Azure OpenAI Prompt Engineering

Back Next

Step 3. Configure and publish the process

Configure and publish the process so that it can submit prompts to Azure OpenAI.

Open the

Prompt Engineering AZURE Open AI

process.

In the

Start

step, use the

Temp Fields

tab to enter values for the following fields:

In the api_version
field, optionally enter the API version of the LLM model. Default is

2024-06-01

In the deployment_id
field, enter the user-specific deployment ID.

For information about changing the API version, see the Azure OpenAI documentation.

Optionally, in the

Configure Request Parameters

step, use the

Assignments

tab to edit the top_p, temperature, and max tokens for each request.

You can edit the code in the Expression Editor. For example:

<GenerationConfig_AzureAI>
	<top_p>1</top_p>
	<temperature>0.5</temperature>
	<max_tokens>500</max_tokens>
</GenerationConfig_AzureAI>

The following table describes the properties:

Property	Description
top_p	Determines the cumulative probability threshold for token selection. The model considers the smallest set of tokens whose cumulative probability meets or exceeds top_p. For example, if top_p is set to 0.1, the model considers only the top 10% most probable tokens at each step.
temperature	Controls the randomness of the model's output. A lower value makes the output more deterministic, while a higher value increases randomness and creativity. For example, a temperature of 0.5 balances between deterministic and creative outputs.
max_tokens	Defines the maximum number of tokens that the model can generate in its response. Setting a limit ensures that the response is concise and fits within the desired length constraints.