Skip to main content

Cohere Model

This section explains how to connect Cohere as a Gen AI Model data source in DataDios. Cohere's Command models power AI Studio text-to-SQL, chat, insights, and metadata discovery.

Cohere has a first-class embeddings API (the Embed models), so a Cohere data source can also be selected as your RAG embedding source.

Prerequisites​

Get a Cohere API key from the Cohere dashboard.

Steps to Create and Test a Cohere 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 Cohere 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 Cohere (the only provider available today)
  • model_type: The Command model to use (required, defaults to command-a-03-2025). The list is refreshed automatically — see Choosing a model below
  • embedding_model: The Embed model for vector/RAG operations. Options are embed-v4.0, embed-english-v3.0, embed-multilingual-v3.0 and embed-english-light-v3.0
  • API_KEY: Your Cohere API key (required, stored encrypted)
  • schedule_sync: (Optional) 15 Minutes, Hourly, or Daily for metadata synchronization

JSON Configuration​

{
   "project_name": "cohere_prod",
   "provider_type": "Direct Cohere",
   "model_type": "command-a-03-2025",
   "embedding_model": "embed-v4.0",
   "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 Command models appear without a DataDios upgrade. Models that shipped with your release are always present regardless.

Only the Command chat models are offered. Cohere's translate-only, vision and other specialised models are filtered out — they cannot be driven through the chat interface DataDios uses.

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

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