Try EmbeddingGemma 2 multimodal embeddings in Colab
Melvin Vivas · X post · 2026-10-09 · Open on X
Topics: Embeddings & Vector Databases, Retrieval-Augmented Generation (RAG) · Level: intermediate
Summary
EmbeddingGemma 2 is Google's multimodal embedding model. It maps text, code, images, video and audio into one shared embedding space. The creator shares a Google Colab notebook in his GitHub notebooks repo so you can try it. The quoted post points to Google's developer guide, which uses the sentence-transformers library.
Key points
- EmbeddingGemma 2 puts text, code, images, video and audio into a single embedding space
- A shared space enables search across media types, for example a text query that finds images or video
- The model can be loaded with sentence-transformers or other frameworks
- Workflow from the guide: load the model through your preferred framework, then embed multimodal content
- A ready-to-run Colab notebook is in the creator's donvito/notebooks repo
Resources mentioned
- donvito/notebooks · repo · github.com · free
The creator's notebooks for fine-tuning and running local models, which you can run in Google Colab, including a GLiNER2.5-Decide intent classification example.
Also in: Run LightOnOCR-3 0.8B and Other Open Models on a Free Colab T4 (Melvin Vivas on X · notes), Try Liquid AI's open d1-3B decision model in Colab (Melvin Vivas on X · notes), Colab Notebook for Liquid AI's d1-3B Decision Model (Melvin Vivas on X · notes), Fine-tune and Run Local Models for Free on Google Colab's T4 GPU (Melvin Vivas on X · notes) and 10 more - EmbeddingGemma 2 · tool · huggingface.co · free
Google's open 740M-parameter multimodal embedding model that puts text, images, video and audio into one shared vector space for on-device use.
Also in: Google AI Edge Foresight: On-Device Meeting Notes with EmbeddingGemma 2 (Melvin Vivas on X · notes), A day of work done from a phone with Grok Bot agents (Melvin Vivas on X · notes), EmbeddingGemma 2 Colab Notebook for FAQ Semantic Search (Melvin Vivas on X · notes), EmbeddingGemma 2 released on Hugging Face (Melvin Vivas on X · notes) and 2 more - EmbeddingGemma 2 Developer Guide · docs · developers.googleblog.com · free
Google's guide to embedding multimodal content with EmbeddingGemma 2 using sentence-transformers and other frameworks. - Sentence Transformers · tool · sbert.net · free
Open-source Python library for training and running embedding, sparse, reranker and (from v6) multi-vector models.
Also in: Sentence Transformers v6: ColBERT-Style Multi-Vector Models Fully Supported (Melvin Vivas on X · notes) - Google Colab · tool · colab.research.google.com · free · recommended by both Bashiri Smith & Melvin Vivas
Free GPU notebooks.
Also in: Run LightOnOCR-3 0.8B and Other Open Models on a Free Colab T4 (Melvin Vivas on X · notes), Try Liquid AI's open d1-3B decision model in Colab (Melvin Vivas on X · notes), Google Colab notebooks for new open models, built by a coding agent (Melvin Vivas on X · notes), Liquid AI's LFM2.5-24B-A2B: a local MoE model for agent tasks (Melvin Vivas on X · notes) and 27 more
Try this
- Download the EmbeddingGemma 2 notebook from donvito/notebooks and run it in Google Colab
- Read the EmbeddingGemma 2 Developer Guide
- Build a search that works across text, code, images, video and audio using EmbeddingGemma 2
More in Embeddings & Vector Databases
- Google AI Edge Foresight: On-Device Meeting Notes with EmbeddingGemma 2
- Vector Database vs. Graph Database: When to Use Each (and Both for RAG)
- Embeddings: what they mean for businesses
- EmbeddingGemma 2 Colab Notebook for FAQ Semantic Search
- EmbeddingGemma 2 released on Hugging Face
- EmbeddingGemma 2: One On-Device Model for Multimodal Embeddings