Gabriele Venturi
Gabriele Venturi
@zhenkaivip in order to keep it as clean as possible (and not having to add additional dependencies), I would recommend the following approach: * right before we pass the prompt,...
I'd say if it's not huge, we can leave it as part of this repo for the time being. Then if it becomes bigger and bigger we'd rather move it...
Hey @TiansuYu, sounds great, would be great to have such an automation, for example, when a new tag is added. Would love if you could look into it, as it...
@shuangquanhuang super nice addition, will work on it!
@ambujpawar maybe we could also accept a list in the first param and then conditionally run the workflow on only 1 df vs multiple dfs. Something like this: ``` pandas_ai.run(df1,...
@TiansuYu configured everything, but cannot make it work: `There is no pypi-token.test_pypi setting.` This is actually weird, cause we are passing the key
@TiansuYu if what the maintainer of the library mentioned is correct, maybe we should test with an actual release with the right repo and see whether it works!
@mzy2240 @HenriqueAJNB I've created one (#127 )
Feature added with this commit: https://github.com/gventuri/pandas-ai/commit/be4c717a9b0f07b88ee2aed729b637413df28a51 Closing
Hey @TSampley, i really like this approach, and I agree that this probably the safest way. Only downsides: * it would require users to have docker installed, which would not...