---
title: "Gemini Embedding 2: Multimodal Retrieval Demo with ChromaDB"
source_url: https://youtu.be/NqqNpVPhyd4
captured_at: 2026-06-14
author: "Alejandro AO"
contributor: "ชิดชนก"
platform: youtube
---
# Gemini Embedding 2: Multimodal Retrieval Demo with ChromaDB

youtube video by **Alejandro AO**, 10m37s, uploaded 2026-03-11. URL: https://youtu.be/NqqNpVPhyd4
Tags: chromadb, embeddings, gemini, google, llm, multimodal, quickstart, rag, semantic-search, vector-database

## Shared in LINE Note+
- 2026-06-14 21:22 by ชิดชนก

## Description
Gemini Embedding 2 just dropped, and this release is a big step for multimodal retrieval workflows.

In this video, I walk through what is new, key limits to know before you build, benchmark highlights, and a practical ChromaDB demo where we embed mixed media and run semantic queries against one shared vector space.

---
🧑‍💻 Notebook: 

---
🤓 *Topics Covered*
- What Gemini Embedding 2 adds vs prior embedding workflows
- Input limits and practical constraints (text/image/video/audio/PDF)
- Benchmark highlights and how to interpret them
- Building a multimodal vector database with ChromaDB
- Querying and validating retrieval quality in a real notebook

## Connect with me
- X: 
- LinkedIn: 

---
⏱️ *Timestamps*
0:00 Intro + what Gemini Embedding 2 is
0:32 Capabilities, constraints, and benchmark context
3:54 ChromaDB implementation + retrieval demo