Skip to main content

OpenAI Model

This section explains how to connect OpenAI as a Gen AI Model data source in DataDios. Once connected, OpenAI can power AI Studio text-to-SQL, chat, insights, and metadata discovery, and can be bound to AI · reasoning in Manage → Integrations for the whole tenant.

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

The same connector serves both OpenAI and Azure OpenAI — pick which one under provider_type.

Prerequisites​

Get an OpenAI API key from the OpenAI platform. Optionally, create an Admin API key as well if you want the workload Cost dashboard to pull real usage and spend from OpenAI's Admin API.

For Azure OpenAI, you will additionally need your Azure endpoint and the deployment names for your chat and embedding models.

Steps to Create and Test an OpenAI 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 OpenAI 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: OpenAI or Azure OpenAI
  • model_type: The chat model to use (required). The list is refreshed automatically — see Choosing a model below
  • embedding_model: The embedding model for vector/RAG operations. Built-in options are text-embedding-3-small, text-embedding-3-large and text-embedding-ada-002
  • API_KEY: Your OpenAI API key (required, stored encrypted)
  • ADMIN_API_KEY: (Optional) An OpenAI Admin API key, used only to populate the Cost dashboard
  • schedule_sync: (Optional) 15 Minutes, Hourly, or Daily for metadata synchronization

For Azure OpenAI, also provide:

  • azure_endpoint: Your Azure OpenAI resource endpoint
  • deployment_name: The deployment name for your chat model
  • embedding_deployment_name: (Optional) The deployment name for your embedding model
  • base_url: (Optional) An explicit Azure OpenAI v1 base URL ending with /openai/v1
  • api_version: (Optional) The Azure OpenAI REST API version for deployment-based endpoints

JSON Configuration​

{
   "project_name": "openai_prod",
   "provider_type": "OpenAI",
   "model_type": "gpt-4o",
   "embedding_model": "text-embedding-3-small",
   "API_KEY": "sk-...",
   "ADMIN_API_KEY": "",
   "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 OpenAI models appear without a DataDios upgrade. Models that shipped with your release are always present regardless.

gpt-4o is a good general default. 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.

note

Reasoning models (the gpt-5 and o-series families) do not accept the sampling parameters that earlier models do. DataDios detects this and adjusts the request automatically — no configuration needed.

Using OpenAI 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 OpenAI provides embeddings, you can also pick it as the embedding source when configuring RAG / hybrid search.

To make OpenAI available to every user in your tenant without each user creating their own model source, bind it to AI · reasoning in Manage → Integrations.