---
title: "Local Multimodal RAG Pipeline End-to-End Tutorial | On DGX Spark"
source_url: https://youtu.be/7GQPFS7NQrA
captured_at: 2026-03-14
author: "Daniel Bourke"
contributor: "ชิดชนก"
platform: youtube
---
# Local Multimodal RAG Pipeline End-to-End Tutorial | On DGX Spark

youtube video by **Daniel Bourke**, 65m22s, uploaded 2026-01-27. URL: https://youtu.be/7GQPFS7NQrA

## Shared in LINE Note+
- 2026-03-14 22:12 by ชิดชนก

## Description
Let's build a multimodal RAG (Retrieval Augmented Generation) pipeline using NVIDIA's Nemotron embedding and rerank vision-language models.

Multimodal means we'll be able to embed images and text in the same feature space.

This allows us to search over images and text simultaneously.

We'll learn how to create multimodal embeddings, retrieve them with a query, rerank them if necessary and generate an output based on the retrieved samples.

This is a scalable workflow you could take to many different use cases. If you've got a dataset of documents you need to search over, multimodal RAG could be part of the solution.

All of this was performed locally on a NVIDIA DGX Spark (see here for more: 

Businesses:
If you're a business who needs help creating their own multimodal RAG pipeline, contact me at:  

Links:
Source code (book version) -  
Source code (GitHub) -   
Source code (Colab) -  
YouTube playlist of livestreams -  

Resources:
Nemotron RAG models -  
A Realistic RAG System by Martin Fowler -  

Timestamps:
0:00 - Intro and overview
1:42 - What is RAG?
2:29 - RAG vs Fine-tuning
3:25 - A realistic RAG setup
4:15 - What we're going to build
8:35 - Ingredients and tools
9:15