-
-
Notifications
You must be signed in to change notification settings - Fork 13.3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
We need to fix the parsing for the har openai access token #2339
Comments
I've tested the functionality, including the code in g4f/Provide/openai/har_file.py, and haven't encountered any issues. The error "Please add an "api_key" or provide a .har file. Invalid api key" typically occurs when:
Here are my test logs showing successful execution:
I've tested the HAR file parsing functionality in g4f/Provide/openai/har_file.py with multiple accounts and haven't found any issues. However, this is just my observation based on testing. Could you please verify that:
|
Not work. The problem remains |
Due to this error, I install the access token manually, and use the old har file for the rest of the parameters. The GPT-4o model works, but the paid chatgpt subscription features are not available. I tried all the methods of creating a new har file, I still get an error I need the paid functionality provided in the plus subscription to work (search, analysis, sending photos and files, image generation via dalle) I noticed that if me send a request not in a new chat, but within an existing conversation using the current conversation_id, in this case, the paid features of the Plus subscription will work in the request. |
I tried to get the HAR file in a different browser. The "Please add an 'api_key' or provide a .har file" error is gone now. But another issue has arisen. Here are the error logs:
|
Parsing a new HAR file results in the error:
Please add an "api_key" or provide a .har file. Invalid api key
It is necessary to fix the HAR file parsing functionality in the code located at
g4f/Provide/openai/har_file.py
.The text was updated successfully, but these errors were encountered: