Configure client for Azure and OpenAI in parallel #251
-
|
If the client is configured to use Azure OpenAI service then Image generation doesn't work because it is not available on Azure. |
Beta Was this translation helpful? Give feedback.
Replies: 3 comments 1 reply
-
|
The same goes for embeddings. You get different deployment IDs for the different models deployed in Azure but there is only one setting for that in the config. Also the API-versions are different. So it will call GPT instead of Ada of its configured to work with chat completions |
Beta Was this translation helpful? Give feedback.
-
|
This is a case that I haven't considered before. To address it, I will add support for multi-instance initialization. As a workaround, you can create a second instance without using dependency injection. |
Beta Was this translation helpful? Give feedback.
-
|
https://github.com/betalgo/openai/wiki/Working-with-Multiple-Instances wiki page is ready, I will be releasing 6.9.0 soon This update will have only support for typed multiple instances but I am also planning dynamic multiple instances in the next versions. |
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
This is a case that I haven't considered before. To address it, I will add support for multi-instance initialization. As a workaround, you can create a second instance without using dependency injection.