> For the complete documentation index, see [llms.txt](https://docs.diaflow.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.diaflow.io/workflow-builder/nodes/public-ai-llm-models/azure-cloud.md).

# Azure Cloud

<figure><img src="/files/1G3megTQ3XiwiYsYqWf1" alt=""><figcaption></figcaption></figure>

## **Description**

The Azure OpenAI component allows you to integrate Azure-hosted OpenAI models into your flows using your own Azure credentials. You can customize the parameters used by the Azure OpenAI component, specify the context (such as a file or structured data), and provide the user’s input query.

The component interface adapts depending on the selected model, allowing you to choose from chat-based models like GPT-3.5, GPT-4, or others depending on your Azure deployment. See the Parameters section for more detail on the configuration options.

The Azure OpenAI component has the identifier `azure-opa-X`, where `X` represents the instance number of the component in your flow.

## Inputs

The Azure Cloud component has the following input connections.

| Input Name                               | Description                                                                          | Constraints                                                                         |
| ---------------------------------------- | ------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------- |
| From data Loaders/ Data source/Vector DB | This input provides the context for the Azure OpenAI model to use during generation. | Must originate from a Data Loader/Data Source or VectorDB component.                |
| From Input                               | This is the user’s query to the Azure OpenAI model.                                  | Must come from a component outputting text, such as a Text Input, Form, or Trigger. |

## Component settings

<table><thead><tr><th width="190.4296875">Parameter Name</th><th>Description</th></tr></thead><tbody><tr><td>Credentials</td><td>Use your own Azure API credentials (from Azure OpenAI resource).</td></tr><tr><td>Model</td><td></td></tr><tr><td>Prompt</td><td>Customize how the model should respond. You can reference values from other components using <code>@</code>, and structure the prompt using dynamic variables.</td></tr></tbody></table>

| Select the model to be used (based on your Azure deployment, e.g., `gpt-35-turbo`, `gpt-4`, etc.). |
| -------------------------------------------------------------------------------------------------- |

## Advanced configurations

<table><thead><tr><th width="188.21484375">Options</th><th>Description</th></tr></thead><tbody><tr><td>Enable caching</td><td>When enabled, stores the result of this component to be reused if input hasn't changed.</td></tr><tr><td>Caching time</td><td>If caching is enabled, this controls how long the result stays cached.</td></tr></tbody></table>

## Outputs

The Azure component has the following output connections.

| Output Name | Description                                             | Constraints                                                |
| ----------- | ------------------------------------------------------- | ---------------------------------------------------------- |
| To Output   | Contains the response text from the Azure OpenAI model. | Can be connected to any component that accepts text input. |