/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 uses your <a href="https://cloud.google.com/docs/authentication#adc">Application Default Credentials (ADC)</a> to authorize with the Gemini API client.</p> <p>Optionally, you can use an <a href="https://ai.google.dev/gemini-api/docs/api-key#api-keys">API key</a> obtain an API Key from the <a href="https://aistudio.google.com/app/apikey">Google AI Studio</a>.</p> <p>We recommend using an API key for testing and using application default credentials for production.</p> <h2 id="behavior">Behavior</h2> <h3 id="automatic-vectorization">Automatic Vectorization</h3> <p>When a tool parameter is configured with <code>embeddedBy: &lt;your-gemini-model-name&gt;</code>, the Toolbox intercepts the raw text input from the client and sends it to the Gemini API. The resulting numerical array is then formatted before being passed to your database source.</p>