Skip to main content

Gemini Model

This section explains how to connect Google Gemini as a Gen AI Model data source in DataDios. Gemini powers AI Studio text-to-SQL, chat, insights, and metadata discovery.

Unlike Claude, Gemini has a first-class embeddings API, so a Gemini data source can also be selected as your RAG embedding source.

Prerequisites​

Get a Gemini API key from Google AI Studio. This is the key for the Gemini Developer API (the "Direct Gemini" provider) — not a Google Cloud service account.

Steps to Create and Test a Gemini Data Source​

Step 1: Create a Data Source​

  1. Navigate to the Data Sources tab in DataDios
  2. Click + CREATE SOURCE
  3. In the data source type dropdown, expand Gen AI Models and select Gemini Model

Step 2: Fill Connection Details​

Provide the following parameters (toggle to Json for the raw form):

  • project_name: (Optional) A label to group your models under
  • provider_type: Direct Gemini (the only provider available today)
  • model_type: The Gemini chat model to use (required, defaults to gemini-2.5-pro). The list is refreshed automatically — see Choosing a model below
  • embedding_model: The embedding model for vector/RAG operations — models/gemini-embedding-001
  • API_KEY: Your Gemini API key (required, stored encrypted)
  • schedule_sync: (Optional) 15 Minutes, Hourly, or Daily for metadata synchronization

JSON Configuration​

{
   "project_name": "gemini_prod",
   "provider_type": "Direct Gemini",
   "model_type": "gemini-2.5-pro",
   "embedding_model": "models/gemini-embedding-001",
   "API_KEY": "AIza...",
   "schedule_sync": ""
}

Step 3: Test Connection​

  1. Click TEST CONNECTION
  2. A valid key returns Status: OK. The key is never echoed back in any response or log.

Step 4: Save Data Source​

  1. Click CREATE to save the data source
  2. It appears on the Data Sources listing page under Gen AI Models

Choosing a model​

The model_type dropdown is refreshed automatically from a public model catalog at server start, so newly released Gemini models appear without a DataDios upgrade. Models that shipped with your release are always present regardless.

Only the Gemini chat models are offered. Gemma, robotics, computer-use, image, video and speech models are filtered out — they cannot be driven through the chat interface DataDios uses.

The embedding_model list is not refreshed from the catalog, because the catalog does not publish the vector width DataDios needs to size your RAG store correctly.

See Gen AI Model Catalog for how the list is kept up to date, what network access it needs on-premises, and what changes on upgrade.

Using Gemini with AI Studio and RAG​

Select this data source in AI Studio for natural-language queries, SQL generation, chat, and insights (see the AI Studio documentation). Because Gemini provides embeddings, you can also pick it as the embedding source when configuring RAG / hybrid search.

To make Gemini available to every user in your tenant, bind it to the AI · reasoning role under Manage → Integrations → Catalog.