AI Providers
OpenAI Setup
Configure OpenAI as your AI provider for advanced language models and embeddings
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
-
Visit OpenAI Platform
- Go to platform.openai.com
- Sign up for an account or log in to your existing account
-
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
-
Navigate to Organization Settings
- In Elementum, go to Organization Settings
- Select the Providers tab
-
Create New Provider
- Click ”+ Provider”
- Select OpenAI from the provider options
- Configure Provider Settings
Provider Name: Enter a descriptive name (e.g., “OpenAI Production”)API Key: Paste your OpenAI API keyOrganization ID (Optional): If using an organization account, enter your organization IDCloudLink: Leave as “All CloudLinks” unless you have specific requirements
- Save Configuration
- Click “Save” to create the provider
- The system will validate your API key automatically
Step 3: Test Your Connection
Verification Process
-
Connection Test
- After saving, Elementum will automatically test the connection
- Look for a green checkmark indicating successful connection
-
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)
| Model | Primary Use Case | Speed | Intelligence | Best For |
|---|---|---|---|---|
| o3 | Complex reasoning and research | ⭐⭐ | ⭐⭐⭐⭐⭐ | Advanced problem-solving, research tasks, complex analysis |
| o4-mini | Fast, efficient reasoning | ⭐⭐⭐⭐⭐ | ⭐⭐⭐⭐ | Daily tasks, customer support, quick analysis |
| GPT-4 Omni | Balanced 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
-
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
-
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
-
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
Authentication Errors
Authentication Errors
Symptoms: API key rejected or unauthorized errorsCommon Causes:
- Invalid or expired API key
- Insufficient permissions
- Billing issues
- Verify API key is correct and active
- Check billing status and payment methods
- Ensure key has proper permissions
- Regenerate API key if needed
Model Not Available
Model Not Available
Symptoms: Desired model doesn’t appear in service creationCommon Causes:
- Account doesn’t have access to specific models
- Regional restrictions
- Model deprecation
- Check OpenAI account tier and access levels
- Review model availability in your region
- Contact OpenAI support for access issues
- Consider alternative models
Rate Limit Issues
Rate Limit Issues
Symptoms: Requests being throttled or rejectedCommon Causes:
- Exceeding rate limits
- High concurrent usage
- Account tier limitations
- Implement exponential backoff
- Reduce request frequency
- Upgrade account tier if needed
- 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:- Organization ID: Required for organization accounts
- Member Management: Control team access through OpenAI dashboard
- Usage Tracking: Monitor usage across team members
- Billing Management: Centralized billing for the organization
Custom Endpoints
For enterprise OpenAI deployments:- Base URL: Configure custom endpoint URL
- Authentication: May require additional authentication headers
- Model Names: Custom model names may be required
- 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.