June 2026
Intermediate
448 pages
14h 58m
French
Content preview from ML et IA générative dans le lac de données (French Edition)
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Chapitre 10. Le protocole de contexte de modèle
Cet ouvrage a été traduit à l'aide de l'IA. Tes réactions et tes commentaires sont les bienvenus : translation-feedback@oreilly.com
Les LLMs sont passés de simples générateurs de texte autonomes à des composants logiciels capables d'analyser des données, d'appeler des outils et de s'intégrer dans des workflows métier. Ce qui manquait, c'était une méthode standard permettant aux applications d'IA de connecter ces modèles à des systèmes externes.
Dans la plupart des déploiements réels, chaque combinaison de modèle, d’application hôte et de système d’entreprise a nécessité son propre adaptateur personnalisé. Il en résulte un problème d’intégration M×N : des connecteurs fragiles, des efforts de mise en œuvre redondants et des contrôles de sécurité incohérents. Lancé par Anthropic le 25 novembre 2024, le protocole MCP (Model Context Protocol) a été conçu pour résoudre ce problème en tant que norme ouverte permettant de connecter les systèmes d’IA aux sources de données et aux outils.
Le MCP offre aux applications d’IA un moyen commun de découvrir les capacités disponibles, de récupérer le contexte et d’invoquer des actions sur des systèmes locaux et distants. Dans un environnement Lakehouse, cette standardisation est particulièrement précieuse. Un hôte d’IA ne devrait pas avoir besoin d’une intégration personnalisée pour chaque plateforme de données, catalogue, entrepôt, moteur de workflow ou application en aval auquel il pourrait devoir ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.