gemini will use Google Search, and generate an output that is grounded with the relevant internet search results. Grounding with Google Search also offers dynamic retrieval, a new capability to help customers balance quality with cost efficiency by intelligently selecting when to use Google Search results and when to use the model\u2019s training data.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: Grounding with Google Search is simple to use and makes the world\u2019s knowledge available to Gemini.\u00a0 Dynamic retrieval will save you money and will save your users time, only grounding when needed.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Read \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/ground-gemini\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to learn more about how to get started.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eGrounding with third-party datasets\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Vertex AI will offer a new service that lets customers ground their models and AI agents with specialized third-party data. We are working with providers like Moody's, MSCI, Thomson Reuters and Zoominfo to enable access to their datasets.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: These capabilities will help customers build AI agents and applications that offer more accurate and helpful responses.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Coming soon, \u003c/span\u003e\u003ca href\u003d\"https://inthecloud.withgoogle.com/global-gen-ai-contact-sales/cs-bsm.html\" rel\u003d\"noopener\" target\u003d\"_blank\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003econtact sales\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to learn more.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eGrounding with high-fidelity mode\u00a0\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: High-fidelity mode is powered by a version of Gemini 1.5 Flash that\u2019s been fine-tuned to only use customer-provided content to generate answers and ensures high levels of factuality in response.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: In data-intensive industries like financial services, healthcare, and insurance, generative AI use cases often require the generated response to be sourced from only the provided context, not the model\u2019s world knowledge. Grounding with high-fidelity, announced in experimental preview, is purpose-built to support such grounding use cases, including summarization across multiple documents, data extraction against a set corpus of financial data, or processing across a predefined set of documents.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: \u003c/span\u003e\u003ca href\u003d\"https://inthecloud.withgoogle.com/global-gen-ai-contact-sales/cs-bsm.html\" rel\u003d\"noopener\" target\u003d\"_blank\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eContact sales\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to learn more.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eExpanding Vector Search to support hybrid search\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Vector Search, the ultra high performance vector database powering Vertex AI Search, DIY RAG, and other embedding use cases at global scale, now offers hybrid search in Public Preview.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: Embeddings are numerical representations that capture semantic relationships across complex data (text, images, etc.). Embeddings power multiple use cases, including recommendation systems, ad serving, and semantic search for RAG. Hybrid search combines vector-based and keyword-based search techniques to ensure the most relevant and accurate responses for users.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Visit \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/docs/vector-search/overview\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to learn more about Vector Search.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eLangChain on Vertex\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: An agent development SDK and container runtime for LangChain. With LangChain on Vertex AI you can select the model you want to work with, define tools to access external APIs, structure the interface between the user and the system components in an orchestration framework, and deploy the framework to a managed runtime.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: LangChain on Vertex AI simplifies and speeds up deployment while being secure, private and scalable.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Visit \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/reasoning-engine/overview\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to learn more.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eVertex AI extensions, function calling and \u200b\u200bdata connectors\u00a0\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is:\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:circle;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eVertex AI extensions are pre-built reusable modules to connect a foundation model to a specific API or tool. For example, our new code interpreter extension enables models to execute tasks that entail running Python code, such as data analysis, data visualization, and mathematical operations.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:circle;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eVertex AI function calling enables a user to describe a set of functions or APIs and have Gemini models intelligently select, for a given query, the right API or function to call, along with the appropriate API parameters.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:circle;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eVertex AI data connectors help ingest data from enterprise and third-party applications like ServiceNow, Hadoop, and Salesforce, connecting generative applications to commonly-used enterprise systems.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: With these capabilities, Vertex AI Agent Builder makes it easy to augment grounding outputs and take action on your user\u2019s behalf.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Visit documentation to learn more about Vertex AI \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/extensions/overview\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eextensions\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e, \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/function-calling\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003efunction calling\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e and \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/integration-connectors/docs/connectors/gsc_vertex_ai/configure\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003e\u200b\u200bdata connectors\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eFirebase Genkit\u00a0\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Genkit is an open-source TypeScript/JavaScript and Go framework designed by Firebase to simplify the development, deployment, and monitoring of production-ready AI applications.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: With the Vertex AI plugin for Genkit, developers can now take advantage of Google models like Gemini and Imagen 2, as well as text embeddings. Additionally Vertex Eval Service is baked into the Genkit local development experience along with OpenTelemetry tracing.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Learn more in \u003c/span\u003e\u003ca href\u003d\"https://firebase.google.com/docs/genkit\" rel\u003d\"noopener\" target\u003d\"_blank\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eLlamaIndex on Vertex AI\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: LlamaIndex on Vertex AI simplifies building your own search engine for retrieval-augmented generation (RAG), from data ingestion and transformation to embedding, indexing, retrieval, and generation.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: Vertex AI customers can leverage Google\u2019s models and AI-optimized infrastructure alongside LlamaIndex\u2019s simple, flexible, open-source data framework, to connect custom data sources to generative models. \u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Visit \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/llamaindex-on-vertexai\" style\u003d\"font-family:-apple-system,BlinkMacSystemFont,\u0026#39;Segoe UI\u0026#39;,Roboto,Oxygen,Ubuntu,Cantarell,\u0026#39;Open Sans\u0026#39;,\u0026#39;Helvetica Neue\u0026#39;,sans-serif\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to learn more.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e"]]],[null,null,[null,[null,"\u003ch3\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eBuilt on a foundation of scale \u0026amp; enterprise readiness\u003c/strong\u003e\u003c/h3\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eThe revolutionary nature of generative AI requires a platform that offers privacy, security, control, and compliance capabilities organizations can rely on. Google Cloud is committed to helping our customers leverage the full potential of generative AI with privacy, security, and compliance capabilities. Our goal is to build trust by protecting systems, enabling transparency, and offering flexible, always-available infrastructure, all while grounding efforts in our \u003c/span\u003e\u003ca href\u003d\"https://ai.google/responsibility/principles/\" rel\u003d\"noopener\" target\u003d\"_blank\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eAI principles\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e.\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eDynamic Shared Quota\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: With Dynamic Shared Quota, we offer increasing the quota limits for a model (online serving) to the maximum allowed per region. This way we limit the number of queries per second (QPS) that customers can run by the shared capacity of all the queries running on a Servo station (multi-region), instead of limiting a customer\u2019s QPS by a quota. Dynamic Shared Quota is only applicable to Pay-as-you-go Online Serving. For customers that require a consistent or more predictable service level, including SLAs, we offer Provision Throughput.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: By dynamically distributing on-demand capacity among all queries being processed for Pay-as-you-go customers, Google Cloud has eliminated the need to submit quota increase requests (QIRs). Customers can still set a self-imposed quota called a consumer quota override to control cost and prevent budget overruns.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Learn more in \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/quotas#dynamic-shared-quota\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003edocumentation\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eProvisioned Throughput is GA\u00a0\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: Provisioned throughput lets customers responsibly scale their usage of Google\u2019s first-party models, like 1.5 Flash, providing assurances for both capacity and price.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: This Vertex AI feature brings predictability and reliability to customer production workloads, giving them the assurance required to scale gen AI workloads aggressively. \u003c/span\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e\u00a0We have also made it easier than ever for customers to set up PT via a Self Service flow. Customers can now \u003c/span\u003e\u003ca href\u003d\"http://console.cloud.google.com/vertex-ai/provisioned-throughput\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eestimate their needs and purchase\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e Provisioned Throughput for Google\u2019s 1P foundation models via the console, bringing the E2E experience down from weeks to minutes for pre-approved orders subject to available capacity and removing the need for manual order forms.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Follow \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/provisioned-throughput#place-an-order\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003ethese steps\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e to purchase a Provisioned Throughput subscription.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cstrong style\u003d\"vertical-align:baseline\"\u003eData residency for data stored at-rest guarantees in more countries\u003c/strong\u003e\u003c/p\u003e\n\u003cul\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhat it is: We have data residency for data stored at-rest guarantees in 23 countries (13 of which were added in 2024), with additional guarantees around limiting related ML processing to the US and EU. We are also working on expanding our ML processing commitments to eight more countries, starting with four countries in 2024.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eWhy it matters: Customers, especially those from regulated industries, demand control over where their data is stored and processed when using generative AI capabilities.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003cli style\u003d\"list-style-type:disc;vertical-align:baseline\"\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eGet started: Learn more \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/generative-ai/docs/learn/locations\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003ehere\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e.\u003c/span\u003e\u003c/p\u003e\n\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eTo keep up with all of the latest releases, don\u2019t forget to check our \u003c/span\u003e\u003ca href\u003d\"https://cloud.google.com/vertex-ai/docs/release-notes\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003eVertex AI release notes\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e.\u00a0\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eAll of these enhancements are a direct response to what you, our customers, have been asking for. We believe an enterprise AI platform is key to success in production and our goal is to not just build the best platform, but to provide an AI ecosystem that makes enterprise-scale AI accessible.\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003eTo learn about how Vertex AI can help you, \u003c/span\u003e\u003ca href\u003d\"https://inthecloud.withgoogle.com/global-gen-ai-contact-sales/cs-bsm.html?utm_source\u003dcgc-blog\u0026amp;utm_medium\u003dblog\u0026amp;utm_campaign\u003dFY23-Q3-global-ENDM228-website-sm-gen-ai-contact-us-lp\u0026amp;utm_content\u003dvertex-ai-evergreen-announcements\u0026amp;utm_term\u003d-\" rel\u003d\"noopener\" target\u003d\"_blank\"\u003e\u003cspan style\u003d\"text-decoration:underline;vertical-align:baseline\"\u003econtact us\u003c/span\u003e\u003c/a\u003e\u003cspan style\u003d\"vertical-align:baseline\"\u003e for a free consultation.\u003c/span\u003e\u003c/p\u003e"]]]],[["Developers \u0026 Practitioners","Boost your Continuous Delivery pipeline with Generative AI","Learn how to use Gemini models in Vertex AI to automate code reviews, create release notes, and enhance your software delivery pipeline.",["https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg","https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-400x400.jpg 324w, https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg 648w"," 324px, 648px","https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg"],null,7,null,"https://cloud.google.com/blog/topics/developers-practitioners/boost-your-continuous-delivery-pipeline-with-generative-ai",null,1,[["Giovanni Galloro","EMEA Solutions Lead, Application Modernization"],["Daniel Strebel","EMEA Solutions Lead, Application Modernization"]],null,"55631"],["Developers \u0026 Practitioners","Build an AI agent for trip planning with Gemini 1.5 Pro: A step-by-step guide","Check out this step-by-step guide to create an AI agent for trip planning with Gemini 1.5 Pro.",["https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg","https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-400x400.jpg 324w, https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg 648w"," 324px, 648px","https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg"],null,5,null,"https://cloud.google.com/blog/topics/developers-practitioners/learn-how-to-create-an-ai-agent-for-trip-planning-with-gemini-1-5-pro",null,1,[["Kelci Mensah","Cloud Architect, Google"],["Dagmawe Legesse","Cloud Engineer"]],null,"55632"],["Developers \u0026 Practitioners","Create a self-escalating chatbot in Conversational Agents using Webhook and Generators","Learn how to create a self-escalating chatbot using Google Cloud's generative AI solutions such as Vertex AI and Conversational Agents (Dialogflow CX).",["https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg","https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-400x400.jpg 324w, https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg 648w"," 324px, 648px","https://storage.googleapis.com/gweb-cloudblog-publish/images/11_-_Developers__Practitioners_a4Y5EGr.max-700x700.jpg"],null,9,null,"https://cloud.google.com/blog/topics/developers-practitioners/create-a-self-escalating-chatbot-in-conversational-agents",null,1,[["Aniket Agrawal","AI Cloud Engineer"]],null,"55633"],["AI \u0026 Machine Learning","How Commerzbank is transforming financial advisory workflows with gen AI","Commerzbank has automated its financial advisory workflows using an advanced semi-agentic, multi-step gen AI process on Vertex AI.",["https://storage.googleapis.com/gweb-cloudblog-publish/original_images/Commerzbank-v3.gif","https://storage.googleapis.com/gweb-cloudblog-publish/original_images/Commerzbank-v3.gif 324w, https://storage.googleapis.com/gweb-cloudblog-publish/original_images/Commerzbank-v3.gif 648w"," 324px, 648px","https://storage.googleapis.com/gweb-cloudblog-publish/original_images/Commerzbank-v3.gif"],null,5,null,"https://cloud.google.com/blog/products/ai-machine-learning/how-commerzbank-is-transforming-financial-advisory-workflows-with-gen-ai",null,1,[["Tolga Bast\u00fcrk","Product Owner, Commerzbank"],["Anant Nawalgaria","Sr. Staff ML Engineer, Google"]],null,"55621"]],null,"AI \u0026 Machine Learning",["Google Cloud Summit Series","Discover the latest in AI, Security, Workspace, App Dev, \u0026 more.","Register","https://cloudonair.withgoogle.com/summit_series_24?utm_source\u003dcgc-blog\u0026utm_medium\u003dblog\u0026utm_campaign\u003dsummit-series-2024\u0026utm_content\u003dsummit-series-left-hand-rail-cta\u0026utm_term\u003d-"],[["AI \u0026 Machine Learning","https://cloud.google.com/blog/products/ai-machine-learning","ai-machine-learning"],["Google Cloud","https://cloud.google.com/blog/products/gcp","gcp"]],null,null,24], sideChannel: {}});</script><script id="wiz_jd" nonce="5dAgjnjZnWn0wEH1uLTSYA">if (window['_wjdc']) {const wjd = {}; window['_wjdc'](wjd); delete window['_wjdc'];}</script><script aria-hidden="true" id="WIZ-footer" nonce="5dAgjnjZnWn0wEH1uLTSYA">window.wiz_progress&&window.wiz_progress(); window.stopScanForCss&&window.stopScanForCss(); ccTick('bl');</script></body></html><footer id="ZCHFDb"><footer class="nRhiJb-RWrDld nRhiJb-yePe5c QJnbF" jscontroller="NsSboe" track-metadata-module="footer"><h3 class="nRhiJb-VqCwd-L6cTce">Footer Links</h3><section class="nRhiJb-haF9Wb r2W5Od"><section class="nRhiJb-DX2B6"><div class="nRhiJb-j5y3u"><h4 class="nRhiJb-BkAck nRhiJb-BkAck-OWXEXe-TzA9Ye">Follow us</h4><ul class="nRhiJb-Qijihe c3Uqdd" role="list"><li class="nRhiJb-KKXgde"><a class="nRhiJb-ARYxNe" href="https://www.x.com/googlecloud" target="_blank" rel="noopener" track-name="x"track-type="social link"track-metadata-position="footer"track-metadata-eventdetail="www.x.com/googlecloud"track-metadata-module="footer"track-metadata-module_headline="follow us"><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-xgZe3c nRhiJb-Bz112c-OWXEXe-DX2B6" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="M13.9,10.5L21.1,2h-1.7l-6.3,7.4L8,2H2.2l7.6,11.1L2.2,22h1.7l6.7-7.8L16,22h5.8L13.9,10.5L13.9,10.5z M11.5,13.2l-0.8-1.1 L4.6,3.3h2.7l5,7.1l0.8,1.1l6.5,9.2h-2.7L11.5,13.2L11.5,13.2z"></path></svg></a></li><li class="nRhiJb-KKXgde"><a class="nRhiJb-ARYxNe" href="https://www.youtube.com/googlecloud" target="_blank" rel="noopener" track-name="youtube"track-type="social link"track-metadata-position="footer"track-metadata-eventdetail="www.youtube.com/googlecloud"track-metadata-module="footer"track-metadata-module_headline="follow us"><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-xgZe3c nRhiJb-Bz112c-OWXEXe-DX2B6" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="M23.74 7.1s-.23-1.65-.95-2.37c-.91-.96-1.93-.96-2.4-1.02C17.04 3.47 12 3.5 12 3.5s-5.02-.03-8.37.21c-.46.06-1.48.06-2.39 1.02C.52 5.45.28 7.1.28 7.1S.04 9.05 0 10.98V13c.04 1.94.28 3.87.28 3.87s.24 1.65.96 2.38c.91.95 2.1.92 2.64 1.02 1.88.18 7.91.22 8.12.22 0 0 5.05.01 8.4-.23.46-.06 1.48-.06 2.39-1.02.72-.72.96-2.37.96-2.37s.24-1.94.25-3.87v-2.02c-.02-1.93-.26-3.88-.26-3.88zM9.57 15.5V8.49L16 12.13 9.57 15.5z"></path></svg></a></li><li class="nRhiJb-KKXgde"><a class="nRhiJb-ARYxNe" href="https://www.linkedin.com/showcase/google-cloud" target="_blank" rel="noopener" track-name="linkedin"track-type="social link"track-metadata-position="footer"track-metadata-eventdetail="www.linkedin.com/showcase/google-cloud"track-metadata-module="footer"track-metadata-module_headline="follow us"><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-xgZe3c nRhiJb-Bz112c-OWXEXe-DX2B6" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="M20 2H4c-1.1 0-1.99.9-1.99 2L2 20c0 1.1.9 2 2 2h16c1.1 0 2-.9 2-2V4c0-1.1-.9-2-2-2zM8 19H5v-9h3v9zM6.5 8.31c-1 0-1.81-.81-1.81-1.81S5.5 4.69 6.5 4.69s1.81.81 1.81 1.81S7.5 8.31 6.5 8.31zM19 19h-3v-5.3c0-.83-.67-1.5-1.5-1.5s-1.5.67-1.5 1.5V19h-3v-9h3v1.2c.52-.84 1.59-1.4 2.5-1.4 1.93 0 3.5 1.57 3.5 3.5V19z"></path></svg></a></li><li class="nRhiJb-KKXgde"><a class="nRhiJb-ARYxNe" href="https://www.instagram.com/googlecloud/" target="_blank" rel="noopener" track-name="instagram"track-type="social link"track-metadata-position="footer"track-metadata-eventdetail="www.instagram.com/googlecloud/"track-metadata-module="footer"track-metadata-module_headline="follow us"><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-xgZe3c nRhiJb-Bz112c-OWXEXe-DX2B6" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="M12,0 C15.3,0 15.7,0 17,0 C18.3,0.1 19.1,0.3 19.9,0.6 C20.7,0.9 21.3,1.3 22,2 C22.7,2.7 23.1,3.4 23.3,4.2 C23.6,5 23.8,5.8 23.9,7.1 C24,8.3 24,8.7 24,12 C24,15.3 24,15.7 23.9,16.9 C23.8,18.2 23.6,19 23.3,19.8 C23,20.6 22.6,21.2 21.9,21.9 C21.3,22.6 20.6,23 19.8,23.3 C19,23.6 18.2,23.8 16.9,23.9 C15.7,24 15.3,24 12,24 C8.7,24 8.3,24 7,24 C5.7,23.9 4.9,23.7 4.1,23.4 C3.3,23.1 2.7,22.7 2,22 C1.3,21.3 0.9,20.6 0.7,19.8 C0.4,19 0.2,18.2 0.1,16.9 C0,15.7 0,15.3 0,12 C0,8.7 0,8.3 0.1,7.1 C0.1,5.8 0.3,4.9 0.6,4.1 C0.9,3.4 1.3,2.7 2,2 C2.7,1.3 3.4,0.9 4.1,0.6 C4.9,0.3 5.8,0.1 7.1,0.1 C8.3,0 8.7,0 12,0 Z M12,2.2 C8.8,2.2 8.4,2.2 7.2,2.2 C6,2.3 5.3,2.5 4.9,2.6 C4.4,2.9 4,3.1 3.5,3.5 C3.1,3.9 2.8,4.3 2.6,4.9 C2.5,5.3 2.3,6 2.3,7.2 C2.2,8.4 2.2,8.8 2.2,12 C2.2,15.2 2.2,15.5 2.3,16.8 C2.3,17.9 2.5,18.6 2.7,19 C2.9,19.6 3.2,20 3.6,20.4 C4,20.8 4.4,21.1 5,21.3 C5.4,21.5 6,21.6 7.2,21.7 C8.4,21.8 8.8,21.8 12,21.8 C15.2,21.8 15.5,21.8 16.8,21.7 C17.9,21.7 18.6,21.5 19,21.3 C19.6,21.1 20,20.8 20.4,20.4 C20.8,20 21.1,19.6 21.3,19 C21.5,18.6 21.6,18 21.7,16.8 C21.8,15.6 21.8,15.2 21.8,12 C21.8,8.8 21.8,8.5 21.7,7.2 C21.7,6.1 21.5,5.4 21.3,5 C21.1,4.4 20.8,4 20.4,3.6 C20,3.2 19.6,2.9 19,2.7 C18.6,2.5 18,2.4 16.8,2.3 C15.6,2.2 15.2,2.2 12,2.2 Z M12,5.8 C15.4,5.8 18.2,8.6 18.2,12 C18.2,15.4 15.4,18.2 12,18.2 C8.6,18.2 5.8,15.4 5.8,12 C5.8,8.6 8.6,5.8 12,5.8 Z M12,16 C14.2,16 16,14.2 16,12 C16,9.8 14.2,8 12,8 C9.8,8 8,9.8 8,12 C8,14.2 9.8,16 12,16 Z M18.4,7 C17.6268014,7 17,6.37319865 17,5.6 C17,4.82680135 17.6268014,4.2 18.4,4.2 C19.1731986,4.2 19.8,4.82680135 19.8,5.6 C19.8,6.37319865 19.1731986,7 18.4,7 Z"></path></svg></a></li><li class="nRhiJb-KKXgde"><a class="nRhiJb-ARYxNe" href="https://www.facebook.com/googlecloud/" target="_blank" rel="noopener" track-name="facebook"track-type="social link"track-metadata-position="footer"track-metadata-eventdetail="www.facebook.com/googlecloud/"track-metadata-module="footer"track-metadata-module_headline="follow us"><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-xgZe3c nRhiJb-Bz112c-OWXEXe-DX2B6" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="M20 2H4c-1.1 0-1.99.9-1.99 2L2 20c0 1.1.9 2 2 2h16c1.1 0 2-.9 2-2V4c0-1.1-.9-2-2-2zm-1 2v3h-2c-.55 0-1 .45-1 1v2h3v3h-3v7h-3v-7h-2v-3h2V7.5C13 5.57 14.57 4 16.5 4H19z"></path></svg></a></li></ul></div></section></section><section class="nRhiJb-hlZHHf rtKYfe"><div class="nRhiJb-vQnuyc UXgbsb"><a class="ZOs9zc" href="https://cloud.google.com/" title="Google Cloud" track-name="google"track-type="footer link"track-metadata-position="footer"track-metadata-eventdetail="cloud.google.com/"track-metadata-module="footer"><svg class="nRhiJb-vQnuyc-RJLb9c" viewBox="0 0 64 64" role="presentation" aria-hidden="true" width="40" height="40"><path d="M40.37 20.29L42.3333 20.3267L47.67 14.99L47.93 12.73C43.69 8.95667 38.11 6.66 32 6.66C20.9367 6.66 11.6067 14.1833 8.84 24.3833C9.42334 23.98 10.6667 24.28 10.6667 24.28L21.3333 22.5267C21.3333 22.5267 21.8867 21.62 22.1567 21.6767C24.5967 19.0067 28.1067 17.3267 32 17.3267C35.1667 17.3267 38.08 18.44 40.37 20.29Z" fill="#ea4335"/><path d="M55.1667 24.3967C53.93 19.8233 51.37 15.79 47.9267 12.7267L40.3667 20.2867C43.3933 22.7333 45.3333 26.4733 45.3333 30.66V31.9933C49.01 31.9933 52 34.9833 52 38.66C52 42.3367 49.01 45.3267 45.3333 45.3267H32L30.6667 46.6667V54.6667L32 55.9933H45.3333C54.89 55.9933 62.6667 48.2167 62.6667 38.66C62.6667 32.75 59.6933 27.5267 55.1667 24.3967Z" fill="#4285f4"/><path d="M18.6667 55.9933H31.99V45.3267H18.6667C17.6867 45.3267 16.76 45.11 15.92 44.7267L14 45.3167L8.66 50.6567L8.19334 52.46C11.1033 54.6733 14.7333 55.9933 18.6667 55.9933Z" fill="#34a853"/><path d="M18.6667 21.3267C9.11 21.3267 1.33334 29.1033 1.33334 38.66C1.33334 44.2867 4.03 49.2967 8.2 52.4633L15.93 44.7333C13.6167 43.6867 12 41.36 12 38.66C12 34.9833 14.99 31.9933 18.6667 31.9933C21.3667 31.9933 23.6933 33.61 24.74 35.9233L32.47 28.1933C29.3033 24.0233 24.2933 21.3267 18.6667 21.3267Z" fill="#fbbc05"/></svg></a></div><ul class="nRhiJb-hlZHHf-PLDbbf nRhiJb-di8rgd-ZGNLv AXb5J" role="list"><li class="glue-footer__global-links-list-item"><a class="nRhiJb-Fx4vi " href="https://cloud.google.com/" track-name="google cloud"track-type="footer link"track-metadata-position="footer"track-metadata-eventdetail="cloud.google.com/"track-metadata-module="footer">Google Cloud</a></li><li class="glue-footer__global-links-list-item"><a class="nRhiJb-Fx4vi " href="https://cloud.google.com/products/" track-name="google cloud products"track-type="footer link"track-metadata-position="footer"track-metadata-eventdetail="cloud.google.com/products/"track-metadata-module="footer">Google Cloud Products</a></li><li class="glue-footer__global-links-list-item"><a class="nRhiJb-Fx4vi " href="https://myaccount.google.com/privacypolicy?hl=en-US" target="_blank" track-name="privacy"track-type="footer link"track-metadata-position="footer"track-metadata-eventdetail="myaccount.google.com/privacypolicy?hl=en-US"track-metadata-module="footer">Privacy</a></li><li class="glue-footer__global-links-list-item"><a class="nRhiJb-Fx4vi " href="https://myaccount.google.com/termsofservice?hl=en-US" target="_blank" track-name="terms"track-type="footer link"track-metadata-position="footer"track-metadata-eventdetail="myaccount.google.com/termsofservice?hl=en-US"track-metadata-module="footer">Terms</a></li><li aria-hidden="true" class="glue-footer__global-links-list-item"><a aria-hidden="true" role="button" tabindex="0" class="nRhiJb-Fx4vi glue-footer__link glue-cookie-notification-bar-control" href="#" target="_blank" track-name="cookies management controls"track-type="footer link"track-metadata-position="footer"track-metadata-eventdetail="#"track-metadata-module="footer">Cookies management controls</a></li></ul><ul class="nRhiJb-hlZHHf-PLDbbf nRhiJb-hlZHHf-PLDbbf-OWXEXe-hOedQd nRhiJb-di8rgd-ZGNLv qkxr1" role="list"><li class="glue-footer__global-links-list-item nRhiJb-hlZHHf-PLDbbf-rymPhb-ibnC6b-OWXEXe-hOedQd"><a class="nRhiJb-Fx4vi" href="https://support.google.com" target="_blank" track-name="help"track-type="footer link"track-metadata-position="footer"track-metadata-eventdetail="support.google.com"track-metadata-module="footer"><svg class="nRhiJb-Bz112c nRhiJb-Bz112c-OWXEXe-xgZe3c nRhiJb-Bz112c-OWXEXe-yePe5c-h9d3hd" viewBox="0 0 24 24" role="presentation" aria-hidden="true"><path d="M12 2C6.48 2 2 6.48 2 12s4.48 10 10 10 10-4.48 10-10S17.52 2 12 2zm1 17h-2v-2h2v2zm2.07-7.75l-.9.92C13.45 12.9 13 13.5 13 15h-2v-.5c0-1.1.45-2.1 1.17-2.83l1.24-1.26c.37-.36.59-.86.59-1.41 0-1.1-.9-2-2-2s-2 .9-2 2H8c0-2.21 1.79-4 4-4s4 1.79 4 4c0 .88-.36 1.68-.93 2.25z"></path></svg>Help</a></li><li class="glue-footer__global-links-list-item nRhiJb-hlZHHf-PLDbbf-rymPhb-ibnC6b-OWXEXe-hOedQd"><select jsaction="change:xU0iy" aria-label="Change language" class="nRhiJb-CL4aqd-j4gsHd"><option value="" selected disabled hidden>Language</option><option value="en" selected>‪English‬</option><option value="de">‪Deutsch‬</option><option value="fr">‪Français‬</option><option value="ko">‪한국어‬</option><option value="ja">‪日本語‬</option></select></li></ul></section></footer></footer>