{"id":2340,"date":"2026-05-20T09:55:08","date_gmt":"2026-05-20T07:55:08","guid":{"rendered":"https:\/\/askem.eu\/?p=2340"},"modified":"2026-05-20T09:55:12","modified_gmt":"2026-05-20T07:55:12","slug":"llmlingua-compresser-ses-prompts","status":"publish","type":"post","link":"https:\/\/askem.eu\/en\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/","title":{"rendered":"LLMLingua : compresser ses prompts"},"content":{"rendered":"<h2 class=\"wp-block-heading\">LLMLingua&nbsp;: compresser ses prompts pour r\u00e9duire co\u00fbts et latence des LLM<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Quand un agent IA s&rsquo;industrialise, les prompts grossissent&nbsp;: instructions syst\u00e8me, exemples few-shot, contexte RAG, historique conversationnel. Chaque token compte, \u00e0 la fois en facture API et en temps de r\u00e9ponse. <strong><a href=\"https:\/\/github.com\/microsoft\/LLMLingua\">LLMLingua<\/a><\/strong>, projet open source de Microsoft Research (licence MIT), propose une r\u00e9ponse pragmatique&nbsp;: compresser le prompt avant l&rsquo;envoi au mod\u00e8le, sans d\u00e9grader la sortie.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Le principe&nbsp;: un petit mod\u00e8le pour all\u00e9ger les gros<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">LLMLingua repose sur une observation simple&nbsp;: les LLM tol\u00e8rent une part importante de redondance dans leurs entr\u00e9es. Un petit mod\u00e8le de langage local (LLaMA 7B, GPT-2, ou plus petit) calcule la perplexit\u00e9 de chaque token et supprime ceux qui sont les plus pr\u00e9visibles, donc les moins informatifs. Le prompt restant, parfois 5 \u00e0 20 fois plus court, est envoy\u00e9 au mod\u00e8le cible, GPT-4, Claude, ou un mod\u00e8le open source servi via vLLM.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">Trois variantes coexistent dans le projet&nbsp;:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>LLMLingua<\/strong>&nbsp;: compression token par token, rapide et g\u00e9n\u00e9rique<\/li>\n\n\n\n<li><strong>LongLLMLingua<\/strong>&nbsp;: optimis\u00e9 pour les tr\u00e8s longs contextes (RAG, documents), avec r\u00e9ordonnancement des passages pertinents<\/li>\n\n\n\n<li><strong>LLMLingua-2<\/strong>&nbsp;: version supervis\u00e9e, plus rapide encore, form\u00e9e par distillation \u00e0 partir de GPT-4<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\">Ce que \u00e7a change en production<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Les gains rapport\u00e9s par l&rsquo;\u00e9quipe Microsoft tournent autour de 4x \u00e0 20x de compression selon le sc\u00e9nario, avec une perte de qualit\u00e9 n\u00e9gligeable sur les benchmarks classiques (LongBench, GSM8K, ZeroSCROLLS). Concr\u00e8tement, cela ouvre plusieurs leviers&nbsp;:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>R\u00e9duction directe des co\u00fbts API<\/strong>&nbsp;: un prompt RAG de 8000 tokens passe \u00e0 1000 ou 2000, la facture suit<\/li>\n\n\n\n<li><strong>Latence en baisse<\/strong>&nbsp;: moins de tokens en entr\u00e9e, c&rsquo;est aussi moins de temps de traitement c\u00f4t\u00e9 serveur<\/li>\n\n\n\n<li><strong>Fen\u00eatres de contexte respect\u00e9es<\/strong>&nbsp;: utile pour rester sous les limites de mod\u00e8les plus petits ou auto-h\u00e9berg\u00e9s<\/li>\n\n\n\n<li><strong>\u00c9conomie d&rsquo;\u00e9nergie<\/strong> sur les d\u00e9ploiements self-hosted via Ollama, vLLM ou LiteLLM<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\">Int\u00e9gration dans une stack open source<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">LLMLingua s&rsquo;installe en quelques lignes via pip et s&rsquo;int\u00e8gre naturellement avant l&rsquo;appel au LLM, en aval du pipeline RAG (Qdrant, pgvector) et juste avant le routage. Dans une architecture d&rsquo;agents, on peut le placer entre le reranker et l&rsquo;appel final au mod\u00e8le. Le projet expose une API Python claire&nbsp;:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>from llmlingua import PromptCompressor\n\ncompressor = PromptCompressor(model_name=\"microsoft\/llmlingua-2-xlm-roberta-large-meetingbank\")\ncompressed = compressor.compress_prompt(prompt, rate=0.33)\n# compressed&#91;\"compressed_prompt\"] envoy\u00e9 au LLM\n<\/code><\/pre>\n\n\n\n<h3 class=\"wp-block-heading\">Limites et points d&rsquo;attention<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">La compression n&rsquo;est pas magique&nbsp;: sur des prompts tr\u00e8s structur\u00e9s (JSON, code, instructions pr\u00e9cises), elle peut casser la syntaxe. LLMLingua-2 corrige une partie de ce travers via un entra\u00eenement supervis\u00e9, mais il reste prudent de tester son pipeline avec un outil comme <strong>Promptfoo<\/strong> ou <strong><a href=\"https:\/\/askem.eu\/en\/2026\/05\/13\/ragas-mesurer-objectivement-la-qualite-dun-pipeline-rag-en-open-source\/\" type=\"post\" id=\"2320\">RAGAS<\/a><\/strong> avant de basculer en production. \u00c0 noter aussi que le petit mod\u00e8le de compression doit tourner quelque part, ce qui ajoute une d\u00e9pendance mat\u00e9rielle modeste mais r\u00e9elle.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">O\u00f9 LLMLingua trouve sa place<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Dans une architecture IA mature, LLMLingua compl\u00e8te d&rsquo;autres briques \u00e9voqu\u00e9es pr\u00e9c\u00e9demment sur ce site&nbsp;: un pipeline RAG bas\u00e9 sur Qdrant et un reranker, une couche d&rsquo;\u00e9valuation RAGAS, un routage Semantic Router pour aiguiller vers le bon mod\u00e8le, et des tests Promptfoo en CI\/CD. La compression de prompt est l&rsquo;une de ces optimisations discr\u00e8tes qui ne se voient pas dans les d\u00e9mos, mais qui changent l&rsquo;\u00e9conomie d&rsquo;un syst\u00e8me en production.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><em>Projet&nbsp;: <a href=\"https:\/\/github.com\/microsoft\/LLMLingua\" target=\"_blank\" rel=\"noreferrer noopener\">github.com\/microsoft\/LLMLingua<\/a> \u2014 Licence MIT<\/em><\/p>","protected":false},"excerpt":{"rendered":"<p>LLMLingua&nbsp;: compresser ses prompts pour r\u00e9duire co\u00fbts et latence des LLM Quand un agent IA s&rsquo;industrialise, les prompts grossissent&nbsp;: instructions syst\u00e8me, exemples few-shot, contexte RAG, historique conversationnel. Chaque token compte, \u00e0 la fois en facture API et en temps de r\u00e9ponse. LLMLingua, projet open source de Microsoft Research (licence MIT), propose une r\u00e9ponse pragmatique&nbsp;: compresser [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":2341,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ocean_post_layout":"","ocean_both_sidebars_style":"","ocean_both_sidebars_content_width":0,"ocean_both_sidebars_sidebars_width":0,"ocean_sidebar":"","ocean_second_sidebar":"","ocean_disable_margins":"enable","ocean_add_body_class":"","ocean_shortcode_before_top_bar":"","ocean_shortcode_after_top_bar":"","ocean_shortcode_before_header":"","ocean_shortcode_after_header":"","ocean_has_shortcode":"","ocean_shortcode_after_title":"","ocean_shortcode_before_footer_widgets":"","ocean_shortcode_after_footer_widgets":"","ocean_shortcode_before_footer_bottom":"","ocean_shortcode_after_footer_bottom":"","ocean_display_top_bar":"default","ocean_display_header":"default","ocean_header_style":"","ocean_center_header_left_menu":"","ocean_custom_header_template":"","ocean_custom_logo":0,"ocean_custom_retina_logo":0,"ocean_custom_logo_max_width":0,"ocean_custom_logo_tablet_max_width":0,"ocean_custom_logo_mobile_max_width":0,"ocean_custom_logo_max_height":0,"ocean_custom_logo_tablet_max_height":0,"ocean_custom_logo_mobile_max_height":0,"ocean_header_custom_menu":"","ocean_menu_typo_font_family":"","ocean_menu_typo_font_subset":"","ocean_menu_typo_font_size":0,"ocean_menu_typo_font_size_tablet":0,"ocean_menu_typo_font_size_mobile":0,"ocean_menu_typo_font_size_unit":"px","ocean_menu_typo_font_weight":"","ocean_menu_typo_font_weight_tablet":"","ocean_menu_typo_font_weight_mobile":"","ocean_menu_typo_transform":"","ocean_menu_typo_transform_tablet":"","ocean_menu_typo_transform_mobile":"","ocean_menu_typo_line_height":0,"ocean_menu_typo_line_height_tablet":0,"ocean_menu_typo_line_height_mobile":0,"ocean_menu_typo_line_height_unit":"","ocean_menu_typo_spacing":0,"ocean_menu_typo_spacing_tablet":0,"ocean_menu_typo_spacing_mobile":0,"ocean_menu_typo_spacing_unit":"","ocean_menu_link_color":"","ocean_menu_link_color_hover":"","ocean_menu_link_color_active":"","ocean_menu_link_background":"","ocean_menu_link_hover_background":"","ocean_menu_link_active_background":"","ocean_menu_social_links_bg":"","ocean_menu_social_hover_links_bg":"","ocean_menu_social_links_color":"","ocean_menu_social_hover_links_color":"","ocean_disable_title":"default","ocean_disable_heading":"default","ocean_post_title":"","ocean_post_subheading":"","ocean_post_title_style":"","ocean_post_title_background_color":"","ocean_post_title_background":0,"ocean_post_title_bg_image_position":"","ocean_post_title_bg_image_attachment":"","ocean_post_title_bg_image_repeat":"","ocean_post_title_bg_image_size":"","ocean_post_title_height":0,"ocean_post_title_bg_overlay":0.5,"ocean_post_title_bg_overlay_color":"","ocean_disable_breadcrumbs":"default","ocean_breadcrumbs_color":"","ocean_breadcrumbs_separator_color":"","ocean_breadcrumbs_links_color":"","ocean_breadcrumbs_links_hover_color":"","ocean_display_footer_widgets":"default","ocean_display_footer_bottom":"default","ocean_custom_footer_template":"","osh_disable_topbar_sticky":"default","osh_disable_header_sticky":"default","osh_sticky_header_style":"default","osh_sticky_header_effect":"","osh_custom_sticky_logo":0,"osh_custom_retina_sticky_logo":0,"osh_custom_sticky_logo_height":0,"osh_background_color":"","osh_links_color":"","osh_links_hover_color":"","osh_links_active_color":"","osh_links_bg_color":"","osh_links_hover_bg_color":"","osh_links_active_bg_color":"","osh_menu_social_links_color":"","osh_menu_social_hover_links_color":"","ocean_post_oembed":"","ocean_post_self_hosted_media":"","ocean_post_video_embed":"","ocean_link_format":"","ocean_link_format_target":"self","ocean_quote_format":"","ocean_quote_format_link":"post","ocean_gallery_link_images":"on","ocean_gallery_id":[],"footnotes":""},"categories":[16],"tags":[],"class_list":["post-2340","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai","entry","has-media"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.6 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>LLMLingua : compresser ses prompts - askem<\/title>\n<meta name=\"description\" content=\"ASKEM BUREAU D&#039;\u00c9TUDES ET DE FORMATION NUM\u00c9RIQUE. Nous vous assistons dans la transformation num\u00e9rique de vos outils, services et organisations tout en pla\u00e7ant l\u2019humain au c\u0153ur de notre d\u00e9marche d\u2019accompagnement.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/askem.eu\/en\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"LLMLingua : compresser ses prompts - askem\" \/>\n<meta property=\"og:description\" content=\"ASKEM BUREAU D&#039;\u00c9TUDES ET DE FORMATION NUM\u00c9RIQUE. Nous vous assistons dans la transformation num\u00e9rique de vos outils, services et organisations tout en pla\u00e7ant l\u2019humain au c\u0153ur de notre d\u00e9marche d\u2019accompagnement.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/askem.eu\/en\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/\" \/>\n<meta property=\"og:site_name\" content=\"askem\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/fb.me\/askem.eu\" \/>\n<meta property=\"article:published_time\" content=\"2026-05-20T07:55:08+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-05-20T07:55:12+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:auto\/h:auto\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2026\/05\/sujet-askem-2026-05-11.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1600\" \/>\n\t<meta property=\"og:image:height\" content=\"900\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"askemadmin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"askemadmin\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/05\\\/20\\\/llmlingua-compresser-ses-prompts\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/05\\\/20\\\/llmlingua-compresser-ses-prompts\\\/\"},\"author\":{\"name\":\"askemadmin\",\"@id\":\"https:\\\/\\\/askem.eu\\\/#\\\/schema\\\/person\\\/8bbee74ab9a977d56bf4826662e9d2e9\"},\"headline\":\"LLMLingua : compresser ses prompts\",\"datePublished\":\"2026-05-20T07:55:08+00:00\",\"dateModified\":\"2026-05-20T07:55:12+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/05\\\/20\\\/llmlingua-compresser-ses-prompts\\\/\"},\"wordCount\":569,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/05\\\/20\\\/llmlingua-compresser-ses-prompts\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\/\\/askem.eu\\/wp-content\\/uploads\\/2026\\/05\\/sujet-askem-2026-05-11.png\",\"articleSection\":[\"AI\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/askem.eu\\\/2026\\\/05\\\/20\\\/llmlingua-compresser-ses-prompts\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/05\\\/20\\\/llmlingua-compresser-ses-prompts\\\/\",\"url\":\"https:\\\/\\\/askem.eu\\\/2026\\\/05\\\/20\\\/llmlingua-compresser-ses-prompts\\\/\",\"name\":\"LLMLingua : compresser ses prompts - askem\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/05\\\/20\\\/llmlingua-compresser-ses-prompts\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/05\\\/20\\\/llmlingua-compresser-ses-prompts\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\/\\/askem.eu\\/wp-content\\/uploads\\/2026\\/05\\/sujet-askem-2026-05-11.png\",\"datePublished\":\"2026-05-20T07:55:08+00:00\",\"dateModified\":\"2026-05-20T07:55:12+00:00\",\"description\":\"ASKEM BUREAU D'\u00c9TUDES ET DE FORMATION NUM\u00c9RIQUE. Nous vous assistons dans la transformation num\u00e9rique de vos outils, services et organisations tout en pla\u00e7ant l\u2019humain au c\u0153ur de notre d\u00e9marche d\u2019accompagnement.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/05\\\/20\\\/llmlingua-compresser-ses-prompts\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/askem.eu\\\/2026\\\/05\\\/20\\\/llmlingua-compresser-ses-prompts\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/05\\\/20\\\/llmlingua-compresser-ses-prompts\\\/#primaryimage\",\"url\":\"https:\\/\\/askem.eu\\/wp-content\\/uploads\\/2026\\/05\\/sujet-askem-2026-05-11.png\",\"contentUrl\":\"https:\\/\\/askem.eu\\/wp-content\\/uploads\\/2026\\/05\\/sujet-askem-2026-05-11.png\",\"width\":1600,\"height\":900},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/askem.eu\\\/2026\\\/05\\\/20\\\/llmlingua-compresser-ses-prompts\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Accueil\",\"item\":\"https:\\\/\\\/askem.eu\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"LLMLingua : compresser ses prompts\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/askem.eu\\\/#website\",\"url\":\"https:\\\/\\\/askem.eu\\\/\",\"name\":\"askem\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/askem.eu\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/askem.eu\\\/#organization\",\"name\":\"Askem\",\"url\":\"https:\\\/\\\/askem.eu\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/askem.eu\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\/\\/mlpi0fxo3sth.i.optimole.com\\/cb:3obA.c61\\/w:760\\/h:480\\/q:mauto\\/f:best\\/https:\\/\\/askem.eu\\/wp-content\\/uploads\\/2020\\/10\\/logoGalaxieAskem3.png\",\"contentUrl\":\"https:\\/\\/mlpi0fxo3sth.i.optimole.com\\/cb:3obA.c61\\/w:760\\/h:480\\/q:mauto\\/f:best\\/https:\\/\\/askem.eu\\/wp-content\\/uploads\\/2020\\/10\\/logoGalaxieAskem3.png\",\"width\":760,\"height\":480,\"caption\":\"Askem\"},\"image\":{\"@id\":\"https:\\\/\\\/askem.eu\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/fb.me\\\/askem.eu\",\"https:\\\/\\\/linkedin.com\\\/company\\\/askem-eu\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/askem.eu\\\/#\\\/schema\\\/person\\\/8bbee74ab9a977d56bf4826662e9d2e9\",\"name\":\"askemadmin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a202f744ee3a4b6fdbe2ceb57fd84c72559337791a276662270d8d2fb7842e3f?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a202f744ee3a4b6fdbe2ceb57fd84c72559337791a276662270d8d2fb7842e3f?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a202f744ee3a4b6fdbe2ceb57fd84c72559337791a276662270d8d2fb7842e3f?s=96&d=mm&r=g\",\"caption\":\"askemadmin\"},\"sameAs\":[\"https:\\\/\\\/askem.eu\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"LLMLingua : compresser ses prompts - askem","description":"ASKEM BUREAU D'\u00c9TUDES ET DE FORMATION NUM\u00c9RIQUE. Nous vous assistons dans la transformation num\u00e9rique de vos outils, services et organisations tout en pla\u00e7ant l\u2019humain au c\u0153ur de notre d\u00e9marche d\u2019accompagnement.","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:\/\/askem.eu\/en\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/","og_locale":"en_US","og_type":"article","og_title":"LLMLingua : compresser ses prompts - askem","og_description":"ASKEM BUREAU D'\u00c9TUDES ET DE FORMATION NUM\u00c9RIQUE. Nous vous assistons dans la transformation num\u00e9rique de vos outils, services et organisations tout en pla\u00e7ant l\u2019humain au c\u0153ur de notre d\u00e9marche d\u2019accompagnement.","og_url":"https:\/\/askem.eu\/en\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/","og_site_name":"askem","article_publisher":"https:\/\/fb.me\/askem.eu","article_published_time":"2026-05-20T07:55:08+00:00","article_modified_time":"2026-05-20T07:55:12+00:00","og_image":[{"width":1600,"height":900,"url":"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:auto\/h:auto\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2026\/05\/sujet-askem-2026-05-11.png","type":"image\/png"}],"author":"askemadmin","twitter_card":"summary_large_image","twitter_misc":{"Written by":"askemadmin","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/askem.eu\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/#article","isPartOf":{"@id":"https:\/\/askem.eu\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/"},"author":{"name":"askemadmin","@id":"https:\/\/askem.eu\/#\/schema\/person\/8bbee74ab9a977d56bf4826662e9d2e9"},"headline":"LLMLingua : compresser ses prompts","datePublished":"2026-05-20T07:55:08+00:00","dateModified":"2026-05-20T07:55:12+00:00","mainEntityOfPage":{"@id":"https:\/\/askem.eu\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/"},"wordCount":569,"commentCount":0,"publisher":{"@id":"https:\/\/askem.eu\/#organization"},"image":{"@id":"https:\/\/askem.eu\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/#primaryimage"},"thumbnailUrl":"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:auto\/h:auto\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2026\/05\/sujet-askem-2026-05-11.png","articleSection":["AI"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/askem.eu\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/askem.eu\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/","url":"https:\/\/askem.eu\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/","name":"LLMLingua : compresser ses prompts - askem","isPartOf":{"@id":"https:\/\/askem.eu\/#website"},"primaryImageOfPage":{"@id":"https:\/\/askem.eu\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/#primaryimage"},"image":{"@id":"https:\/\/askem.eu\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/#primaryimage"},"thumbnailUrl":"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:auto\/h:auto\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2026\/05\/sujet-askem-2026-05-11.png","datePublished":"2026-05-20T07:55:08+00:00","dateModified":"2026-05-20T07:55:12+00:00","description":"ASKEM BUREAU D'\u00c9TUDES ET DE FORMATION NUM\u00c9RIQUE. Nous vous assistons dans la transformation num\u00e9rique de vos outils, services et organisations tout en pla\u00e7ant l\u2019humain au c\u0153ur de notre d\u00e9marche d\u2019accompagnement.","breadcrumb":{"@id":"https:\/\/askem.eu\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/askem.eu\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/askem.eu\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/#primaryimage","url":"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:auto\/h:auto\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2026\/05\/sujet-askem-2026-05-11.png","contentUrl":"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:auto\/h:auto\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2026\/05\/sujet-askem-2026-05-11.png","width":1600,"height":900},{"@type":"BreadcrumbList","@id":"https:\/\/askem.eu\/2026\/05\/20\/llmlingua-compresser-ses-prompts\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Accueil","item":"https:\/\/askem.eu\/"},{"@type":"ListItem","position":2,"name":"LLMLingua : compresser ses prompts"}]},{"@type":"WebSite","@id":"https:\/\/askem.eu\/#website","url":"https:\/\/askem.eu\/","name":"askem","description":"","publisher":{"@id":"https:\/\/askem.eu\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/askem.eu\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/askem.eu\/#organization","name":"Askem","url":"https:\/\/askem.eu\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/askem.eu\/#\/schema\/logo\/image\/","url":"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:760\/h:480\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2020\/10\/logoGalaxieAskem3.png","contentUrl":"https:\/\/mlpi0fxo3sth.i.optimole.com\/cb:3obA.c61\/w:760\/h:480\/q:mauto\/f:best\/https:\/\/askem.eu\/wp-content\/uploads\/2020\/10\/logoGalaxieAskem3.png","width":760,"height":480,"caption":"Askem"},"image":{"@id":"https:\/\/askem.eu\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/fb.me\/askem.eu","https:\/\/linkedin.com\/company\/askem-eu"]},{"@type":"Person","@id":"https:\/\/askem.eu\/#\/schema\/person\/8bbee74ab9a977d56bf4826662e9d2e9","name":"askemadmin","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/a202f744ee3a4b6fdbe2ceb57fd84c72559337791a276662270d8d2fb7842e3f?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/a202f744ee3a4b6fdbe2ceb57fd84c72559337791a276662270d8d2fb7842e3f?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a202f744ee3a4b6fdbe2ceb57fd84c72559337791a276662270d8d2fb7842e3f?s=96&d=mm&r=g","caption":"askemadmin"},"sameAs":["https:\/\/askem.eu"]}]}},"_links":{"self":[{"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/posts\/2340","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/comments?post=2340"}],"version-history":[{"count":1,"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/posts\/2340\/revisions"}],"predecessor-version":[{"id":2342,"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/posts\/2340\/revisions\/2342"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/media\/2341"}],"wp:attachment":[{"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/media?parent=2340"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/categories?post=2340"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/askem.eu\/en\/wp-json\/wp\/v2\/tags?post=2340"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}