Azure-Samples / Azure-Samples/rag-data-openai-python-promptflow
calling pf_client.run inside the callable target function for evaluate got "Error: (AssertionError) daemonic processes are not allowed to have children."
- Lingua principale
- Python
- Stelle
- 290
- Fork
- 152
- Metriche di merge delle PR
- Nessuna PR unita negli ultimi 30g
Descrizione
> Please provide us with the following information:
> ---------------------------------------------------------------
### This issue is for a: (mark with an `x`)
```
- [ ] bug report -> please search issues before submitting
- [ ] feature request
- [ ] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)
```
### Minimal steps to reproduce
>
I am trying to hook up the evaluate method with my own prompt which used to run from pf_client.run
example code below:
```
from promptflow.client import PFClient
pf_client = PFClient()
def user_call():
my_prompt_flow = pf_client.run(my prompt flow configs)
return my_prompt_flow_output
def run_evaluation():
results = evaluate(
evaluation_name=evaluation_name,
data=data_path,
target=user_call,
evaluators={
"violence": violence_evaluator,
"sexual": sex_evaluator,
"self_harm": self_harm_evaluator,
"hate_unfairnes": hate_unfairness_evaluator,
"content_safety": content_safety_evaluator
},
azure_ai_project=project_scope
)
```
### Any log messages given by the failure
>
2024-07-06 00:58:41 +0000 1845174 execution.bulk INFO The process [1845174] has received a terminate signal.
2024-07-06 00:58:42 +0000 1844849 execution ERROR 1/1 flow run failed, indexes: [0], exception of index 0: Execution failure in 'user_call': (UnexpectedError) **Unexpected error occurred while executing the batch run. Error: (AssertionError) daemonic processes are not allowed to have children.**
### Expected/desired behavior
>
### OS and Version?
> Windows 7, 8 or 10. Linux (which distribution). macOS (Yosemite? El Capitan? Sierra?)
Linux
### Versions
>
### Mention any other details that might be useful
> ---------------------------------------------------------------
> Thanks! We'll be in touch soon.
Guida per i contributori
Nessuna guida per i contributori indicizzata per questo repository
Direzione di ricerca
Inizia riproducendo su Linux il flusso mostrato evaluate(target=user_call), concentrandoti sull’interazione tra pf_client.run e il processo worker di valutazione. Confronta questo con una chiamata diretta a pf_client.run e identifica cosa deve cambiare affinché la valutazione venga completata senza l’asserzione relativa a un processo daemon.
Scritto dal modello di indicizzazione a partire dal testo della issue.
Valutazione
- Stack tecnologico
- azure, python
- Ambito
- ai
- Tipo di issue
- Bug
- Difficoltà
- 4/5
- Tempo stimato
- 3-5 giorni
- Stato di attività
- Ferma
- Chiarezza
- Da chiarire
- Idoneità per principianti
- 25/100