Create Azure OpenAI Instance
- Go to Azure AI service >> Azure OpenAI
- Click
Create
and configure the details including region of the instance (where your ML model deployment is hosted). - After an instance is created, go to the instance by clicking it on the list e.g. in the first screenshot click “ca-inst”.
- Click manage deployment on the left sidebar and click the “Manage Deployment” button.
- Click “Create new deployment” to select a model. You need to create two deployments for
text-embedding-ada-002
andgpt-35-turbo
models. Use the settings as per the screenshot. You can any name for the deployment but this is needed later on when we will configure the app.- text-embedding-ada-002: Use model name:
text-embedding-ada-002
and model version:2
. Rate limit can be set to default value. - gpt-35-turbo: Use model name:
gpt-35-turbo
and model version:0125
. Rate limit can be set to default value.
Note: The availability of models varies based on the region and subscription.
- text-embedding-ada-002: Use model name:
- Once a model deployment is created (like the 2 deployments on the screenshot above), you will be able to access the model from an endpoint. Go back to the instance created in step 2 and 3. Click “keys and Endpoint” on the side panel to get the API access.
- Keep the following information handy for the deployment in the next steps:
- AZURE_OPENAI_ENDPOINT: Endpoint URL from step 6.
- AZURE_OPENAI_DEPLOYMENT: Deployment name of gpt-35-turbo model from step 5.
- AZURE_OPENAI_MODEL: Deployment model like gpt-35-turbo from step 5.
- AZURE_OPENAI_API_KEY: Key from step 6, Only one key is needed.
All the required infrastructure components will be deployed at this stage, please proceed to deploy the application