I am a newbie to python and streamlit. I use streamlit cloud and try to prepare training data on it.
Here is my repository and streamlit app page:
There are 3 steps:
input API key
upload an excel file
using openai.FineTune.prepare_data to turn the excel file into a jsonl file and download it
The error message says:
2023-05-09 03:02:34.710 Uncaught app exception
Traceback (most recent call last):
File “/app/fine-tune-testing/test.py”, line 25, in
jsonl = openai.FineTune.prepare_data(df=df)
AttributeError: type object ‘FineTune’ has no attribute ‘prepare_data’
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File “/home/appuser/venv/lib/python3.9/site-packages/streamlit/runtime/scriptrunner/script_runner.py”, line 565, in _run_script
exec(code, module.dict)
File “/app/fine-tune-testing/test.py”, line 32, in
except errors.AuthenticationError:
NameError: name ‘errors’ is not defined
======
Please can anyone tell me what goes wrong? Do I use the wrong version of openai in requirements.txt? Thank you so much!
So, I thought I can use it like that in the terminal. Can you tell me what I should do to call this openai.FineTune.prepare_data? Or this is not possible to use it like in a CLI command? Thank you!
There is a class FineTune in openai and another, different one, in openai.cli. What I found in the docs apparently refers to the former but I guess you want the latter.
This topic was automatically closed 180 days after the last reply. New replies are no longer allowed.
Hello there 👋🏻
Thanks for stopping by! We use cookies to help us understand how you interact with our website.
By clicking “Accept all”, you consent to our use of cookies. For more information, please see our privacy policy.
Cookie settings
Strictly necessary cookies
These cookies are necessary for the website to function and cannot be switched off. They are usually only set in response to actions made by you which amount to a request for services, such as setting your privacy preferences, logging in or filling in forms.
Performance cookies
These cookies allow us to count visits and traffic sources so we can measure and improve the performance of our site. They help us understand how visitors move around the site and which pages are most frequently visited.
Functional cookies
These cookies are used to record your choices and settings, maintain your preferences over time and recognize you when you return to our website. These cookies help us to personalize our content for you and remember your preferences.
Targeting cookies
These cookies may be deployed to our site by our advertising partners to build a profile of your interest and provide you with content that is relevant to you, including showing you relevant ads on other websites.