Web Timeout: Setting TEXT_GENERATION_TIMEOUT_MS Not Effective

[JiweiZh]

Self Checks

• This is only for bug report, if you would like to ask a question, please head to Discussions.
• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

Dify version

0.14.2

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

I’m experiencing a timeout issue in my application when executing large model iterations multiple times. The overall execution time exceeds 5 minutes, and upon completion, the page does not return the final result. Instead, it displays the message: Results are not displayed due to timeout. please refer to the logs....

I Attempts to Fix by
• Increased TEXT_GENERATION_TIMEOUT_MS in docker_compose.yml to 10 minutes(600000ms).
• Updated textGenerationTimeoutMs in /web/config/index.ts to (600000ms).
• Restarted Docker Compose after making configuration changes.

Despite these efforts, the application still times out after approximately 5 minutes, and the final results are not displayed.

✔️ Expected Behavior

The application should wait for the entire execution process to complete (over 5 minutes) and display the final results without timing out.

❌ Actual Behavior

the application does not display the final results and shows the following timeout message, after setting TEXT_GENERATION_TIMEOUT_MS

[dosubot]

@JiweiZh Hello! I'm here to help you with bug reports, answer questions, and provide assistance while you wait for a human maintainer. Let's tackle this issue together!

The issue you're experiencing might be related to other timeout settings in the Dify codebase that could be affecting the overall behavior. Here are a few things to consider:

1. GUNICORN_TIMEOUT: This setting controls the request handling timeout for the Gunicorn server. By default, it is set to 360 seconds (6 minutes). You might want to increase this value to accommodate longer processing times ^[1].

2. NGINX Timeouts: If you're using NGINX as a reverse proxy, check the NGINX_PROXY_READ_TIMEOUT and NGINX_PROXY_SEND_TIMEOUT settings. These are set to 3600 seconds by default, but if they have been modified, they could be causing the timeout ^[1].

3. Other Timeout Settings: Ensure that other related timeout settings, such as SANDBOX_WORKER_TIMEOUT and API tool timeouts, are configured appropriately. These settings can also influence the behavior of long-running processes ^[1].

4. Logs and Error Messages: Check the logs for any specific error messages that might indicate what is causing the timeout. This can provide more insight into whether the issue is related to resource allocation, rate limits, or other factors ^[2].

By reviewing and adjusting these settings, you may be able to resolve the timeout issue you're encountering.

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other}