Multimodal RAG - Chat with Text, Images and Tables

26 Apr 2025 · 18 min
17:34

LARRUZ shows how to build systems that search images, text, and tables together. The demo converts PDFs to images, embeds them with Cohere's EmbedV, retrieves matches by similarity, then feeds them to Gemini to answer questions like Nike's net profit or Tesla calculations. Local alternatives using ColPoly models are also covered.

Questions this video answers

Drei Größen: 512 bis 1536 (dimensionen).

8 Milliarden (Netto, bis Februar 2025).

32 Milliarden; Motorola Mobility: 12,5 Milliarden; Bandant: 5,4 Milliarden.

0,3 Milliarden (Nettogewinn inklusive Zinsen, laut Modellantwort).

Chapters

More from LARRUZ

8:49
youtube.com

OpenAI’s New AI Is Doing Things We Barely Understand

2d ago
5:38
youtube.com

DeepSeek Solved AI’s Memory Problem

4d ago
33:17
youtube.com

DeepMind's New AI Just Cracked The Code Of Life

1w ago
3:43
youtube.com

The Billion Dollar AI Advantage Is Disappearing

1w ago
5:14
youtube.com

Claude Opus 5.5 AI: An Incredible Leap Forward

3w ago
5:16
youtube.com

Yes, Jev Is Insane, But There's A Catch

3w ago
5:11
youtube.com

DeepSeek’s Insane New Architecture

3w ago
4:16
youtube.com

Claude Is Now Leaving Invisible Fingerprints In Its Text

1mo ago
9:18
youtube.com

I Never Thought I’d See This Happen

1mo ago
5:22
youtube.com

GPT-6 Astra Changes Everything

1mo ago
4:55
youtube.com

Claude Fable AI Is Much Stranger Than The Headlines Suggest

1mo ago
See all content