April 2026
Intermediate
292 pages
7h 12m
French
Content preview from Bases de données vectorielles (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 8. Créer un système complet de recherche conversationnelle et RAG
Cet ouvrage a été traduit à l'aide de l'IA. Tes réactions et tes commentaires sont les bienvenus : translation-feedback@oreilly.com
À l'ère du numérique, nous générons d'énormes quantités de données conversationnelles via les assistants IA, les applications de chat et les plateformes collaboratives. Ces conversations contiennent souvent des informations précieuses, des solutions à des problèmes, des idées créatives et des connaissances acquises qui deviennent de plus en plus difficiles à retrouver à mesure que leur volume augmente. Comment retrouver efficacement cette discussion spécifique sur les décorateurs Python datant d'il y a trois mois, ou te rappeler les conseils d'architecture donnés pour ton application web ?
Dans les chapitres précédents, nous avons exploré la manière dont les bases de données vectorielles traitent les articles de recherche statiques. Cependant, nos vies numériques personnelles sont désordonnées et conversationnelles. Si tu utilises des LLMs comme Claude ou ChatGPT pour ton travail, tu as probablement des milliers de messages contenant des informations « perdues ». Ce chapitre passe de la recherche dans les données publiques à la création d’un « deuxième cerveau » pour ton propre historique de chat.
Ce système gère les connaissances privées et personnelles en tenant compte de la nuance suivante : les conversations ont des caractéristiques uniques :
- Dépendances contextuelles
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.