Development100% OFF

IA Full-Stack avec Ollama : Llama, Deepseek, Mistral, QwQ

Udemy Instructor

0(11.9K students)

Self-paced

All Levels

About this course

IA Full-Stack avec Ollama : Llama, DeepSeek, Mistral, QwQ, Phi-2, MedLlama2, Granite3. 2 est la formation pratique ultime pour apprendre à développer et déployer des applications d’IA concrètes en utilisant les derniers modèles open-source. Que vous soyez débutant curieux de l’intelligence artificielle ou développeur expérimenté, ce cours vous propose des projets concrets pour intégrer des modèles de langage (LLMs) dans des applications web, des outils d’automatisation et des solutions avancées pilotées par l’IA.

Tout au long du cours, vous apprendrez à installer, configurer et utiliser Ollama pour exécuter localement des modèles puissants sans dépendre des APIs cloud coûteuses. Vous travaillerez avec LLaMA 3, DeepSeek, Mistral, Mixtral, QwQ, Phi-2, MedLlama2, Granite3. 2 et CodeLlama, en acquérant de l'expérience dans le traitement du langage naturel (NLP), la génération de texte, la complétion de code, le débogage, l’analyse de documents, l’analyse de sentiments et l’automatisation par IA.

Le cours est riche en projets pratiques. Vous développerez un résumé intelligent de l’actualité, un outil de relecture assisté par IA, un chatbot de support client, ainsi qu’un assistant intelligent pour automatiser les tâches métiers. Chaque projet vous offre une expérience complète avec FastAPI, Python, Ollama et les REST APIs, pour maîtriser le développement full-stack en IA.

Vous apprendrez également à récupérer et traiter des données en temps réel via des APIs, ce qui est idéal pour créer des applications IA qui analysent des flux d’information actuels. Vous réaliserez un résuméur d’actualités en temps réel, un analyseur de rapports financiers, et un outil d’analyse automatisée de candidatures. À la fin du cours, vous aurez construit plusieurs projets d’IA couvrant le développement full-stack, le traitement de texte, la compréhension du langage naturel, les chatbots, l’automatisation par IA et les applications à base de LLMs.

Vous serez prêt à déployer des modèles IA dans des applications en production et à exploiter les technologies IA les plus avancées pour créer des solutions intelligentes. Ce cours s’adresse aux développeurs, data scientists, entrepreneurs, chercheurs et passionnés d’IA. Vous apprendrez à concevoir des applications web avec IA, intégrer des modèles NLP, et automatiser des tâches à l’aide d’outils pilotés par l’IA.

Si vous êtes prêt à faire passer vos compétences en IA au niveau supérieur, ce cours est fait pour vous !

Skills you'll gain

Data ScienceFrench

Available Coupons

Course Information

Level: All Levels

Suitable for learners at this level

Duration: Self-paced

Total course content

Instructor: Udemy Instructor

Expert course creator

This course includes:

📹Video lectures
📄Downloadable resources
📱Mobile & desktop access
🎓Certificate of completion
♾️Lifetime access

$0$85.99

Save $85.99 today!

Enroll Now - Free

Redirects to Udemy • Limited free enrollments

Share this course

https://freecourse.io/courses/ia-full-stack-avec-ollama-llama-deepseek-mistral-qwq

This course contains the use of artificial intelligence.Building an AI agent that works for five minutes is easy. Building one that works for five hours, unattended, is a different problem.Leave an agent running overnight and it breaks in predictable ways. Its context fills up and it starts mixing up customers. The server restarts at 2 AM and nobody knows whether that refund went through. It gets stuck in a loop and burns money until morning. It marks work as "done" when nothing was done. And sometimes it takes an action nobody can undo.This course teaches the design patterns that prevent each of these failures. They are the same patterns behind today's coding agents, background agents and durable workflow engines, explained clearly enough that you can apply them in any stack.One story, one night, one agentThe whole course follows Nightshift, an agent working the night shift at Pebblecart, a small online store with 600 support tickets left over from Black Friday. Nightshift has real tools: it looks up orders, reads the refund policy, emails customers and issues refunds.The first night goes badly. Section by section, you give Nightshift the patterns it needs, and in the last lesson it finishes a full night: tickets resolved, risky refunds waiting for approval, hard cases handed to humans, and a sensible bill.The 5 ways long-running agents break, and what you'll learn to fix themForgetting: compaction, clearing tool results, just-in-time retrieval, sub-agents, progress files, structured work lists, goal anchoring.Dying: checkpoints, event logs and replay, idempotent tools, workflow engines, suspend and resume with webhooks, work queues with leases.Getting stuck: retries with backoff, loop detection, token and money budgets, stop conditions, circuit breakers and fallback models.Lying: verification with facts instead of the agent's word, evaluator–optimizer reviewers, overnight reconciliation.Acting recklessly: approval gates, async human approval, escalation, and defending against prompt injection in customer emails.You'll also learn when multiple agents beat one, how to hand off work between agents, how to trace an 8-hour run, and how to cut the cost of a night's work.What makes this course differentPatterns, not a framework. Everything applies whether you use the Claude Agent SDK, LangGraph, Cloudflare Agents, Temporal, Inngest or your own loop. Each lesson ends with where the pattern already exists in popular platforms.Short, focused lessons. Every video is 3 to 6 minutes and teaches one pattern.Animated diagrams instead of slides. Every idea is drawn and animated step by step, so you can see the mechanism, not just hear about it.Pseudocode code cards. Each pattern ends with a short pseudocode card you can translate into any language. The harness grows lesson by lesson, with new lines highlighted.No setup, no repo to maintain. Watch on your phone, on the train, or between meetings.Also includedA scenario quiz at the end of every section, based on real incidents from Nightshift's nightsA final assignment: design the harness for your own agent on one pagePattern cards (PDF): one card per pattern with the problem, diagram, pseudocode and trade-offsPattern map (PDF): every pattern on one page, organized by failure modeOvernight checklist (PDF): what to check before you let an agent run unattendedBy the end of this course, you'll be able to look at any agent, predict how it will fail on a long run, and choose the patterns that keep it on track.Enroll now and give your agent a night shift it can survive.This course is independent and is not affiliated with or endorsed by any of the companies or products mentioned. Pebblecart and Nightshift are fictional names created for this course.

NumPy, SciPy, Matplotlib & Pandas A-Z: Machine Learning

Udemy Instructor

Are you eager to dive into the core libraries that form the backbone of data manipulation, scientific computing, visualization, and machine learning in Python? Welcome to "NumPy, SciPy, Matplotlib & Pandas A-Z: Machine Learning," your comprehensive guide to mastering these essential libraries for data science and machine learning.NumPy, SciPy, Matplotlib, and Pandas are the cornerstone libraries in Python for performing data analysis, scientific computing, and visualizing data. Whether you're a data enthusiast, aspiring data scientist, or machine learning practitioner, this course will equip you with the skills needed to harness the full potential of these libraries for your data-driven projects.Key Learning Objectives:Learn NumPy's fundamentals, including arrays, array operations, and broadcasting for efficient numerical computations.Explore SciPy's capabilities for mathematics, statistics, optimization, and more, enhancing your scientific computing skills.Master Pandas for data manipulation, data analysis, and transforming datasets to extract valuable insights.Dive into Matplotlib to create stunning visualizations, including line plots, scatter plots, histograms, and more to effectively communicate data.Understand how these libraries integrate with machine learning algorithms to preprocess, analyze, and visualize data for predictive modeling.Apply these libraries to real-world projects, from data cleaning and exploration to building machine learning models.Learn techniques to optimize code and make efficient use of these libraries for large datasets and complex computations.Gain insights into best practices, tips, and tricks for maximizing your productivity while working with these libraries.Why Choose This Course?This course offers a deep dive into NumPy, SciPy, Matplotlib, and Pandas, ensuring you grasp their core functionalities for data science and machine learning.Practice your skills with coding exercises, projects, and practical examples that simulate real-world data analysis scenarios.Benefit from the guidance of experienced instructors who are passionate about data science and eager to share their knowledge.Enroll once and enjoy lifetime access to the course materials, enabling you to learn at your own pace and revisit concepts whenever necessary.Mastery of these libraries is crucial for anyone pursuing a career in data science, machine learning, or scientific computing.Unlock the power of NumPy, SciPy, Matplotlib, and Pandas for data analysis and machine learning. Enroll today in "NumPy, SciPy, Matplotlib & Pandas A-Z: Machine Learning" and elevate your data science skills. Don't miss this opportunity to become proficient in these fundamental libraries and enhance your data-driven projects!

AI Networking Certified Professional NCP-AIN [Exams 2026]

Paweł Krakowiak

Practice questions to prepare for AI Networking NCP-AI!Prepare for the AI Networking certification with this comprehensive mock exam course. Designed for networking professionals, AI infrastructure engineers, and data center specialists, this course equips you with the knowledge and confidence to pass the NCP-AI certification exam. With six expertly crafted mock exams, you will gain hands-on experience in AI-driven networking, ensuring you are ready to tackle the real-world challenges of high-performance AI workloads.Each mock exam is structured to mirror the official NCP-AI certification, covering essential topics such as high-speed networking architectures, RDMA over Converged Ethernet (RoCE), GPUDirect Storage, InfiniBand and Ethernet network design for AI clusters, congestion control, performance tuning, and AI-driven networking solutions. The questions are designed to assess both theoretical knowledge and practical applications, simulating real-world scenarios encountered in AI and HPC environments.Every question includes a detailed explanation of the correct answer, providing valuable insights into core concepts, troubleshooting strategies, and best practices for optimizing AI workloads. These explanations help reinforce your understanding, clarify complex topics, and bridge knowledge gaps.Whether you're an AI infrastructure expert or a networking professional looking to expand your expertise, this course will sharpen your skills and boost your confidence. Strengthen your knowledge, refine your test-taking strategies, and take a step closer to becoming a Certified Professional in AI Networking!Can I retake the practice tests?Yes, you are welcome to attempt each practice test as many times as you like. After completing a test, you will receive your final score. Each time you retake the test, the questions and answer choices will be shuffled to provide a fresh experience.Is there a time limit for the practice tests?Yes, each test has a time limit.What score do I need to pass?To successfully pass each practice test, you need to achieve a score of at least 70%.Are explanations provided for the questions?Yes, detailed explanations are available for every question to support your learning.Can I review my answers after the test?Absolutely! You will have the opportunity to review all your submitted answers and see which ones were correct or incorrect.Are the questions updated frequently?Yes, the questions are regularly updated to ensure the most relevant and up-to-date learning experience.Additional Note:To maximize your preparation, we highly recommend taking the practice exams multiple times until you consistently score 90% or higher. Don't hesitate—start your preparation today. Wishing you the best of luck!

3.0•1.7K•Self-paced

FREE$91.99

Enroll

IA Full-Stack avec Ollama : Llama, Deepseek, Mistral, QwQ

About this course

Skills you'll gain

Available Coupons

Course Information

This course includes:

Share this course

You May Also Like

Long-Running AI Agents: Patterns for Agents That Run Hours

NumPy, SciPy, Matplotlib & Pandas A-Z: Machine Learning

AI Networking Certified Professional NCP-AIN [Exams 2026]

IA Full-Stack avec Ollama : Llama, Deepseek, Mistral, QwQ

About this course

Skills you'll gain

Available Coupons

Course Information

This course includes:

Share this course

You May Also Like

Long-Running AI Agents: Patterns for Agents That Run Hours

NumPy, SciPy, Matplotlib & Pandas A-Z: Machine Learning

AI Networking Certified Professional NCP-AIN [Exams 2026]