{"id":1027041,"date":"2024-04-23T11:20:10","date_gmt":"2024-04-23T18:20:10","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=1027041"},"modified":"2024-11-15T13:25:12","modified_gmt":"2024-11-15T21:25:12","slug":"graphrag","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/graphrag\/","title":{"rendered":"Project GraphRAG"},"content":{"rendered":"<section class=\"mb-3 moray-highlight\">\n\t<div class=\"card-img-overlay mx-lg-0\">\n\t\t<div class=\"card-background  has-background- card-background--full-bleed\">\n\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"2633\" height=\"1836\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2024\/04\/graphrag-banner.png\" class=\"attachment-full size-full\" alt=\"Image of an entity network with color-coded communities\" style=\"\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2024\/04\/graphrag-banner.png 2633w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2024\/04\/graphrag-banner-300x209.png 300w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2024\/04\/graphrag-banner-1024x714.png 1024w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2024\/04\/graphrag-banner-768x536.png 768w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2024\/04\/graphrag-banner-1536x1071.png 1536w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2024\/04\/graphrag-banner-2048x1428.png 2048w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2024\/04\/graphrag-banner-240x167.png 240w\" sizes=\"(max-width: 2633px) 100vw, 2633px\" \/>\t\t<\/div>\n\t\t<!-- Foreground -->\n\t\t<div class=\"card-foreground d-flex mt-md-n5 my-lg-5 px-g px-lg-0\">\n\t\t\t<!-- Container -->\n\t\t\t<div class=\"container d-flex mt-md-n5 my-lg-5 \">\n\t\t\t\t<!-- Card wrapper -->\n\t\t\t\t<div class=\"w-100 w-lg-col-5\">\n\t\t\t\t\t<!-- Card -->\n\t\t\t\t\t<div class=\"card material-md-card py-5 px-md-5\">\n\t\t\t\t\t\t<div class=\"card-body \">\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n<h1 class=\"wp-block-heading\" id=\"project-graphrag\">Project GraphRAG<\/h1>\n\n\n\n<p>LLM-Derived Knowledge Graphs<\/p>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n<div class=\"wp-block-media-text has-video  has-vertical-margin-small  has-vertical-padding-none  is-stacked-on-mobile\" style=\"grid-template-columns:40% auto\" data-bi-an=\"media-text\"><figure class=\"wp-block-media-text__media video-wrapper\"><iframe class=\"media-text__video\" src=\"https:\/\/www.youtube-nocookie.com\/embed\/jCjyaQL-7mA?enablejsapi=1&rel=0\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe><\/figure><div class=\"wp-block-media-text__content\" data-bi-an=\"media-text\">\n<h2 class=\"wp-block-heading\" id=\"graphrag\">GraphRAG<\/h2>\n\n\n\n<p>GraphRAG (Graphs + Retrieval Augmented Generation) is a technique for richly understanding text datasets by combining text extraction, network analysis, and LLM prompting and summarization into a single end-to-end system.<\/p>\n\n\n\n<div class=\"wp-block-buttons is-layout-flex wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button is-style-fill\"><a data-bi-type=\"button\" class=\"wp-block-button__link wp-element-button\" href=\"https:\/\/www.microsoft.com\/en-us\/research\/publication\/from-local-to-global-a-graph-rag-approach-to-query-focused-summarization\/\">Read the pre-print<\/a><\/div>\n<\/div>\n<\/div><\/div>\n\n\n<div class=\"msr-cards__card msr-cards__card--default col\">\n\t<div class=\"card has-spectrum-border-top__hover material-card h-100 p-0\" data-mount=\"click-group\">\n\n\t\t\n\t\t<div class=\"card-body bg-white p-4 pt-3\">\n\t\t\t\t\t\t\n\t\t\t\t\t<\/div>\n\t<\/div>\n<\/div>\n\n\n\n<p><strong>Open Source<\/strong><\/p>\n\n\n\n<p>The GraphRAG library and complementary solution accelerator, an easy-to-use API experience hosted on Azure, <a href=\"https:\/\/www.microsoft.com\/en-us\/research\/blog\/graphrag-new-tool-for-complex-data-discovery-now-on-github\/\">are now both available on GitHub<\/a>!<\/p>\n\n\n\n<p><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/github.com\/Azure-Samples\/graphrag-accelerator\">GraphRAG Solution Accelerator<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/p>\n\n\n\n<p><a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/github.com\/microsoft\/graphrag\">GraphRAG Library<span class=\"sr-only\"> (opens in new tab)<\/span><\/a><\/p>\n\n\n\n<p><\/p>\n\n\n\n<p><\/p>\n\n\n","protected":false},"excerpt":{"rendered":"<p>LLM-Derived Knowledge Graphs GraphRAG (Graphs + Retrieval Augmented Generation) is a technique for richly understanding text datasets by combining text extraction, network analysis, and LLM prompting and summarization into a single end-to-end system. Open Source The GraphRAG library and complementary solution accelerator, an easy-to-use API experience hosted on Azure, are now both available on GitHub! [&hellip;]<\/p>\n","protected":false},"featured_media":1027164,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13556,13555],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1027041","msr-project","type-msr-project","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-research-area-search-information-retrieval","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[1029069],"related-downloads":[1057299],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Jonathan Larson","user_id":32385,"people_section":"Related people","alias":"jolarso"},{"type":"user_nicename","display_name":"Steven Truitt","user_id":43143,"people_section":"Related people","alias":"steventruitt"},{"type":"user_nicename","display_name":"Darren Edge","user_id":31509,"people_section":"Related people","alias":"daedge"},{"type":"user_nicename","display_name":"Ha Trinh","user_id":43245,"people_section":"Related people","alias":"trinhha"},{"type":"guest","display_name":"Newman Cheng","user_id":1027767,"people_section":"Related people","alias":""},{"type":"user_nicename","display_name":"Alex Chao","user_id":43254,"people_section":"Related people","alias":"achao"},{"type":"user_nicename","display_name":"Apurva Mody","user_id":43257,"people_section":"Related people","alias":"moapurva"},{"type":"user_nicename","display_name":"Joshua Bradley","user_id":43272,"people_section":"Related people","alias":"joshbradley"},{"type":"user_nicename","display_name":"Nathan Evans","user_id":36539,"people_section":"Related people","alias":"naevans"},{"type":"user_nicename","display_name":"Alonso Guevara Fern&aacute;ndez","user_id":42522,"people_section":"Related people","alias":"alonsog"},{"type":"guest","display_name":"Andres Morales Esquivel","user_id":1028154,"people_section":"Related people","alias":""},{"type":"user_nicename","display_name":"Chris Trevino","user_id":43260,"people_section":"Related people","alias":"chtrevin"},{"type":"user_nicename","display_name":"Dayenne Souza","user_id":42084,"people_section":"Related people","alias":"ddesouza"},{"type":"user_nicename","display_name":"Gaudy Blanco Meneses","user_id":43278,"people_section":"Related people","alias":"gaudyb"},{"type":"guest","display_name":"Rodrigo Racanicci","user_id":1028880,"people_section":"Related people","alias":""},{"type":"user_nicename","display_name":"Sarah Smith","user_id":42579,"people_section":"Related people","alias":"smithsarah"},{"type":"user_nicename","display_name":"Ben Cutler","user_id":31188,"people_section":"Related people","alias":"bcutler"},{"type":"user_nicename","display_name":"Amber Hoak","user_id":37992,"people_section":"Related people","alias":"amhoak"},{"type":"user_nicename","display_name":"David Tittsworth","user_id":38064,"people_section":"Related people","alias":"datittsw"},{"type":"user_nicename","display_name":"Kate Lytvynets","user_id":38073,"people_section":"Related people","alias":"kalytv"},{"type":"guest","display_name":"Katy Smith","user_id":1028889,"people_section":"Related people","alias":""},{"type":"guest","display_name":"Richard Ortega","user_id":1028166,"people_section":"Related people","alias":""},{"type":"guest","display_name":"Promise Tachtevrenidou","user_id":1029021,"people_section":"Related people","alias":""},{"type":"guest","display_name":"Alina Pana","user_id":1029012,"people_section":"Related people","alias":""},{"type":"guest","display_name":"Basil Cherian","user_id":1028700,"people_section":"Related people","alias":""},{"type":"guest","display_name":"Jyoti Gawade","user_id":1032747,"people_section":"Related people","alias":""}],"msr_research_lab":[],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1027041"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":29,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1027041\/revisions"}],"predecessor-version":[{"id":1104690,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1027041\/revisions\/1104690"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/1027164"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1027041"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1027041"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1027041"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1027041"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1027041"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}