Closed yl-miao closed 2 months ago
Hi @yl-miao, thank you for your interest to GPTSwarm! Indeed, some couple of weeks ago, numpy==2.0 had been released and broke outstandingly many builds in the python world. We will consider adding a constraint of numpy<2 in the next version of GPTSwarm release. Meanwhile a hotfix is to manually install pip install numpy==1.25.2
and possibly downgrade versions of packages like seaborn as needed. Please let me know if it solves the issue for you.
@yl-miao you can always install the recent or your own customized version from the cloned repo with poetry install
. Please find the instruction in https://github.com/metauto-ai/GPTSwarm/blob/main/DEVELOPMENT.md.
You can also try my latest fix at #27.
Hi, the #27 fixes this. Thank you very much : ) @Obs01ete
Hi,
After testing, the demo_swarm can be run in a newly-created Colab Notebook after
pip install gptswarm
, but cannot be run in a newly-created Python 3.10 environment by miniconda afterpip install gptswarm
. Please refer to the pictures:I suspect the reason might be: In Colab, although the default version for Python is 3.10, the default version for numpy is 1.25.2. However, in a newly-created conda Python 3.10 environment, during
pip install gptswarm
, it would install numpy version 2.0.0.I wondered if this issue can be fixed by adding a restriction for numpy version in the "pyproject.toml" file, or it may be caused by something in the demo code, or by something else, I'm not entirely sure.
Thank you very much!
@Obs01ete
The detailed output (After 'conda create -n tmpenv python=3.10' and 'pip install gptswarm' and the demo_swarm):