Closed baswenneker closed 9 months ago
Hi @baswenneker, thanks for opening this issue. I will have a look today
The issue is due to a recent change of the Azure API within the openai
library. Specifically, it used to use the name keyword name "engine"
to label Azure deployment, but now they have unified to use "model"
just like normal OpenAI model.
I have updated the source code to align our repo with the latest API. I updated the notebook and tested the change as well. Please re-install our library from source (GitHub) and make sure your openai
library has a version >1.0
.
Let me know if we can help you with anything else, or re-open this issue. We always welcome feedback and suggestions!
You likely forgot to also update: https://github.com/hegelai/prompttools/blob/5a807328435d269d7ed17b53f86283e116e08244/prompttools/experiment/experiments/openai_completion_experiment.py#L156
As it is referenced in the examples: https://github.com/hegelai/prompttools/blob/5a807328435d269d7ed17b53f86283e116e08244/examples/notebooks/AzureOpenAIServiceExperiment.ipynb
🐛 Describe the bug
I'm trying to get the AzureOpenAIServiceExperiment notebook runnning (with my own Azure credentials) but it gives me the following error when running:
The error is as follows, but the script keeps running so I have to interrupt it:
I've got Version: 0.0.43 installed (from pip). I started a clean virtualenv and only installed prompttools.
Any ideas?