May 2026
Intermediate
358 pages
11h 21m
Italian
Content preview from RAG pratico per la produzione (Italian 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.
Capitolo 9. RAGpotenziato dalla conoscenza
Questo lavoro è stato tradotto utilizzando l'AI. Siamo lieti di ricevere il tuo feedback e i tuoi commenti: translation-feedback@oreilly.com
Il RAG ha cambiato radicalmente il modo in cui affrontiamo il recupero delle informazioni. Siamo passati dal rigido mondo della corrispondenza delle parole chiave al dominio più fluido e intuitivo della ricerca semantica. Questo cambiamento ci permette di trovare documenti in base al loro significato concettuale, non solo alle parole specifiche che contengono. Nonostante i suoi punti di forza, i sistemi RAG basati esclusivamente sulla ricerca vettoriale o ibrida possono avere difficoltà con le query che richiedono una comprensione più precisa delle relazioni tra le entità. Questo problema nasce perché la ricerca vettoriale si basa su probabilità e somiglianze, non su fatti deterministici. Ecco alcuni esempi:
- Fatti limitati nel tempo
-
La ricerca semantica basata sull'e non è adatta a rispondere a domande che dipendono da un momento specifico nel tempo, perché gli embedding tendono a confondere le informazioni del passato con quelle del presente.1
-
Ad esempio, una query del tipo "Chi era l'amministratore delegato di Twitter nell'ottobre 2022?" potrebbe restituire frammenti che menzionano Elon Musk, Jack Dorsey o Parag Agrawal, a seconda del testo recuperato, senza alcun chiaro allineamento con la data richiesta. Questo spesso porta a una risposta errata o al fatto che l'LLM cerchi di fornire tutte ...
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.