Replies: 4 comments 3 replies
-
|
The code in this comment seems to be from https://github.com/openai/openai-python/blob/75c90a71e88e4194ce22c71edeb3d2dee7f6ac93/openai/util.py#L21 that translates to variability in the header passed to the endpoint. Specifically, azure does not use Is this configurable in the npm package |
Beta Was this translation helpful? Give feedback.
-
|
Thank you for bringing this up. That's correct, there are some differences between the two endpoints, and I am aware of them. This isn't supported at the moment. I'm curious what models you are more interested in using from your Azure OpenAI Service deployments? i.e. text-davinci, code-davinci or chatgpt? I may consider updating my chatgpt api fork to support Azure OpenAI endpoints. |
Beta Was this translation helpful? Give feedback.
-
|
wait for azure support 👍 |
Beta Was this translation helpful? Give feedback.
-
|
This is now supported in Genie Test it out and let us know if you face any issues via our repo's Issues. @gencay could you transfer this as an issue over to us? |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Using the python module for ChatGPT, it is possible to use a "local" instance that is hosted on a Azure subscription, but we have not figured out how to connect that VS Code extension to a Azure hosted instance... these are the paramaters that are used in the python module:
Microsoft Azure Endpoints
In order to use the library with Microsoft Azure endpoints, you need to set the api_type, api_base and api_version in addition to the api_key. The api_type must be set to 'azure' and the others correspond to the properties of your endpoint. In addition, the deployment name must be passed as the engine parameter.
`import openai
openai.api_type = "azure"
openai.api_key = "..."
openai.api_base = "https://example-endpoint.openai.azure.com"
openai.api_version = "2022-12-01"
create a completion
completion = openai.Completion.create(engine="deployment-name", prompt="Hello world")
print the completion
print(completion.choices[0].text)`
How can we contribute to enable this feature ?
Beta Was this translation helpful? Give feedback.
All reactions