Skip to main content

​
Overview

OpenAI provides industry-leading language models including GPT-4, GPT-3.5, and text-embedding models. This guide walks you through setting up OpenAI as an AI Provider in Elementum.
Prerequisites: You’ll need an OpenAI account with API access. Individual accounts and organization accounts are both supported.

​
Step 1: Get Your OpenAI API Key

​
Creating an OpenAI Account

  1. Visit OpenAI Platform
  2. Set Up Billing
    • Navigate to Settings → Billing
    • Add a payment method to enable API access
    • Consider setting up usage limits to control costs

​
Generating Your API Key

1

Access API Keys

In your OpenAI dashboard, navigate to API Keys in the left sidebar
2

Create New Key

Click “Create new secret key”Give your key a descriptive name like “Elementum Integration”
3

Copy and Store

Critical: Copy the API key immediately and store it securelyYou won’t be able to view it again after closing the dialog
4

Set Permissions (Optional)

If using an organization account, you can set specific permissions for the keyEnsure the key has access to the models you plan to use
Security Important: Never share your API key or commit it to version control. Store it in a secure location like a password manager.

​
Step 2: Configure OpenAI in Elementum

​
Adding the Provider

  1. Navigate to Organization Settings
    1. In Elementum, go to Organization Settings
    2. Select the Providers tab
  2. Create New Provider
    1. Click ”+ Provider”
    2. Select OpenAI from the provider options
  3. Configure Provider Settings
Provider Name: Enter a descriptive name (e.g., “OpenAI Production”)API Key: Paste your OpenAI API keyEndpoint URL (Optional): Custom endpoint URL for Azure OpenAI or other OpenAI-compatible APIs. Leave blank to use the default OpenAI API endpoint.CloudLink: Select which CloudLinks can access models from this provider. Leave as “All CloudLinks” unless you need to restrict access.
  1. Save Configuration
    1. Click “Save” to create the provider
    2. The system will validate your API key automatically

​
Step 3: Test Your Connection

​
Verification Process

  1. Connection Test
    • After saving, Elementum will automatically test the connection
    • Look for a green checkmark indicating successful connection
  2. Model Availability
    • Navigate to Services tab
    • Click ”+ Service” to see available models
    • You should see OpenAI models listed

​
Available Models

Your OpenAI provider will give you access to:

​
Language Models (LLMs)

ModelPrimary Use CaseSpeedIntelligenceBest For
o3Complex reasoning and research⭐⭐⭐⭐⭐⭐⭐Advanced problem-solving, research tasks, complex analysis
o4-miniFast, efficient reasoning⭐⭐⭐⭐⭐⭐⭐⭐⭐Daily tasks, customer support, quick analysis
GPT-4 OmniBalanced performance⭐⭐⭐⭐⭐⭐⭐⭐Content creation, detailed analysis, conversational AI
Model Recommendations: Use o4-mini for most daily tasks and customer interactions. Choose o3 for complex reasoning that requires the highest intelligence. GPT-4 Omni provides a good balance for general-purpose applications.
Note: Embeddings for AI Search are handled exclusively through Snowflake Cortex. OpenAI models are used for LLM services only.

​
Step 4: Create Your First AI Service

With your OpenAI provider configured, create an AI Service:
1

Navigate to Services

In Organization Settings, go to the Services tab
2

Create LLM Service

Click ”+ Service” and select LLM (Language Model service)Service Name: Give it a descriptive name (e.g., “OpenAI Customer Support”)Model: Select from available OpenAI modelsCost Per Million Tokens: Set for cost tracking (optional)
3

Test Service

Use the built-in testing interface to verify your service works correctly

​
Usage Guidelines

​
Cost Management

OpenAI charges based on token usage. To manage costs:

Monitor Usage

Track Consumption
  • Monitor usage in OpenAI dashboard
  • Set up billing alerts
  • Review token consumption regularly

Optimize Usage

Efficiency Tips
  • Use appropriate models for tasks
  • Implement context windowing
  • Cache responses when possible
  • Use o4-mini for speed-critical applications

​
Best Practices

  1. Model Selection
    • Use o4-mini for most customer support and daily automation tasks
    • Use o3 for complex reasoning, research, and advanced problem-solving
    • Use GPT-4 Omni for content creation and detailed analysis
  2. Prompt Engineering
    • Be specific and clear in your prompts
    • Use system messages for consistent behavior
    • Provide examples for better results
    • For o3, structure complex problems step-by-step
  3. Performance Optimization
    • Choose o4-mini for speed-critical applications
    • Use o3 sparingly for tasks requiring maximum intelligence
    • Implement caching for repeated queries
    • Consider request queuing for high-volume usage

​
Troubleshooting

Symptoms: API key rejected or unauthorized errorsCommon Causes:
  • Invalid or expired API key
  • Insufficient permissions
  • Billing issues
Solutions:
  1. Verify API key is correct and active
  2. Check billing status and payment methods
  3. Ensure key has proper permissions
  4. Regenerate API key if needed
Symptoms: Desired model doesn’t appear in service creationCommon Causes:
  • Account doesn’t have access to specific models
  • Regional restrictions
  • Model deprecation
Solutions:
  1. Check OpenAI account tier and access levels
  2. Review model availability in your region
  3. Contact OpenAI support for access issues
  4. Consider alternative models
Symptoms: Requests being throttled or rejectedCommon Causes:
  • Exceeding rate limits
  • High concurrent usage
  • Account tier limitations
Solutions:
  1. Implement exponential backoff
  2. Reduce request frequency
  3. Upgrade account tier if needed
  4. Distribute load across multiple keys

​
Security Considerations

API Key Security

Protect Your Keys
  • Never expose API keys in client-side code
  • Rotate keys regularly
  • Use environment variables for storage
  • Monitor key usage for anomalies

Data Privacy

Understand Data Handling
  • OpenAI may use data for training (check current policy)
  • Consider data sensitivity in prompts
  • Review OpenAI’s privacy policy
  • Implement data sanitization if needed

​
Advanced Configuration

​
Organization Accounts

If using an OpenAI organization account:
  1. Organization ID: Required for organization accounts
  2. Member Management: Control team access through OpenAI dashboard
  3. Usage Tracking: Monitor usage across team members
  4. Billing Management: Centralized billing for the organization

​
Custom Endpoints

For Azure OpenAI or other OpenAI-compatible APIs:
  1. Endpoint URL: Enter your custom endpoint (e.g., https://your-resource.openai.azure.com/)
  2. Authentication: May require additional authentication headers depending on the endpoint
  3. Model Names: Custom model names may be required for non-standard endpoints
  4. Rate Limits: May differ from standard OpenAI limits

​
Next Steps

With OpenAI configured as your AI Provider:

Create AI Services

Set up specific LLM and embedding services for your workflows

Configure Snowflake Cortex

Set up Snowflake Cortex for AI Search and embeddings

Build Agents

Create conversational AI assistants using OpenAI models

Use AI Actions

Add AI capabilities to your automation workflows
OpenAI provides advanced, general-purpose AI capabilities that work well for most use cases. Once configured, you can leverage these models across all of Elementum’s AI features.