Using RAG expansion to improve model speed and accuracy

Опубликовано 21 ноября 2024, 17:00

How Google Search serves pages → goo.gle/4fzNtOh
Small to big rag (GitHub) → goo.gle/3ZgpcY1
Vertex AI embeddings and task types → goo.gle/40WFlTt

Unlock the potential of document and query expansion, a powerful technique that enhances information retrieval in AI systems. Learn how this method addresses vocabulary mismatch, improves search relevance, and optimizes retrieval speed. Join Aja and Jason in this episode of Real Terms for AI as they explore practical examples and showcase how document and query expansion can significantly enhance AI applications.

Chapters:
0:00 - Intro
0:25 - What is RAG expansion?
1:50 - Addressing latency in AI apps
2:40 - Why use document & query expansion?
3:49 - RAG expansion use case
5:00 - Summary

Watch more Real Terms for AI → goo.gle/AIwordsExplained
Subscribe to Google Cloud Tech → goo.gle/GoogleCloudTech

#GoogleCloud #GenerativeAI

Speakers: Aja Hammerly, Jason Davenport
Products Mentioned: Gemini, Cloud General, Vertex AI