/documentation/configuration/embedding-models/Recent content in EmbeddingModels on MCP Toolbox for DatabasesHugoen/documentation/configuration/embedding-models/gemini/Mon, 01 Jan 0001 00:00:00 +0000/documentation/configuration/embedding-models/gemini/<h2 id="about">About</h2> <p>Google Gemini provides state-of-the-art embedding models that convert text into high-dimensional vectors.</p> <h3 id="authentication">Authentication</h3> <p>Toolbox supports two authentication modes:</p> <ol> <li><strong>Google AI (API Key):</strong> Used if you provide <code>apiKey</code> (or set <code>GOOGLE_API_KEY</code>/<code>GEMINI_API_KEY</code> environment variables). This uses the <a href="https://aistudio.google.com/app/apikey">Google AI Studio</a> backend.</li> <li><strong>Vertex AI (ADC):</strong> Used if provided <code>project</code> and <code>location</code> (or set <code>GOOGLE_CLOUD_PROJECT</code>/<code>GOOGLE_CLOUD_LOCATION</code> environment variables). This uses <a href="https://cloud.google.com/docs/authentication#adc">Application Default Credentials (ADC)</a>.</li> </ol> <p>We recommend using an API key for quick testing and using Vertex AI with ADC for production environments.</p>