{"id":147,"date":"2026-02-06T08:28:20","date_gmt":"2026-02-06T08:28:20","guid":{"rendered":"https:\/\/pythonia.fr\/?page_id=147"},"modified":"2026-03-18T12:16:56","modified_gmt":"2026-03-18T12:16:56","slug":"agents-ia-avec-python","status":"publish","type":"page","link":"https:\/\/pythonia.fr\/index.php\/agents-ia-avec-python\/","title":{"rendered":"Agents IA avec Python"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-page\" data-elementor-id=\"147\" class=\"elementor elementor-147\">\n\t\t\t\t<div class=\"elementor-element elementor-element-0ee8abf e-grid e-con-boxed e-con e-parent\" data-id=\"0ee8abf\" data-element_type=\"container\" data-e-type=\"container\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-9dcad6e elementor-widget elementor-widget-heading\" data-id=\"9dcad6e\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\">Agents IA avec Python<\/h2>\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-c9b24f6 e-grid e-con-boxed e-con e-parent\" data-id=\"c9b24f6\" data-element_type=\"container\" data-e-type=\"container\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-7188aa2 elementor-widget elementor-widget-heading\" data-id=\"7188aa2\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\"><div style=\"display:flex;gap:40px;flex-wrap:wrap;font-family:sans-serif\">\n\n  <!-- Colonne gauche : Objectifs -->\n  <div style=\"flex:2;min-width:300px\">\n    <h3 style=\"color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px;font-size:16px\">\n      Objectifs :\n    <\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:2;margin-left:20px\">\n      <li>Impl\u00e9menter des cha\u00eenes de traitement et une m\u00e9moire conversationnelle avec LangChain<\/li>\n      <li>Cr\u00e9er des outils personnalis\u00e9s et capables d'ex\u00e9cuter des actions m\u00e9tier<\/li>\n      <li>Orchestrer des workflows complexes avec LangGraph<\/li>\n      <li>Coordonner des syst\u00e8mes multi-agents<\/li>\n    <\/ul>\n  <\/div>\n\n  <!-- Colonne droite : Tarif + liens -->\n  <div style=\"flex:1;min-width:200px;background:#0B1D33;padding:25px;border-radius:12px;height:fit-content\">\n\n    <div style=\"padding:12px 0;border-bottom:1px solid #1a3a5c\">\n      <span style=\"color:#8899AA;font-size:12px;text-transform:uppercase;letter-spacing:0.5px\">Tarif inter \/ participant<\/span>\n      <div style=\"color:#FFFFFF;font-size:22px;font-weight:bold;margin-top:4px\">\n        2 500 \u20ac <span style=\"font-size:13px;font-weight:normal;color:#8899AA\">HT<\/span>\n      <\/div>\n    <\/div>\n\n    <a href=\"http:\/\/pythonia.fr\/wp-content\/uploads\/2026\/03\/Programme_AgentsIA_Pythonia.pdf\" target=\"_blank\" style=\"display:block;color:#FFFFFF;font-size:15px;text-decoration:none;padding:12px 0;border-bottom:1px solid #1a3a5c\">\n      \ud83d\udcc4 Programme (PDF)\n    <\/a>\n\n    <a href=\"#\" id=\"btn-dates\" style=\"display:block;color:#FFFFFF;font-size:15px;text-decoration:none;padding:12px 0;border-bottom:1px solid #1a3a5c\">\n      \ud83d\udcc5 Voir les dates\n    <\/a>\n\n    <button id=\"btn-contact\" style=\"display:block;width:100%;margin-top:20px;padding:15px 20px;background:#5DADE2;color:#FFFFFF;font-size:15px;font-weight:bold;border:none;border-radius:8px;cursor:pointer\">\n      \u2709\ufe0f Demande d'information\n    <\/button>\n\n  <\/div>\n<\/div><\/h2>\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t<div class=\"elementor-element elementor-element-9f88d07 e-grid e-con-boxed e-con e-parent\" data-id=\"9f88d07\" data-element_type=\"container\" data-e-type=\"container\" data-settings=\"{&quot;background_background&quot;:&quot;classic&quot;}\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-81fc3cb elementor-widget elementor-widget-heading\" data-id=\"81fc3cb\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"heading.default\">\n\t\t\t\t\t<h2 class=\"elementor-heading-title elementor-size-default\"><div style=\"display:flex;gap:40px;flex-wrap:wrap\">\n\n  <!-- Colonne gauche : Contenu -->\n  <div style=\"flex:2;min-width:300px\">\n\n    <h3 style=\"font-size:24px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">Public vis\u00e9<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>D\u00e9veloppeurs Python de niveau interm\u00e9diaire \u00e0 avanc\u00e9<\/li>\n      <li>Professionnels souhaitant concevoir des agents IA autonomes<\/li>\n      <li>D\u00e9veloppeurs souhaitant automatiser des workflows complexes avec LangChain, LangGraph et les syst\u00e8mes multi-agents<\/li>\n    <\/ul>\n\n    <h3 style=\"font-size:24px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">Objectifs p\u00e9dagogiques<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>Expliquer l'architecture d'un agent IA (boucle perception-d\u00e9cision-action) et le diff\u00e9rencier d'un chatbot<\/li>\n      <li>Impl\u00e9menter des cha\u00eenes de traitement et une m\u00e9moire conversationnelle avec LangChain<\/li>\n      <li>Concevoir un syst\u00e8me RAG complet (embeddings, base vectorielle, recherche s\u00e9mantique)<\/li>\n      <li>Cr\u00e9er des outils personnalis\u00e9s et des agents ReAct capables d'ex\u00e9cuter des actions m\u00e9tier<\/li>\n      <li>Orchestrer des workflows complexes avec LangGraph (graphes, branchements, human-in-the-loop)<\/li>\n      <li>Coordonner des syst\u00e8mes multi-agents sp\u00e9cialis\u00e9s avec CrewAI<\/li>\n      <li>D\u00e9ployer un workflow automatis\u00e9 complet r\u00e9pondant \u00e0 un besoin m\u00e9tier en production<\/li>\n    <\/ul>\n\n    <h3 style=\"font-size:24px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">Pr\u00e9requis<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>Ma\u00eetriser Python niveau interm\u00e9diaire (POO, modules, API REST)<\/li>\n      <li>Avoir des connaissances de base sur les API de LLM (prompt engineering, appels API)<\/li>\n      <li>Avoir suivi la formation Python &amp; IA (API) ou justifier d'un niveau \u00e9quivalent<\/li>\n      <li>Disposer d'un ordinateur avec Python 3.x et acc\u00e8s internet<\/li>\n    <\/ul>\n\n    <h3 style=\"font-size:24px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">M\u00e9thodes p\u00e9dagogiques<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>Alternance de th\u00e9orie (25%) et de pratique (75%)<\/li>\n      <li>Expos\u00e9s interactifs, d\u00e9monstrations d'architectures d'agents en direct<\/li>\n      <li>TP individuels et en \u00e9quipe avec LangChain, LangGraph, CrewAI, API r\u00e9elles<\/li>\n      <li>P\u00e9dagogie active : conception it\u00e9rative, d\u00e9bogage collaboratif, revue d'architecture en groupe<\/li>\n      <li>Supports de cours num\u00e9riques et fichiers d'exercices (acc\u00e8s p\u00e9renne)<\/li>\n    <\/ul>\n\n    <h3 style=\"font-size:24px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">Certification vis\u00e9e : RS6962 \u2013 Programmer et automatiser des t\u00e2ches avec Python (Tosa) - Eligible CPF<\/h3>\n\n    <h1 style=\"font-size:24px;color:#FFFFFF;font-weight:bold;margin-top:40px;margin-bottom:20px\">Programme d\u00e9taill\u00e9<\/h1>\n\n    <h3 style=\"font-size:16px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">JOUR 1 \u2014 Introduction aux agents IA et LangChain<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>Concept d'agent IA : diff\u00e9rence entre chatbot et agent autonome<\/li>\n      <li>Boucle perception-d\u00e9cision-action : architecture d'un agent<\/li>\n      <li>Introduction \u00e0 LangChain : philosophie, composants, installation<\/li>\n      <li>Mod\u00e8les de langage dans LangChain : configuration, param\u00e8tres<\/li>\n      <li>Prompts templates : cr\u00e9ation, variables, composition<\/li>\n      <li>Chains : encha\u00eenement d'op\u00e9rations, LLMChain, SequentialChain<\/li>\n      <li>M\u00e9moire conversationnelle : types de m\u00e9moire, persistence<\/li>\n    <\/ul>\n    <p style=\"font-size:14px;color:#FFFFFF;margin-left:20px;margin-top:15px\"><strong>\u25a0 Travaux pratiques :<\/strong><br>\n    \u2192 TP1 : Configuration de LangChain avec diff\u00e9rents LLM<br>\n    \u2192 TP2 : Cr\u00e9ation de chains pour traitement de texte en plusieurs \u00e9tapes<br>\n    \u2192 TP3 : Chatbot avec m\u00e9moire conversationnelle persistante<\/p>\n\n    <h3 style=\"font-size:16px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">JOUR 2 \u2014 RAG et bases de donn\u00e9es vectorielles<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>RAG (Retrieval-Augmented Generation) : principe et architecture<\/li>\n      <li>Embeddings : repr\u00e9sentation vectorielle du texte, mod\u00e8les<\/li>\n      <li>Chunking de documents : strat\u00e9gies de d\u00e9coupage, overlapping<\/li>\n      <li>Bases vectorielles : ChromaDB, Pinecone, Weaviate \u2014 comparatif<\/li>\n      <li>Indexation de documents : PDF, Word, pages web<\/li>\n      <li>Recherche s\u00e9mantique : similarit\u00e9 cosinus, top-k retrieval<\/li>\n      <li>Int\u00e9gration RAG dans LangChain : RetrievalQA<\/li>\n    <\/ul>\n    <p style=\"font-size:14px;color:#FFFFFF;margin-left:20px;margin-top:15px\"><strong>\u25a0 Travaux pratiques :<\/strong><br>\n    \u2192 TP1 : Cr\u00e9ation d'une base vectorielle ChromaDB \u00e0 partir de documents<br>\n    \u2192 TP2 : Syst\u00e8me de recherche s\u00e9mantique sur documentation technique<br>\n    \u2192 TP3 : Chatbot RAG capable de r\u00e9pondre sur une base de connaissances<\/p>\n\n    <h3 style=\"font-size:16px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">JOUR 3 \u2014 Function Calling et outils<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>Function calling : principe, d\u00e9finition de fonctions, JSON Schema<\/li>\n      <li>Outils (Tools) dans LangChain : cr\u00e9ation, documentation, binding<\/li>\n      <li>Outils int\u00e9gr\u00e9s : recherche web, calculatrice, Wikipedia<\/li>\n      <li>Cr\u00e9ation d'outils personnalis\u00e9s pour acc\u00e8s \u00e0 des API m\u00e9tier<\/li>\n      <li>Agents ReAct : raisonnement et action, boucle d'ex\u00e9cution<\/li>\n      <li>Gestion des erreurs d'outils et fallback<\/li>\n      <li>S\u00e9curit\u00e9 : validation des appels, limitation des permissions<\/li>\n    <\/ul>\n    <p style=\"font-size:14px;color:#FFFFFF;margin-left:20px;margin-top:15px\"><strong>\u25a0 Travaux pratiques :<\/strong><br>\n    \u2192 TP1 : Agent avec outils de calcul et recherche web<br>\n    \u2192 TP2 : Cr\u00e9ation d'outils personnalis\u00e9s (m\u00e9t\u00e9o, base de donn\u00e9es)<br>\n    \u2192 TP3 : Assistant capable d'ex\u00e9cuter des actions m\u00e9tier (CRM, tickets)<\/p>\n\n    <h3 style=\"font-size:16px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">JOUR 4 \u2014 LangGraph et workflows complexes<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>LangGraph : graphes d'ex\u00e9cution, n\u0153uds et ar\u00eates<\/li>\n      <li>\u00c9tats et transitions : gestion du flux de donn\u00e9es<\/li>\n      <li>Branchements conditionnels : routage dynamique<\/li>\n      <li>Boucles et it\u00e9rations dans les graphes<\/li>\n      <li>Persistence de l'\u00e9tat : checkpoints, reprise d'ex\u00e9cution<\/li>\n      <li>Human-in-the-loop : validation humaine dans le workflow<\/li>\n      <li>Debugging et visualisation des graphes<\/li>\n    <\/ul>\n    <p style=\"font-size:14px;color:#FFFFFF;margin-left:20px;margin-top:15px\"><strong>\u25a0 Travaux pratiques :<\/strong><br>\n    \u2192 TP1 : Workflow de traitement de documents avec validation<br>\n    \u2192 TP2 : Agent de support client avec escalade conditionnelle<br>\n    \u2192 TP3 : Pipeline de g\u00e9n\u00e9ration de contenu avec r\u00e9vision it\u00e9rative<\/p>\n\n    <h3 style=\"font-size:16px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">JOUR 5 \u2014 Multi-agents et projet final<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>Architecture multi-agents : coordination, communication<\/li>\n      <li>CrewAI : d\u00e9finition de r\u00f4les, t\u00e2ches, \u00e9quipes<\/li>\n      <li>Sp\u00e9cialisation des agents : recherche, analyse, r\u00e9daction<\/li>\n      <li>Orchestration : s\u00e9quentiel vs parall\u00e8le, d\u00e9pendances<\/li>\n      <li>Gestion des conflits et consensus entre agents<\/li>\n      <li>Monitoring et observabilit\u00e9 des syst\u00e8mes multi-agents<\/li>\n    <\/ul>\n    <p style=\"font-size:14px;color:#FFFFFF;margin-left:20px;margin-top:15px\"><strong>\u25a0 Travaux pratiques :<\/strong><br>\n    \u2192 TP1 : \u00c9quipe CrewAI de veille et synth\u00e8se d'actualit\u00e9s<br>\n    \u2192 TP2 : Syst\u00e8me multi-agents de r\u00e9daction de rapports<br>\n    \u2192 TP3 (Projet final) : Workflow automatis\u00e9 complet r\u00e9pondant \u00e0 un besoin m\u00e9tier<\/p>\n\n    <h3 style=\"font-size:16px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">\u00c9valuation<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>Test de positionnement en d\u00e9but de formation<\/li>\n      <li>\u00c9valuations formatives : exercices pratiques corrig\u00e9s, revue d'architecture, d\u00e9bogage en groupe, QCM interm\u00e9diaires<\/li>\n      <li>QCM final de 40 questions (Jour 5) \u2014 crit\u00e8re de r\u00e9ussite : 60%<\/li>\n      <li>Attestation de fin de formation d\u00e9livr\u00e9e<\/li>\n      <li>Passage de la certification RS6962 \u2013 Tosa Python<\/li>\n    <\/ul>\n\n  <\/div>\n<\/div><\/h2>\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>Agents IA avec Python Objectifs : Impl\u00e9menter des cha\u00eenes de traitement et une m\u00e9moire conversationnelle avec LangChain Cr\u00e9er des outils [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"site-sidebar-layout":"no-sidebar","site-content-layout":"","ast-site-content-layout":"full-width-container","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"disabled","ast-breadcrumbs-content":"","ast-featured-img":"disabled","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"class_list":["post-147","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/pythonia.fr\/index.php\/wp-json\/wp\/v2\/pages\/147","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/pythonia.fr\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/pythonia.fr\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/pythonia.fr\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/pythonia.fr\/index.php\/wp-json\/wp\/v2\/comments?post=147"}],"version-history":[{"count":53,"href":"https:\/\/pythonia.fr\/index.php\/wp-json\/wp\/v2\/pages\/147\/revisions"}],"predecessor-version":[{"id":1061,"href":"https:\/\/pythonia.fr\/index.php\/wp-json\/wp\/v2\/pages\/147\/revisions\/1061"}],"wp:attachment":[{"href":"https:\/\/pythonia.fr\/index.php\/wp-json\/wp\/v2\/media?parent=147"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}