Engel Nyst
Engel Nyst
Oh, thanks for taking this up! You're fast ❤️ I'm just thinking that if we add another "embedding deployment" var, then the var we have becomes unused. 😅 To me...
> Thanks to your test script in comments above, I see it wasn't necessary in the completion call, isn't that right? The llm.py completion call worked _as is_. To be...
This looks solved, user input in the terminal has been disabled a while ago.
About embeddings: We don't yet get what we set, because this PR was tested without the threading added in memory.py. With them, the PR implementation _still_ retries more than num_retries,...
Can you please try ```poetry update``` ?
/litellm-models is not how you call the models, you need to set the URL as *LM Studio* exposes it. Check its documentation on how to call the model you want...
Also reported in #420
@marcofiocco I'm not sure how to solve this off-hand, but we can find a solution. I don't currently have Azure, though, so I may need your help here. > Allow...
This parameter, ideally: ``` test_token = litellm.get_secret("AZURE_AD_TOKEN") ```
The embedding deployment name doesn't look right (it's not a GPT). This is in addition, @ayanjiushishuai to the other error, the one you experienced and solved. The API version also...