You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
1.3.0
Cloud or Self Hosted
Self Hosted (Docker)
Steps to reproduce
Using custom tools in chatflow or agent is very slow. When I call them with Postman or Python code, I get the result about 100ms, but in Dify it takes 5 seconds to get the result.
✔️ Expected Behavior
Speed up the tool usage.
❌ Actual Behavior
Using custom tools in chatflow or agent is very slow. When I call them with Postman or Python code, I get the result about 100ms, but in Dify it takes 5 seconds to get the result.
The text was updated successfully, but these errors were encountered:
For optimizing performance in a self-hosted Dify setup using Docker, consider the following configurations:
Server and Worker Configuration: Adjust the SERVER_WORKER_AMOUNT to match your CPU cores using the formula CPU cores x 2 + 1 for optimal performance. Also, consider increasing the GUNICORN_TIMEOUT to support long SSE connections [1].
Concurrency Management: Dify uses a GraphEngineThreadPool to manage concurrent executions. The default MAX_SUBMIT_COUNT is set to 100, which allows for a higher number of concurrent task submissions. Adjusting these settings might help improve performance [2].
Timeout Settings: Check the timeout settings in your config/provider.json file. The default is 120 seconds, but you might need to adjust this based on your specific use case [3].
These configurations and settings can help optimize the performance of custom tools in Dify. Adjust them based on your specific hardware and workload requirements.
Self Checks
Dify version
1.3.0
Cloud or Self Hosted
Self Hosted (Docker)
Steps to reproduce
Using custom tools in chatflow or agent is very slow. When I call them with Postman or Python code, I get the result about 100ms, but in Dify it takes 5 seconds to get the result.
✔️ Expected Behavior
Speed up the tool usage.
❌ Actual Behavior
Using custom tools in chatflow or agent is very slow. When I call them with Postman or Python code, I get the result about 100ms, but in Dify it takes 5 seconds to get the result.
The text was updated successfully, but these errors were encountered: