gemini-embedding-2

Community

Embed multimodal data for fast cross-modal search

AuthorFandry96
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Gemini Embedding 2 provides a unified 3072-dim vector space to represent text, images, video, audio, and PDFs for efficient cross-modal representation and retrieval.

Core Features & Use Cases

  • Natively multimodal embeddings with a single transformer backbone for text, images, video, audio, and PDFs
  • Supports MRL truncation (128-3072 dims) for flexible memory and index sizing
  • Ideal for semantic search, RAG pipelines, clustering, classification, and cross-modal retrieval
  • Works with vector databases and narrative memory for agentic retrieval and memory

Quick Start

Invoke gemini-embedding-2 to generate embeddings for a multimodal dataset and integrate them into your semantic search workflow.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: gemini-embedding-2
Download link: https://github.com/Fandry96/k3-agentic-skills/archive/main.zip#gemini-embedding-2

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.