{"id":27505,"date":"2023-06-26T07:21:54","date_gmt":"2023-06-26T07:21:54","guid":{"rendered":"https:\/\/meetcody.ai\/blog\/chunking-explique\/"},"modified":"2023-06-27T03:22:04","modified_gmt":"2023-06-27T03:22:04","slug":"chunking-explique","status":"publish","type":"post","link":"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/","title":{"rendered":"Comment Cody g\u00e9n\u00e8re-t-il des r\u00e9ponses \u00e0 partir de vos documents ?"},"content":{"rendered":"

Lorsque vous commencez \u00e0 utiliser Cody, il est possible que vous soyez d\u00e9\u00e7u ou d\u00e9courag\u00e9 par l’incapacit\u00e9 de Cody \u00e0 g\u00e9n\u00e9rer les r\u00e9ponses attendues. Dans ce court blog, nous n’approfondirons pas la fa\u00e7on dont vous devriez utiliser Cody, mais nous vous donnerons une id\u00e9e de la fa\u00e7on dont Cody utilise vos documents pour g\u00e9n\u00e9rer des r\u00e9ponses afin que vous puissiez mieux comprendre le processus de g\u00e9n\u00e9ration et l’exp\u00e9rimenter.<\/p>\n

Deux facteurs principaux influencent la g\u00e9n\u00e9ration de r\u00e9ponses \u00e0 l’aide de vos documents :<\/p>\n

    \n
  1. Chunking<\/strong><\/li>\n
  2. Fen\u00eatre contextuelle<\/strong><\/li>\n<\/ol>\n

    Ces deux terminologies, le d\u00e9coupage et la fen\u00eatre contextuelle, sont interd\u00e9pendantes. On peut faire une analogie simple en comparant la g\u00e9n\u00e9ration de r\u00e9ponses \u00e0 la cuisson des aliments. Les morceaux peuvent \u00eatre vus comme des pi\u00e8ces individuelles de l\u00e9gumes que vous coupez, tandis que la fen\u00eatre contextuelle repr\u00e9sente la taille de l’ustensile de cuisine. Il est important de couper les l\u00e9gumes en morceaux de taille optimale pour am\u00e9liorer le go\u00fbt g\u00e9n\u00e9ral, et un ustensile plus grand permet d’ajouter plus de morceaux de l\u00e9gumes.<\/p>\n

    Qu’est-ce que le d\u00e9coupage ?<\/h2>\n

    En termes simples, le d\u00e9coupage est l’action de diviser le contenu en morceaux g\u00e9rables pour une utilisation efficace de la m\u00e9moire. Si vous avez lu nos blogs<\/a>, vous savez sans doute que les mod\u00e8les tels que le GPT n\u00e9cessitent des ressources importantes et que, pour faire face aux contraintes de la fen\u00eatre contextuelle, nous employons de multiples processus tels que le d\u00e9coupage en morceaux.<\/p>\n

    Le regroupement est un processus effectu\u00e9 apr\u00e8s le t\u00e9l\u00e9chargement des documents dans Cody. Il divise ou segmente le document en plusieurs morceaux, chaque morceau contenant un contexte environnant pertinent. Des \u00e9tiquettes num\u00e9riques sont ensuite attribu\u00e9es \u00e0 ces morceaux pour faciliter le calcul, ce qui est connu sous le nom de “embedding” (int\u00e9gration). Il est important de trouver la taille optimale des morceaux. Une taille de morceau plus petite r\u00e9duit la pertinence du contexte, tandis qu’une taille de morceau plus grande introduit plus de bruit. L’algorithme de d\u00e9coupage de Cody ajuste dynamiquement la taille des morceaux en fonction de la distribution des jetons d\u00e9finie par l’utilisateur.<\/p>\n

    Comment la fen\u00eatre contextuelle affecte-t-elle les r\u00e9ponses du bot ?<\/strong><\/h2>\n

    Diff\u00e9rents facteurs tels que la personnalit\u00e9, le score de pertinence, etc., influencent la qualit\u00e9 des r\u00e9ponses des robots. La fen\u00eatre contextuelle du mod\u00e8le joue \u00e9galement un r\u00f4le important dans la d\u00e9termination de la qualit\u00e9. La fen\u00eatre contextuelle fait r\u00e9f\u00e9rence \u00e0 la quantit\u00e9 de texte qu’un mod\u00e8le linguistique peut traiter en un seul appel. Puisque Cody utilise les embeddings et l’injection de contexte pour g\u00e9n\u00e9rer des r\u00e9ponses \u00e0 l’aide de mod\u00e8les OpenAI, une fen\u00eatre de contexte plus large permet au mod\u00e8le d’ing\u00e9rer plus de donn\u00e9es dans chaque requ\u00eate.<\/p>\n

    \ud83d\udca1 Chaque requ\u00eate (\u2264 fen\u00eatre contextuelle)<\/strong> = Personnalit\u00e9 du robot + morceaux de connaissance + historique + donn\u00e9es de l’utilisateur + r\u00e9ponse<\/p><\/blockquote>\n

    Fen\u00eatres contextuelles de diff\u00e9rents mod\u00e8les :<\/strong><\/p>\n

      \n
    1. GPT-3.5 :<\/strong> 4096 tokens (\u22483500 mots)<\/li>\n
    2. GPT-3.5 16K :<\/strong> 16000 tokens (\u224813000 mots)<\/li>\n
    3. GPT-4 :<\/strong> 8000 tokens (\u22487000 mots)<\/li>\n<\/ol>\n

      Lorsque la fen\u00eatre contextuelle est plus grande, elle permet d’afficher une plus grande proportion de chaque param\u00e8tre, y compris la personnalit\u00e9, les morceaux, l’historique, l’entr\u00e9e et la r\u00e9ponse. Ce contexte \u00e9largi permet au bot de g\u00e9n\u00e9rer des r\u00e9ponses plus pertinentes, plus coh\u00e9rentes et plus cr\u00e9atives.<\/p>\n

      Le dernier ajout de Cody permet aux utilisateurs de v\u00e9rifier les citations de documents en cliquant sur le nom du document \u00e0 la fin des r\u00e9ponses. Ces citations correspondent aux morceaux obtenus par la recherche s\u00e9mantique. Cody d\u00e9termine le seuil des morceaux pour le contexte sur la base du score de pertinence d\u00e9fini par l’utilisateur. Si l’utilisateur d\u00e9finit un score de pertinence \u00e9lev\u00e9, Cody n’utilise que les morceaux qui d\u00e9passent un seuil pr\u00e9d\u00e9fini comme contexte pour g\u00e9n\u00e9rer la r\u00e9ponse.<\/p>\n

      Exemple<\/h2>\n

      En supposant un seuil limite pr\u00e9d\u00e9fini de 90 % pour un score de pertinence \u00e9lev\u00e9, Cody \u00e9carte tous les morceaux dont le score de pertinence est inf\u00e9rieur \u00e0 90 %. Nous recommandons aux nouveaux utilisateurs de commencer par un score de pertinence moins \u00e9lev\u00e9 (faible ou \u00e9quilibr\u00e9), en particulier lorsqu’ils utilisent des documents t\u00e9l\u00e9charg\u00e9s (PDF, PowerPoint, Word, etc.) ou des sites web. Les documents ou sites web t\u00e9l\u00e9charg\u00e9s peuvent rencontrer des probl\u00e8mes de formatage et de lisibilit\u00e9 lors du pr\u00e9traitement, ce qui peut se traduire par des scores de pertinence inf\u00e9rieurs. La mise en forme du document \u00e0 l’aide de notre \u00e9diteur de texte int\u00e9gr\u00e9, au lieu de t\u00e9l\u00e9charger des documents bruts, garantit la plus grande pr\u00e9cision et la meilleure cote de confiance.<\/p>\n

      \"Illustre<\/p>\n

      Si vous avez trouv\u00e9 ce blog int\u00e9ressant et que vous souhaitez approfondir les concepts de fen\u00eatre contextuelle et de d\u00e9coupage, nous vous recommandons vivement de lire ce blog<\/a> \u00e9crit par Kristian de All About AI. Pour plus de ressources, vous pouvez \u00e9galement consulter notre Centre d’aide<\/a> et rejoindre notre communaut\u00e9 Discord<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"

      Lorsque vous commencez \u00e0 utiliser Cody, il est possible que vous soyez d\u00e9\u00e7u ou d\u00e9courag\u00e9 par l’incapacit\u00e9 de Cody \u00e0 g\u00e9n\u00e9rer les r\u00e9ponses attendues. Dans ce court blog, nous n’approfondirons pas la fa\u00e7on dont vous devriez utiliser Cody, mais nous vous donnerons une id\u00e9e de la fa\u00e7on dont Cody utilise vos documents pour g\u00e9n\u00e9rer des… Read more »<\/a><\/p>\n","protected":false},"author":2,"featured_media":27513,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"inline_featured_image":false,"footnotes":""},"categories":[29],"tags":[],"class_list":["post-27505","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-non-classifiee"],"acf":[],"yoast_head":"\nComment Cody g\u00e9n\u00e8re-t-il des r\u00e9ponses \u00e0 partir de vos documents ?<\/title>\n<meta name=\"description\" content=\"Ces blogs expliquent de mani\u00e8re simplifi\u00e9e comment le d\u00e9coupage en morceaux et la fen\u00eatre contextuelle jouent un r\u00f4le majeur dans la g\u00e9n\u00e9ration de r\u00e9ponses.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Comment Cody g\u00e9n\u00e8re-t-il des r\u00e9ponses \u00e0 partir de vos documents ?\" \/>\n<meta property=\"og:description\" content=\"Ces blogs expliquent de mani\u00e8re simplifi\u00e9e comment le d\u00e9coupage en morceaux et la fen\u00eatre contextuelle jouent un r\u00f4le majeur dans la g\u00e9n\u00e9ration de r\u00e9ponses.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/\" \/>\n<meta property=\"og:site_name\" content=\"Cody - The AI Trained on Your Business\" \/>\n<meta property=\"article:published_time\" content=\"2023-06-26T07:21:54+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-06-27T03:22:04+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/meetcody.ai\/wp-content\/uploads\/2023\/06\/ChunkingCoevr.png\" \/>\n\t<meta property=\"og:image:width\" content=\"2400\" \/>\n\t<meta property=\"og:image:height\" content=\"1350\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Om Kamath\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@meetcodyai\" \/>\n<meta name=\"twitter:site\" content=\"@meetcodyai\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Om Kamath\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/\"},\"author\":{\"name\":\"Om Kamath\",\"@id\":\"https:\/\/meetcody.ai\/#\/schema\/person\/cde65ec55b79cd833a9777d0a62e83c8\"},\"headline\":\"Comment Cody g\u00e9n\u00e8re-t-il des r\u00e9ponses \u00e0 partir de vos documents ?\",\"datePublished\":\"2023-06-26T07:21:54+00:00\",\"dateModified\":\"2023-06-27T03:22:04+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/\"},\"wordCount\":907,\"publisher\":{\"@id\":\"https:\/\/meetcody.ai\/#organization\"},\"image\":{\"@id\":\"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/meetcody.ai\/wp-content\/uploads\/2023\/06\/ChunkingCoevr.png\",\"articleSection\":[\"Non classifi\u00e9(e)\"],\"inLanguage\":\"fr-FR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/\",\"url\":\"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/\",\"name\":\"Comment Cody g\u00e9n\u00e8re-t-il des r\u00e9ponses \u00e0 partir de vos documents ?\",\"isPartOf\":{\"@id\":\"https:\/\/meetcody.ai\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/meetcody.ai\/wp-content\/uploads\/2023\/06\/ChunkingCoevr.png\",\"datePublished\":\"2023-06-26T07:21:54+00:00\",\"dateModified\":\"2023-06-27T03:22:04+00:00\",\"description\":\"Ces blogs expliquent de mani\u00e8re simplifi\u00e9e comment le d\u00e9coupage en morceaux et la fen\u00eatre contextuelle jouent un r\u00f4le majeur dans la g\u00e9n\u00e9ration de r\u00e9ponses.\",\"breadcrumb\":{\"@id\":\"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/#primaryimage\",\"url\":\"https:\/\/meetcody.ai\/wp-content\/uploads\/2023\/06\/ChunkingCoevr.png\",\"contentUrl\":\"https:\/\/meetcody.ai\/wp-content\/uploads\/2023\/06\/ChunkingCoevr.png\",\"width\":2400,\"height\":1350},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/meetcody.ai\/fr\/home-v2\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Comment Cody g\u00e9n\u00e8re-t-il des r\u00e9ponses \u00e0 partir de vos documents ?\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/meetcody.ai\/#website\",\"url\":\"https:\/\/meetcody.ai\/\",\"name\":\"Cody AI - The AI Trained on Your Business\",\"description\":\"AI Powered Knowledge Base for Employees\",\"publisher\":{\"@id\":\"https:\/\/meetcody.ai\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/meetcody.ai\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/meetcody.ai\/#organization\",\"name\":\"Cody AI - The AI Trained on Your Business\",\"url\":\"https:\/\/meetcody.ai\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/meetcody.ai\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/meetcody.ai\/wp-content\/uploads\/2023\/05\/logo-codyai.svg\",\"contentUrl\":\"https:\/\/meetcody.ai\/wp-content\/uploads\/2023\/05\/logo-codyai.svg\",\"width\":\"1024\",\"height\":\"1024\",\"caption\":\"Cody AI - The AI Trained on Your Business\"},\"image\":{\"@id\":\"https:\/\/meetcody.ai\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/meetcodyai\",\"https:\/\/discord.com\/invite\/jXEVDcFxqs\"]},{\"@type\":\"Person\",\"@id\":\"https:\/\/meetcody.ai\/#\/schema\/person\/cde65ec55b79cd833a9777d0a62e83c8\",\"name\":\"Om Kamath\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\/\/meetcody.ai\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/3903c678cd7f6c8df0a843ae177998f5d413954afa3062f984a030a889a97849?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/3903c678cd7f6c8df0a843ae177998f5d413954afa3062f984a030a889a97849?s=96&d=mm&r=g\",\"caption\":\"Om Kamath\"},\"description\":\"Om Kamath\",\"sameAs\":[\"http:\/\/meetcody.ai\"],\"url\":\"https:\/\/meetcody.ai\/fr\/blog\/author\/omkamath\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Comment Cody g\u00e9n\u00e8re-t-il des r\u00e9ponses \u00e0 partir de vos documents ?","description":"Ces blogs expliquent de mani\u00e8re simplifi\u00e9e comment le d\u00e9coupage en morceaux et la fen\u00eatre contextuelle jouent un r\u00f4le majeur dans la g\u00e9n\u00e9ration de r\u00e9ponses.","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:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/","og_locale":"fr_FR","og_type":"article","og_title":"Comment Cody g\u00e9n\u00e8re-t-il des r\u00e9ponses \u00e0 partir de vos documents ?","og_description":"Ces blogs expliquent de mani\u00e8re simplifi\u00e9e comment le d\u00e9coupage en morceaux et la fen\u00eatre contextuelle jouent un r\u00f4le majeur dans la g\u00e9n\u00e9ration de r\u00e9ponses.","og_url":"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/","og_site_name":"Cody - The AI Trained on Your Business","article_published_time":"2023-06-26T07:21:54+00:00","article_modified_time":"2023-06-27T03:22:04+00:00","og_image":[{"width":2400,"height":1350,"url":"https:\/\/meetcody.ai\/wp-content\/uploads\/2023\/06\/ChunkingCoevr.png","type":"image\/png"}],"author":"Om Kamath","twitter_card":"summary_large_image","twitter_creator":"@meetcodyai","twitter_site":"@meetcodyai","twitter_misc":{"Written by":"Om Kamath","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/#article","isPartOf":{"@id":"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/"},"author":{"name":"Om Kamath","@id":"https:\/\/meetcody.ai\/#\/schema\/person\/cde65ec55b79cd833a9777d0a62e83c8"},"headline":"Comment Cody g\u00e9n\u00e8re-t-il des r\u00e9ponses \u00e0 partir de vos documents ?","datePublished":"2023-06-26T07:21:54+00:00","dateModified":"2023-06-27T03:22:04+00:00","mainEntityOfPage":{"@id":"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/"},"wordCount":907,"publisher":{"@id":"https:\/\/meetcody.ai\/#organization"},"image":{"@id":"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/#primaryimage"},"thumbnailUrl":"https:\/\/meetcody.ai\/wp-content\/uploads\/2023\/06\/ChunkingCoevr.png","articleSection":["Non classifi\u00e9(e)"],"inLanguage":"fr-FR"},{"@type":"WebPage","@id":"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/","url":"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/","name":"Comment Cody g\u00e9n\u00e8re-t-il des r\u00e9ponses \u00e0 partir de vos documents ?","isPartOf":{"@id":"https:\/\/meetcody.ai\/#website"},"primaryImageOfPage":{"@id":"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/#primaryimage"},"image":{"@id":"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/#primaryimage"},"thumbnailUrl":"https:\/\/meetcody.ai\/wp-content\/uploads\/2023\/06\/ChunkingCoevr.png","datePublished":"2023-06-26T07:21:54+00:00","dateModified":"2023-06-27T03:22:04+00:00","description":"Ces blogs expliquent de mani\u00e8re simplifi\u00e9e comment le d\u00e9coupage en morceaux et la fen\u00eatre contextuelle jouent un r\u00f4le majeur dans la g\u00e9n\u00e9ration de r\u00e9ponses.","breadcrumb":{"@id":"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/#primaryimage","url":"https:\/\/meetcody.ai\/wp-content\/uploads\/2023\/06\/ChunkingCoevr.png","contentUrl":"https:\/\/meetcody.ai\/wp-content\/uploads\/2023\/06\/ChunkingCoevr.png","width":2400,"height":1350},{"@type":"BreadcrumbList","@id":"https:\/\/meetcody.ai\/fr\/blog\/chunking-explique\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/meetcody.ai\/fr\/home-v2\/"},{"@type":"ListItem","position":2,"name":"Comment Cody g\u00e9n\u00e8re-t-il des r\u00e9ponses \u00e0 partir de vos documents ?"}]},{"@type":"WebSite","@id":"https:\/\/meetcody.ai\/#website","url":"https:\/\/meetcody.ai\/","name":"Cody AI - The AI Trained on Your Business","description":"AI Powered Knowledge Base for Employees","publisher":{"@id":"https:\/\/meetcody.ai\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/meetcody.ai\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"},{"@type":"Organization","@id":"https:\/\/meetcody.ai\/#organization","name":"Cody AI - The AI Trained on Your Business","url":"https:\/\/meetcody.ai\/","logo":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/meetcody.ai\/#\/schema\/logo\/image\/","url":"https:\/\/meetcody.ai\/wp-content\/uploads\/2023\/05\/logo-codyai.svg","contentUrl":"https:\/\/meetcody.ai\/wp-content\/uploads\/2023\/05\/logo-codyai.svg","width":"1024","height":"1024","caption":"Cody AI - The AI Trained on Your Business"},"image":{"@id":"https:\/\/meetcody.ai\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/meetcodyai","https:\/\/discord.com\/invite\/jXEVDcFxqs"]},{"@type":"Person","@id":"https:\/\/meetcody.ai\/#\/schema\/person\/cde65ec55b79cd833a9777d0a62e83c8","name":"Om Kamath","image":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/meetcody.ai\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/3903c678cd7f6c8df0a843ae177998f5d413954afa3062f984a030a889a97849?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/3903c678cd7f6c8df0a843ae177998f5d413954afa3062f984a030a889a97849?s=96&d=mm&r=g","caption":"Om Kamath"},"description":"Om Kamath","sameAs":["http:\/\/meetcody.ai"],"url":"https:\/\/meetcody.ai\/fr\/blog\/author\/omkamath\/"}]}},"_links":{"self":[{"href":"https:\/\/meetcody.ai\/fr\/wp-json\/wp\/v2\/posts\/27505","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/meetcody.ai\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/meetcody.ai\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/meetcody.ai\/fr\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/meetcody.ai\/fr\/wp-json\/wp\/v2\/comments?post=27505"}],"version-history":[{"count":1,"href":"https:\/\/meetcody.ai\/fr\/wp-json\/wp\/v2\/posts\/27505\/revisions"}],"predecessor-version":[{"id":27523,"href":"https:\/\/meetcody.ai\/fr\/wp-json\/wp\/v2\/posts\/27505\/revisions\/27523"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/meetcody.ai\/fr\/wp-json\/wp\/v2\/media\/27513"}],"wp:attachment":[{"href":"https:\/\/meetcody.ai\/fr\/wp-json\/wp\/v2\/media?parent=27505"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/meetcody.ai\/fr\/wp-json\/wp\/v2\/categories?post=27505"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/meetcody.ai\/fr\/wp-json\/wp\/v2\/tags?post=27505"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}