Troubleshoot AI autodocumentation issues

This page provides solutions to common issues encountered while using the AI Autodocumentation feature. If your issue is not listed here, please contact our Support team.

Rate limit reached

If you see the following error message while generating AI descriptions for an object:

Rate limit reached for gpt-4 in organization org-{orgId} on tokens per min (TPM): Limit 10000, Used 7803, Requested 5731. Please try again in 21.204s. Visit https://platform.openai.com/account/rate-limits to learn more.

Cause

This error occurs when the API request exceeds the token per minute (TPM) limit set by OpenAI. It commonly happens when generating descriptions for tables or views with a large number of columns. You can check your organization's API limits at OpenAI Rate Limits.

Solutions

• Wait for the specified cooldown period indicated in the error message and click the Rerun generation buttons under each object to generate missing descriptions
• If using the GPT-4 model, consider switching to GPT-3.5, which has higher token limits
• Reduce the Max tokens setting in AI configuration to generate shorter descriptions. See Configuring AI Autodocumentation for GPT for details

Quota exceeded

If you see the following error message while generating AI descriptions for an object:

You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.

Cause

This error indicates that the quota assigned to your OpenAI API account is insufficient for the requested operation. The API call cannot be processed due to limitations in your subscription plan.

Solutions

• Verify your OpenAI API plan and available quota at OpenAI Billing
• Upgrade your subscription plan if necessary to increase your quota
• Reduce the number of requests or optimize token usage by lowering the Max tokens setting

SSL Connection could not be established

If you see the following error message while generating AI descriptions for an object:

The SSL connection could not be established, see inner exception.

Cause

The AI Autodocumentation feature requires access to OpenAI's API. If Dataedo Portal is installed in an environment without internet access, the connection cannot be established.

Solutions

• Ensure internet access is enabled for Dataedo Portal
• If internet access cannot be enabled, add OpenAI's API endpoint (https://api.openai.com/v1/chat/completions) to your firewall exception list or any other network security mechanism blocking access

Need help?

If you run into any problems or have questions, reach out to Dataedo support.