Skip to content

Details

Building a RAG app for a non-English audience? Fortunately, language models and embedding models is that they understand a wide range of languages. Unfortunately, they have a bias towards English, so you need to choose your approach carefully when deploying them in other languages.
In this session, we'll dive into tokenization, optimal data chunking strategies, and other best practices for internationalization.

Presented by Anthony Shaw, Python Cloud Advocate and Renee Noble, Regional Cloud advocate.

** Part of RAGHack, a free global hackathon to develop RAG applications. Join at https://aka.ms/raghack **

**📌 Check out the RAGHack 2024 series here! **

Pre-requisites:

  • Read the official rules and join the hack at https://aka.ms/raghack. No Purchase Necessary. Must be 18+ to enter. Contest ends 9/16/24.

  • Want more hands-on RAG training? Visit the Reactor series home page to see all the RAGHack 2024 sessions!

Sponsors

Microsoft Reactor YouTube

Microsoft Reactor YouTube

Watch past Microsoft Reactor events on-demand anytime

Microsoft Learn AI Hub

Microsoft Learn AI Hub

Learning hub for all things AI

Microsoft Copilot Hub

Microsoft Copilot Hub

Learning hub for all things Copilot

Microsoft Reactor LinkedIn

Microsoft Reactor LinkedIn

Follow Microsoft Reactor on LinkedIn

You may also like