{"id":7825,"date":"2024-05-14T11:18:00","date_gmt":"2024-05-14T09:18:00","guid":{"rendered":"http:\/\/nextbrain.ai\/?p=7825"},"modified":"2024-05-14T11:22:02","modified_gmt":"2024-05-14T09:22:02","slug":"rag-explained-in-simple-words","status":"publish","type":"post","link":"https:\/\/nextbrain.ai\/fr\/blog\/rag-explained-in-simple-words","title":{"rendered":"RAG expliqu\u00e9 en mots simples"},"content":{"rendered":"
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

La g\u00e9n\u00e9ration augment\u00e9e par r\u00e9cup\u00e9ration (RAG) est la m\u00e9thode d'affinage de la sortie d'un mod\u00e8le de langage substantiel en se r\u00e9f\u00e9rant \u00e0 une base de connaissances cr\u00e9dible au-del\u00e0 de ses sources de donn\u00e9es d'entra\u00eenement avant de g\u00e9n\u00e9rer une r\u00e9ponse.<\/p>

Dans cet article, nous expliquerons comment cela fonctionne r\u00e9ellement en termes simples.<\/p>

\u00a0<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Imaginez que nous avons un utilisateur. L'utilisateur peut \u00eatre une personne, un bot ou une autre application, tous cherchant des r\u00e9ponses \u00e0 des questions sp\u00e9cifiques. Par exemple, ils pourraient demander : \u00ab Quel \u00e9tait le taux de d\u00e9sabonnement au T1 pour les clients de la r\u00e9gion sud ? \u00bb<\/p>

La premi\u00e8re partie de cette question est g\u00e9n\u00e9ralement dans le champ d'application d'un mod\u00e8le de langage large (LLM) g\u00e9n\u00e9ral. Cependant, la sp\u00e9cificit\u00e9 des donn\u00e9es requises pour \u00ab Q1 des clients du sud \u00bb n'est pas directement disponible dans les LLM, car elle est unique \u00e0 l'entreprise et \u00e9volue avec le temps.<\/p>

Pour g\u00e9rer cela, plusieurs sources de donn\u00e9es pourraient \u00eatre n\u00e9cessaires. Celles-ci pourraient inclure des PDF, d'autres applications professionnelles ou m\u00eame des images. Acc\u00e9der aux bonnes donn\u00e9es est crucial pour r\u00e9pondre avec pr\u00e9cision \u00e0 de telles requ\u00eates sp\u00e9cifiques.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Le r\u00f4le des bases de donn\u00e9es vectorielles dans RAG<\/strong><\/h3>

Une fois que vous avez rassembl\u00e9 les donn\u00e9es n\u00e9cessaires, elles sont saisies dans une base de donn\u00e9es vectorielle<\/span>. Cette base de donn\u00e9es organise \u00e0 la fois des donn\u00e9es structur\u00e9es et non structur\u00e9es dans un format de tableau math\u00e9matique, qui est plus compr\u00e9hensible pour les mod\u00e8les de machine learning et d'IA g\u00e9n\u00e9rative par rapport aux donn\u00e9es brutes. En interrogeant cette base de donn\u00e9es vectorielle, vous r\u00e9cup\u00e9rez un embedding contenant des donn\u00e9es pertinentes pour votre question.<\/p>

Cet embedding est ensuite r\u00e9introduit dans le LLM, enrichissant le prompt original avec des donn\u00e9es pr\u00e9cises et sourc\u00e9es. Le LLM traite ce prompt am\u00e9lior\u00e9 et fournit la r\u00e9ponse \u00e0 la question originale, garantissant pr\u00e9cision et pertinence.<\/p>

\u00c0 mesure que de nouvelles donn\u00e9es entrent dans la base de donn\u00e9es vectorielle, elles mettent \u00e0 jour les embeddings pertinents pour les requ\u00eates en cours telles que le taux de d\u00e9sabonnement au T1. Cette mise \u00e0 jour continue garantit que les requ\u00eates suivantes re\u00e7oivent les informations les plus r\u00e9centes et pertinentes.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Att\u00e9nuer les risques dans l'analyse de donn\u00e9es pilot\u00e9e par l'IA<\/strong><\/h3>\n

La qualit\u00e9 des donn\u00e9es entrant dans la base de donn\u00e9es vectorielle est tr\u00e8s importante pour les r\u00e9sultats produits. Assurer des donn\u00e9es propres, bien gouvern\u00e9es et correctement g\u00e9r\u00e9es est essentiel. De plus, la transparence des LLM utilis\u00e9s dans le processus est \u00e9galement cruciale. Il est important d'utiliser des LLM qui sont transparents dans leurs processus de formation pour garantir fiabilit\u00e9 et pr\u00e9cision.<\/p>\n

Chez NextBrain AI<\/a>, nous utilisons la derni\u00e8re technologie AI pour fournir une analyse de donn\u00e9es pr\u00e9cise et des insights commerciaux exploitables, sans les complexit\u00e9s souvent associ\u00e9es aux mises en \u0153uvre techniques. Planifiez votre d\u00e9monstration aujourd'hui<\/a> pour exp\u00e9rimenter de premi\u00e8re main comment notre solution fonctionne.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\"R\u00e9servez\t\t\t\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>","protected":false},"excerpt":{"rendered":"

Retrieval-Augmented Generation (RAG) is the method of refining the output of a substantial language model by referring to a credible knowledge base beyond its training […]<\/p>\n","protected":false},"author":1,"featured_media":7826,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[70],"tags":[598,601,290,434,264,597,600,282,587,599],"class_list":["post-7825","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-blog","tag-ai-driven-data-analysis","tag-business-insights","tag-data-analysis-2","tag-data-governance","tag-generative-ai","tag-large-language-model","tag-llm","tag-machine-learning","tag-rag","tag-vector-database"],"yoast_head":"\nRAG Explained in Simple Words - NextBrain AI | No-Code Machine Learning<\/title>\n<meta name=\"description\" content=\"Discover how Retrieval-Augmented Generation (RAG) revolutionizes data handling with vector databases and large language models.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/nextbrain.ai\/fr\/blog\/rag-explained-in-simple-words\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"RAG Explained in Simple Words - NextBrain AI | No-Code Machine Learning\" \/>\n<meta property=\"og:description\" content=\"Discover how Retrieval-Augmented Generation (RAG) revolutionizes data handling with vector databases and large language models.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/nextbrain.ai\/fr\/blog\/rag-explained-in-simple-words\" \/>\n<meta property=\"og:site_name\" content=\"NextBrain AI | No-Code Machine Learning\" \/>\n<meta property=\"article:published_time\" content=\"2024-05-14T09:18:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-05-14T09:22:02+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/nextbrain.ai\/wp-content\/uploads\/2024\/05\/RAG.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1080\" \/>\n\t<meta property=\"og:image:height\" content=\"1080\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"admin1061\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@nextbrain_ai\" \/>\n<meta name=\"twitter:site\" content=\"@nextbrain_ai\" \/>\n<meta name=\"twitter:label1\" content=\"\u00c9crit par\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin1061\" \/>\n\t<meta name=\"twitter:label2\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"RAG expliqu\u00e9 en termes simples - NextBrain AI | No-Code Machine Learning","description":"D\u00e9couvrez comment la g\u00e9n\u00e9ration augment\u00e9e par r\u00e9cup\u00e9ration (RAG) r\u00e9volutionne la gestion des donn\u00e9es avec des bases de donn\u00e9es vectorielles et des mod\u00e8les de langage large.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/nextbrain.ai\/fr\/blog\/rag-explained-in-simple-words","og_locale":"fr_FR","og_type":"article","og_title":"RAG Explained in Simple Words - NextBrain AI | No-Code Machine Learning","og_description":"Discover how Retrieval-Augmented Generation (RAG) revolutionizes data handling with vector databases and large language models.","og_url":"https:\/\/nextbrain.ai\/fr\/blog\/rag-explained-in-simple-words","og_site_name":"NextBrain AI | No-Code Machine Learning","article_published_time":"2024-05-14T09:18:00+00:00","article_modified_time":"2024-05-14T09:22:02+00:00","og_image":[{"width":1080,"height":1080,"url":"https:\/\/nextbrain.ai\/wp-content\/uploads\/2024\/05\/RAG.png","type":"image\/png"}],"author":"admin1061","twitter_card":"summary_large_image","twitter_creator":"@nextbrain_ai","twitter_site":"@nextbrain_ai","twitter_misc":{"\u00c9crit par":"admin1061","Dur\u00e9e de lecture estim\u00e9e":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/nextbrain.ai\/blog\/rag-explained-in-simple-words#article","isPartOf":{"@id":"https:\/\/nextbrain.ai\/blog\/rag-explained-in-simple-words"},"author":{"name":"admin1061","@id":"https:\/\/nextbrain.ai\/#\/schema\/person\/664f8de536c1bdc2b939139c7ddac060"},"headline":"RAG Explained in Simple Words","datePublished":"2024-05-14T09:18:00+00:00","dateModified":"2024-05-14T09:22:02+00:00","mainEntityOfPage":{"@id":"https:\/\/nextbrain.ai\/blog\/rag-explained-in-simple-words"},"wordCount":401,"commentCount":0,"publisher":{"@id":"https:\/\/nextbrain.ai\/#organization"},"image":{"@id":"https:\/\/nextbrain.ai\/blog\/rag-explained-in-simple-words#primaryimage"},"thumbnailUrl":"https:\/\/nextbrain.ai\/wp-content\/uploads\/2024\/05\/RAG.png","keywords":["AI-driven data analysis","business insights","data analysis","Data Governance","generative AI","large language model","LLM","Machine Learning","RAG","vector database"],"articleSection":["blog"],"inLanguage":"fr-FR","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/nextbrain.ai\/blog\/rag-explained-in-simple-words#respond"]}]},{"@type":"WebPage","@id":"https:\/\/nextbrain.ai\/blog\/rag-explained-in-simple-words","url":"https:\/\/nextbrain.ai\/blog\/rag-explained-in-simple-words","name":"RAG expliqu\u00e9 en termes simples - NextBrain AI | No-Code Machine Learning","isPartOf":{"@id":"https:\/\/nextbrain.ai\/#website"},"primaryImageOfPage":{"@id":"https:\/\/nextbrain.ai\/blog\/rag-explained-in-simple-words#primaryimage"},"image":{"@id":"https:\/\/nextbrain.ai\/blog\/rag-explained-in-simple-words#primaryimage"},"thumbnailUrl":"https:\/\/nextbrain.ai\/wp-content\/uploads\/2024\/05\/RAG.png","datePublished":"2024-05-14T09:18:00+00:00","dateModified":"2024-05-14T09:22:02+00:00","description":"D\u00e9couvrez comment la g\u00e9n\u00e9ration augment\u00e9e par r\u00e9cup\u00e9ration (RAG) r\u00e9volutionne la gestion des donn\u00e9es avec des bases de donn\u00e9es vectorielles et des mod\u00e8les de langage large.","breadcrumb":{"@id":"https:\/\/nextbrain.ai\/blog\/rag-explained-in-simple-words#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/nextbrain.ai\/blog\/rag-explained-in-simple-words"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/nextbrain.ai\/blog\/rag-explained-in-simple-words#primaryimage","url":"https:\/\/nextbrain.ai\/wp-content\/uploads\/2024\/05\/RAG.png","contentUrl":"https:\/\/nextbrain.ai\/wp-content\/uploads\/2024\/05\/RAG.png","width":1080,"height":1080},{"@type":"BreadcrumbList","@id":"https:\/\/nextbrain.ai\/blog\/rag-explained-in-simple-words#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Portada","item":"https:\/\/nextbrain.ai\/"},{"@type":"ListItem","position":2,"name":"RAG Explained in Simple Words"}]},{"@type":"WebSite","@id":"https:\/\/nextbrain.ai\/#website","url":"https:\/\/nextbrain.ai\/","name":"NextBrain AI | Machine Learning sans code","description":"Upgrade your decision-making","publisher":{"@id":"https:\/\/nextbrain.ai\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/nextbrain.ai\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"},{"@type":"Organization","@id":"https:\/\/nextbrain.ai\/#organization","name":"NextBrain.ai","url":"https:\/\/nextbrain.ai\/","logo":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/nextbrain.ai\/#\/schema\/logo\/image\/","url":"http:\/\/nextbrain.ai\/wp-content\/uploads\/2022\/01\/logoNext.png","contentUrl":"http:\/\/nextbrain.ai\/wp-content\/uploads\/2022\/01\/logoNext.png","width":270,"height":96,"caption":"NextBrain.ai"},"image":{"@id":"https:\/\/nextbrain.ai\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/nextbrain_ai","https:\/\/www.linkedin.com\/company\/nextbrain-ai\/","https:\/\/www.youtube.com\/channel\/UCpRhfXZE3YEdfgp2K0U9kxQ","https:\/\/github.com\/NextBrain-ai"]},{"@type":"Person","@id":"https:\/\/nextbrain.ai\/#\/schema\/person\/664f8de536c1bdc2b939139c7ddac060","name":"admin1061","image":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/nextbrain.ai\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/56db6a17980685fa0a8ed3f9e359af33?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/56db6a17980685fa0a8ed3f9e359af33?s=96&d=mm&r=g","caption":"admin1061"},"sameAs":["http:\/\/nextbrain.ai\/"]}]}},"_links":{"self":[{"href":"https:\/\/nextbrain.ai\/fr\/wp-json\/wp\/v2\/posts\/7825"}],"collection":[{"href":"https:\/\/nextbrain.ai\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/nextbrain.ai\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/nextbrain.ai\/fr\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/nextbrain.ai\/fr\/wp-json\/wp\/v2\/comments?post=7825"}],"version-history":[{"count":19,"href":"https:\/\/nextbrain.ai\/fr\/wp-json\/wp\/v2\/posts\/7825\/revisions"}],"predecessor-version":[{"id":7845,"href":"https:\/\/nextbrain.ai\/fr\/wp-json\/wp\/v2\/posts\/7825\/revisions\/7845"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/nextbrain.ai\/fr\/wp-json\/wp\/v2\/media\/7826"}],"wp:attachment":[{"href":"https:\/\/nextbrain.ai\/fr\/wp-json\/wp\/v2\/media?parent=7825"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/nextbrain.ai\/fr\/wp-json\/wp\/v2\/categories?post=7825"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/nextbrain.ai\/fr\/wp-json\/wp\/v2\/tags?post=7825"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}