Azure OpenAI Chat with File using Guide

Back Next

Step 3: Configure and publish the processes

Configure the deployment details of the LLM model and publish the processes.

To publish the

Get Content from File

process, click Actions
in the row that contains the process and select Publish
.

Open the

Chat with File

process.

On the Temp Fields
tab of the Start step, enter values for the following fields:

In the deployment_id
field, enter the deployment ID of the LLM model.

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

Optionally, in the

Configure Request Parameters

step, enter the prompt instructions in the

Assignments

field by updating the

Prompt_Configuration

field using the Expression Editor, as shown in the following sample code:

For Prompt_Configuration: 
 <GenerationConfig_AzureAI>
   <temperature>0.5</temperature>
   <topP>1</topP>
   <max_tokens>1000</max_tokens>
</GenerationConfig_AzureAI>

For the

Prompt_Configuration

field, enter values for the following properties:

Property	Description
temperature	Controls the randomness of the model's output. A lower value close to 0 makes the output more deterministic, while a higher value close to 1 increases randomness and creativity. For example, if temperature is set to 0.5, the model balances between deterministic and creative outputs.
topP	Determines the cumulative probability threshold for token selection. The model considers the smallest set of tokens whose cumulative probability meets or exceeds topP . For example, if topP is set to 0.1, the model considers only the top 10% most probable tokens at each step.
max_tokens	Defines the token count of your prompt. The max_tokens can't exceed the model's context length. Most of the models have a context length of 2048 tokens.

Optionally, in the

Prepare Request

step, enter the prompt instructions in the

Assignments

field by updating the

Request

field using the Expression Editor, as shown in the following sample code:

For Request:
<CreateChatCompletionRequest>
 <temperature>{$temp.Prompt_Configuration[1]/temperature  }</temperature>
   <top_p>{$temp.Prompt_Configuration[1]/top_p }</top_p>
   <max_tokens>{$temp.Prompt_Configuration[1]/max_tokens }</max_tokens>
<messages>
    <role>user</role>
    <content>You are a helpful assistant.{$temp.Content_From_File}</content>
</messages>
<messages>
    <role>user</role>
    <content>{$input.User_Prompt}</content>
</messages>
</CreateChatCompletionRequest>

Save and publish the process.

Using the Azure OpenAI Chat with File using Guide recipe

Download Guide

Watch

Comments

Cloud Application Integration Homepage