Azure Cloud
Use Azure-hosted OpenAI models with your own Azure API Key
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.
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
Credentials
Use your own Azure API credentials (from Azure OpenAI resource).
Model
Select the model to be used (based on your Azure deployment, e.g., gpt-35-turbo, gpt-4, etc.).
Prompt
Customize how the model should respond. You can reference values from other components using @, and structure the prompt using dynamic variables.
Advanced configurations
Enable caching
When enabled, stores the result of this component to be reused if input hasn't changed.
Caching time
If caching is enabled, this controls how long the result stays cached.
Outputs
The Azure component has the following output connections.
To Output
Contains the response text from the Azure OpenAI model.
Can be connected to any component that accepts text input.
Last updated
Was this helpful?