-
Notifications
You must be signed in to change notification settings - Fork 2.2k
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
The output generated by GPTResearcher lacks consistency, and the source URLs provided are neither valid nor accurate with model gpt-4o. #939
Comments
can you pls assign me this issue and label it under "hacktoberfest" |
Go for it @Shaunak-Gupta-dev ! |
For additional information, The prompt which i used to generate the report is The report was generated both programmatically using from gpt_researcher import GPTResearcher and utilizing the GPTResearcher GitHub code.References
References The reference links are invalid. |
i want to work on this issue please assign to me |
@Manideep-Maddileti go for it! |
Describe the bug
I executed GPTResearcher with the following prompt list:
for example,
gpt_researcher_prompt_list = ['''Generate a list of the acquisitions made by JPMorgan Chase & Co. (JPMC) in the 2022, 2023, and 2024 years. The output should be structured in a clear ordered list format (markdown format) with the following sections: Year of Acquisition, Company Name, Description, Synergy Gains.''']
Despite using the same configuration, I am receiving different outputs with each execution. Additionally, the source URLs provided are not valid and accurate path.
Actual results:
Execution 1 output:
2022
1. Nutmeg
2023
1. First Republic Bank
2024
1. InstaMed
2. Vera Whole Health
Execution 2 output:
2023
2024
Expected behavior
The response is expected to be consistent, and the source URLs should be accurate
Desktop :
The text was updated successfully, but these errors were encountered: