geekan
[IPKernelApp] WARNING | Parent appears to have exited, shutting down.
Bug description
I got the error "[IPKernelApp] WARNING | Parent appears to have exited, shutting down." while I'm running the example.
Bug solved method
Environment information
- LLM type and model name:
- System version: MacOS
- Python version: Python 3.11.7
- packages version:
- installation method:
Screenshots or logs
MacBook-Pro mytest % python solve_math_problems.py
2024-03-15 22:03:02.242 | INFO | metagpt.const:get_metagpt_package_root:29 - Package root set to /Users/jason/git/github/MetaGPT/workspace/mytest
-```json
[
{
"task_id": "1",
"dependent_task_ids": [],
"instruction": "Find the prime factorization of 6 and 126."
},
{
"task_id": "2",
"dependent_task_ids": ["1"],
"instruction": "Determine the values of m and n based on the prime factorization and the given conditions."
},
{
"task_id": "3",
"dependent_task_ids": ["2"],
"instruction": "Calculate the least possible value of m + n."
}
]
-```
2024-03-15 22:03:07.142 | INFO | metagpt.utils.cost_manager:update_cost:52 - Total running cost: $0.001 | Max budget: $10.000 | Current cost: $0.001, prompt_tokens: 265, completion_tokens: 123
2024-03-15 22:03:07.142 | INFO | metagpt.roles.role:_plan_and_act:494 - ready to take on task task_id='1' dependent_task_ids=[] instruction='Find the prime factorization of 6 and 126.' task_type='' code='' result='' is_success=False is_finished=False
2024-03-15 22:03:07.142 | INFO | metagpt.roles.di.data_interpreter:_write_code:79 - ready to WriteCodeWithoutTools
2024-03-15 22:03:09.482 | INFO | metagpt.utils.cost_manager:update_cost:52 - Total running cost: $0.001 | Max budget: $10.000 | Current cost: $0.001, prompt_tokens: 557, completion_tokens: 66
1 import math
2
3 # Prime factorization of 6
4 prime_factors_6 = [2, 3]
5
6 # Prime factorization of 126
7 prime_factors_126 = [2, 3, 3, 7]
0.00s - Debugger warning: It seems that frozen modules are being used, which may
0.00s - make the debugger miss breakpoints. Please pass -Xfrozen_modules=off
0.00s - to python to disable frozen modules.
0.00s - Note: Debugging will proceed. Set PYDEVD_DISABLE_FILE_VALIDATION=1 to disable this validation.
0.00s - Debugger warning: It seems that frozen modules are being used, which may
0.00s - make the debugger miss breakpoints. Please pass -Xfrozen_modules=off
0.00s - to python to disable frozen modules.
0.00s - Note: Debugging will proceed. Set PYDEVD_DISABLE_FILE_VALIDATION=1 to disable this validation.
2024-03-15 22:03:10.305 | INFO | metagpt.roles.role:_plan_and_act:494 - ready to take on task task_id='2' dependent_task_ids=['1'] instruction='Determine the values of m and n based on the prime factorization and the given conditions.' task_type='' code='' result='' is_success=False is_finished=False
2024-03-15 22:03:10.306 | INFO | metagpt.roles.di.data_interpreter:_write_code:79 - ready to WriteCodeWithoutTools
2024-03-15 22:03:11.936 | INFO | metagpt.utils.cost_manager:update_cost:52 - Total running cost: $0.001 | Max budget: $10.000 | Current cost: $0.001, prompt_tokens: 615, completion_tokens: 21
1 from sympy import *
2024-03-15 22:03:12.123 | INFO | metagpt.roles.role:_plan_and_act:494 - ready to take on task task_id='3' dependent_task_ids=['2'] instruction='Calculate the least possible value of m + n.' task_type='' code='' result='' is_success=False is_finished=False
2024-03-15 22:03:12.123 | INFO | metagpt.roles.di.data_interpreter:_write_code:79 - ready to WriteCodeWithoutTools
2024-03-15 22:03:34.325 | INFO | metagpt.utils.cost_manager:update_cost:52 - Total running cost: $0.001 | Max budget: $10.000 | Current cost: $0.001, prompt_tokens: 612, completion_tokens: 21
1 from sympy import *
MacBook-Pro mytest % [IPKernelApp] WARNING | Parent appears to have exited, shutting down.
According to your log:
2024-03-15 22:03:34.325 | INFO | metagpt.utils.cost_manager:update_cost:52 - Total running cost: $0.001 | Max budget: $10.000 | Current cost: $0.001, prompt_tokens: 612, completion_tokens: 21
1 from sympy import *
the llm didn't provide a runnable code:
from sympy import *
What's the model name?
What's the model name?
The model is GPT 3.5. Seems that's OK with azure gpt 4.
I suspect that the calling speed is too high. Maybe @garylin2099 can confirm
Thank you for bringing up this issue. I've attempted to reproduce the bug following the steps you provided, but so far, I haven't been successful. I'll continue trying, and I'd also like to ask for more information from you. Specifically, could you please provide details about your IDE software (such as VSCode or PyCharm), and any other configurations that might be relevant to this problem? Additionally, if you could offer more detailed reproduction steps or any relevant log information, it would be greatly appreciated. Thank you!
Great thanks! I'm going to have a try. @orange-crow
hi，Does it https://github.com/geekan/MetaGPT/pull/1141 work?