DeepInfra: Add max_tokens and stop

[nullstreak]

No description provided.

[github-actions]

Review for Pull Request: DeepInfra: Add max_tokens and stop by @nullstreak

Hi @nullstreak,

Thank you for contributing to the project! I've reviewed the pull request where you've added max_tokens and stop parameters to the create_async_generator function in DeepInfra.py. Here are some comments and suggestions:

Suggestions:

1. Validation of Parameters:

   • It would be beneficial to add validation for the max_tokens and stop parameters to ensure they meet certain conditions (e.g., max_tokens should be a positive integer, stop should be a list). This would help in preventing unexpected behaviors or errors when the API is called.

2. Update Documentation:

   • Please update the function's docstring or the module documentation to reflect the new parameters and their usage. This will help other developers understand how to use the max_tokens and stop parameters effectively.

3. Test Cases:

   • Adding some test cases to cover the new functionality would be excellent. This helps in ensuring that the max_tokens and stop parameters work as expected and do not inadvertently affect other functionalities.

Overall:

The changes you've proposed are straightforward and align well with the feature set of the DeepInfra.py module. Adding the capability to control the number of tokens and specify stop conditions dynamically enhances the module's flexibility in generating responses.

Thank you again for your valuable contribution to the project! If you have any questions or need further assistance, please feel free to ask.

Kind regards,
[Your Name]

[hlohaus]

Thank you