{"id":422,"date":"2026-03-02T13:13:02","date_gmt":"2026-03-02T13:13:02","guid":{"rendered":"https:\/\/pythonia.fr\/?page_id=422"},"modified":"2026-03-20T10:06:45","modified_gmt":"2026-03-20T10:06:45","slug":"elementor-422","status":"publish","type":"page","link":"https:\/\/pythonia.fr\/index.php\/en\/elementor-422\/","title":{"rendered":"Elementor #422"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-page\" data-elementor-id=\"422\" class=\"elementor elementor-422\">\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\">AI Agents with Python<br><\/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\">\n  <!-- Left column : Content -->\n  <div style=\"flex:2;min-width:300px\">\n    <h3 style=\"color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">\n      Objectives\n    <\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>\n        Implement processing chains and conversational memory using <b>LangChain<\/b>\n      <\/li>\n      <li>\n        Create custom tools capable of executing business actions\n      <\/li>\n      <li>\n        Orchestrate complex workflows using <b>LangGraph<\/b>\n      <\/li>\n      <li>\n        Coordinate <b>multi-agent systems<\/b>\n      <\/li>\n    <\/ul>\n  <\/div>\n  <!-- Right column : Links and buttons -->\n  <div style=\"flex:1;min-width:200px;background:#0B1D33;padding:25px;border-radius:12px;height:fit-content\">\n    <a href=\"http:\/\/pythonia.fr\/wp-content\/uploads\/2026\/02\/Agents_IA_Python.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 Program (PDF)\n    <\/a>\n    <a href=\"#\" id=\"btn-dates-en\" style=\"display:block;color:#FFFFFF;font-size:15px;text-decoration:none;padding:12px 0;border-bottom:1px solid #1a3a5c\">\n      \ud83d\udcc5 View dates\n    <\/a>\n    <button id=\"btn-contact-en\" 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 Request information\n    <\/button>\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  <!-- Left column : Content -->\n  <div style=\"flex:2;min-width:300px\"><div style=\"display:flex;gap:40px;flex-wrap:wrap\">\n\n  <!-- Left column : Content -->\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\">Target Audience<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>Intermediate to advanced Python developers<\/li>\n      <li>Professionals who want to design autonomous AI agents<\/li>\n      <li>Developers who want to automate complex workflows using LangChain, LangGraph and multi-agent systems<\/li>\n    <\/ul>\n\n    <h3 style=\"font-size:24px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">Learning Objectives<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>Explain the architecture of an AI agent (perception\u2013decision\u2013action loop) and differentiate it from a chatbot<\/li>\n      <li>Implement processing chains and conversational memory using LangChain<\/li>\n      <li>Design a complete RAG system (embeddings, vector database, semantic search)<\/li>\n      <li>Create custom tools and ReAct agents capable of executing business actions<\/li>\n      <li>Orchestrate complex workflows using LangGraph (graphs, branching, human-in-the-loop)<\/li>\n      <li>Coordinate specialized multi-agent systems using CrewAI<\/li>\n      <li>Deploy a complete automated workflow addressing a real business need in production<\/li>\n    <\/ul>\n\n    <h3 style=\"font-size:24px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">Prerequisites<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>Intermediate Python knowledge (OOP, modules, REST APIs)<\/li>\n      <li>Basic knowledge of LLM APIs (prompt engineering, API calls)<\/li>\n      <li>Completion of the Python &amp; AI (API) training or equivalent level<\/li>\n      <li>A computer with Python 3.x and internet access<\/li>\n    <\/ul>\n\n    <h3 style=\"font-size:24px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">Teaching Methods<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>Combination of theory (25%) and practice (75%)<\/li>\n      <li>Interactive lectures and live demonstrations of agent architectures<\/li>\n      <li>Individual and team practical exercises using LangChain, LangGraph, CrewAI and real APIs<\/li>\n      <li>Active learning: iterative design, collaborative debugging, group architecture reviews<\/li>\n      <li>Digital course materials and exercise files (permanent access)<\/li>\n    <\/ul>\n\n    <h3 style=\"font-size:24px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">\n      Target Certification: RS6962 \u2013 Programming and Automating Tasks with Python (TOSA) \u2013 CPF eligible\n    <\/h3>\n\n    <h1 style=\"font-size:24px;color:#FFFFFF;font-weight:bold;margin-top:40px;margin-bottom:20px\">Detailed Program<\/h1>\n\n    <h3 style=\"font-size:16px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">DAY 1 \u2014 Introduction to AI Agents and LangChain<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>AI agent concept: difference between a chatbot and an autonomous agent<\/li>\n      <li>Perception\u2013decision\u2013action loop: agent architecture<\/li>\n      <li>Introduction to LangChain: philosophy, components, installation<\/li>\n      <li>Language models in LangChain: configuration and parameters<\/li>\n      <li>Prompt templates: creation, variables, composition<\/li>\n      <li>Chains: operation pipelines, LLMChain, SequentialChain<\/li>\n      <li>Conversational memory: memory types and persistence<\/li>\n    <\/ul>\n    <p style=\"font-size:14px;color:#FFFFFF;margin-left:20px;margin-top:15px\">\n    <strong>\u25a0 Practical exercises:<\/strong><br>\n    \u2192 Lab 1: Configure LangChain with different LLMs<br>\n    \u2192 Lab 2: Build chains for multi-step text processing<br>\n    \u2192 Lab 3: Chatbot with persistent conversational memory\n    <\/p>\n\n    <h3 style=\"font-size:16px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">DAY 2 \u2014 RAG and Vector Databases<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>RAG (Retrieval-Augmented Generation): principles and architecture<\/li>\n      <li>Embeddings: vector representation of text and models<\/li>\n      <li>Document chunking strategies and overlapping<\/li>\n      <li>Vector databases: ChromaDB, Pinecone, Weaviate \u2014 comparison<\/li>\n      <li>Document indexing: PDF, Word, web pages<\/li>\n      <li>Semantic search: cosine similarity, top-k retrieval<\/li>\n      <li>Integrating RAG in LangChain: RetrievalQA<\/li>\n    <\/ul>\n    <p style=\"font-size:14px;color:#FFFFFF;margin-left:20px;margin-top:15px\">\n    <strong>\u25a0 Practical exercises:<\/strong><br>\n    \u2192 Lab 1: Build a ChromaDB vector database from documents<br>\n    \u2192 Lab 2: Semantic search system on technical documentation<br>\n    \u2192 Lab 3: RAG chatbot capable of answering from a knowledge base\n    <\/p>\n\n    <h3 style=\"font-size:16px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">DAY 3 \u2014 Function Calling and Tools<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>Function calling: principles, function definition, JSON schema<\/li>\n      <li>Tools in LangChain: creation, documentation, binding<\/li>\n      <li>Built-in tools: web search, calculator, Wikipedia<\/li>\n      <li>Custom tools for accessing business APIs<\/li>\n      <li>ReAct agents: reasoning and action loop<\/li>\n      <li>Error handling for tools and fallback strategies<\/li>\n      <li>Security: validating calls and limiting permissions<\/li>\n    <\/ul>\n    <p style=\"font-size:14px;color:#FFFFFF;margin-left:20px;margin-top:15px\">\n    <strong>\u25a0 Practical exercises:<\/strong><br>\n    \u2192 Lab 1: Agent using calculation and web search tools<br>\n    \u2192 Lab 2: Create custom tools (weather, database)<br>\n    \u2192 Lab 3: Assistant capable of executing business actions (CRM, tickets)\n    <\/p>\n\n    <h3 style=\"font-size:16px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">DAY 4 \u2014 LangGraph and Complex Workflows<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>LangGraph: execution graphs, nodes and edges<\/li>\n      <li>States and transitions: managing data flow<\/li>\n      <li>Conditional branching: dynamic routing<\/li>\n      <li>Loops and iterations in graphs<\/li>\n      <li>State persistence: checkpoints and execution recovery<\/li>\n      <li>Human-in-the-loop: human validation within workflows<\/li>\n      <li>Graph debugging and visualization<\/li>\n    <\/ul>\n    <p style=\"font-size:14px;color:#FFFFFF;margin-left:20px;margin-top:15px\">\n    <strong>\u25a0 Practical exercises:<\/strong><br>\n    \u2192 Lab 1: Document processing workflow with validation<br>\n    \u2192 Lab 2: Customer support agent with conditional escalation<br>\n    \u2192 Lab 3: Content generation pipeline with iterative review\n    <\/p>\n\n    <h3 style=\"font-size:16px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">DAY 5 \u2014 Multi-Agent Systems and Final Project<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>Multi-agent architecture: coordination and communication<\/li>\n      <li>CrewAI: defining roles, tasks and teams<\/li>\n      <li>Agent specialization: research, analysis, writing<\/li>\n      <li>Orchestration: sequential vs parallel execution, dependencies<\/li>\n      <li>Conflict management and consensus between agents<\/li>\n      <li>Monitoring and observability of multi-agent systems<\/li>\n    <\/ul>\n    <p style=\"font-size:14px;color:#FFFFFF;margin-left:20px;margin-top:15px\">\n    <strong>\u25a0 Practical exercises:<\/strong><br>\n    \u2192 Lab 1: CrewAI team for news monitoring and summarization<br>\n    \u2192 Lab 2: Multi-agent report writing system<br>\n    \u2192 Lab 3 (Final project): Complete automated workflow solving a real business problem\n    <\/p>\n\n    <h3 style=\"font-size:16px;color:#FFFFFF;font-weight:bold;margin-top:25px;margin-bottom:10px\">Assessment<\/h3>\n    <ul style=\"font-size:14px;color:#FFFFFF;line-height:1.8;margin-left:20px\">\n      <li>Initial assessment test at the beginning of the training<\/li>\n      <li>Formative assessments: corrected practical exercises, architecture reviews, collaborative debugging, intermediate quizzes<\/li>\n      <li>Final 40-question multiple-choice test (Day 5) \u2014 passing score: 60%<\/li>\n      <li>Certificate of completion issued<\/li>\n    <\/ul>\n\n  <\/div>\n<\/div>\n   \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>AI Agents with Python Objectives Implement processing chains and conversational memory using LangChain Create custom tools capable of executing business [&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-422","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/pythonia.fr\/index.php\/wp-json\/wp\/v2\/pages\/422","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=422"}],"version-history":[{"count":19,"href":"https:\/\/pythonia.fr\/index.php\/wp-json\/wp\/v2\/pages\/422\/revisions"}],"predecessor-version":[{"id":771,"href":"https:\/\/pythonia.fr\/index.php\/wp-json\/wp\/v2\/pages\/422\/revisions\/771"}],"wp:attachment":[{"href":"https:\/\/pythonia.fr\/index.php\/wp-json\/wp\/v2\/media?parent=422"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}