Connect to Azure OpenAI
This page provides step-by-step instructions for connecting Kibana to large language models (LLMs) in Azure OpenAI. You’ll first need to configure Azure, then connect Kibana to your deployment.
First, set up an Azure OpenAI deployment:
- Log in to the Azure console and search for Azure OpenAI.
- In Azure AI services, select Create.
- For the Project Details, select your subscription and resource group. If you don’t have a resource group, select Create new to make one.
- For Instance Details, select the desired region and specify a name, such as
example-deployment-openai. - Select the Standard pricing tier, then click Next.
- Configure your network settings, click Next, optionally add tags, then click Next.
- Review your deployment settings, then click Create. When complete, select Go to resource.
The following video demonstrates these steps (click to watch).
Next, create access keys for the deployment:
- From within your Azure OpenAI deployment, select Click here to manage keys.
- Store your keys in a secure location.
The following video demonstrates these steps (click to watch).
Now, set up the Azure OpenAI model:
From within your Azure OpenAI deployment, select Model deployments, then click Manage deployments.
On the Deployments page, select Create new deployment.
Under Select a model, choose a model.
Set the model version to "Auto-update to default".
ImportantThe models available to you depend on region availability. For more information on how different models perform for different tasks, refer to the Large language model performance matrix.
Under Deployment type, select Standard.
Name your deployment.
Slide the Tokens per Minute Rate Limit to the maximum. The following example supports 80,000 TPM, but other regions might support higher limits.
Click Create.
The following video demonstrates these steps (click to watch).
Create an inference endpoint so that Kibana can use models from Azure OpenAI. AI features in Kibana can use only endpoints with the chat_completion task type. For more information about adding endpoints, refer to External inference.
- Go to the External inference page by using the navigation menu or the global search field.
- Select Add endpoint.
- Select Azure OpenAI as the service.
- For Resource Name, enter the name of your Azure OpenAI resource. For Deployment ID, enter the name that you gave your deployment.
- For API Version, enter an API version that your deployment supports.
- For API Key, enter one of your API keys.
- Select the
chat_completiontask type, then select Save.
Create an OpenAI connector that points to your Azure OpenAI deployment so that Kibana can use it.
Log in to Kibana.
Find the Connectors page in the navigation menu or use the global search field. Then click Create Connector, and select OpenAI.
Give your connector a name to help you keep track of different models, such as
Azure OpenAI (GPT-4 Turbo v. 0125).For Select an OpenAI provider, choose Azure OpenAI.
Update the URL field. We recommend doing the following:
- Navigate to your deployment in Azure AI Studio and select Open in Playground. The Chat playground screen displays.
- Select View code, then from the drop-down, change the Sample code to
Curl. - Highlight and copy the URL without the quotes, then paste it into the URL field in Kibana.
- (Optional) Alternatively, refer to the API documentation to learn how to create the URL manually.
Under API key, enter one of your API keys.
(Optional) In the Default model field, enter a model name, for example gpt-4o.NoteThis field is only required if you're routing requests through Azure API Management (APIM) or another proxy endpoint that cannot infer the model from the deployment URL. Standard Azure OpenAI deployments do not need it. When set, the value acts as a fallback: it is only injected into the request body when the request does not already specify a model.
Click Save & test, then click Run.
Your LLM connector is now configured. The following video demonstrates these steps (click to watch).
