This use case demonstrates how to provide a simple question to the specified OpenAI model. The simple prompt focuses on clarity and conciseness, avoiding complex phrasing or unnecessary details that can potentially confuse the model.

1. Configure a REST Adapter trigger connection.
2. Configure an OpenAI Adapter invoke connection. See Create a Connection.
3. Create an application integration.
4. Drag the REST Adapter trigger connection into the integration canvas for configuration. For this example, the REST Adapter is configured as follows:
   • A REST Service URL of /extended is specified for this example.
   • A Method of POST is selected.
   • A Request Media Type of JSON is selected and the following sample JSON structure is specified:

     { "model" : "gpt-4o", "input" : "register the functions for tool calling"
         }

   • A Response Media Type of JSON is selected and the following sample JSON structure is specified:

     { "id" : "resp_682b6c897b408198aff19b602ca3f0a20b404da49e82c3e4", "object" : "response", 
     "created_at" : 1747676297, "status" : "completed", "model" : "gpt-4o-2024-08-06", "output" : 
     [ { "id" : "msg_682b6c8a1fd08198b585adaae3f27b6e0b404da49e82c3e4", "type" : "message", "status" : 
     "completed", "content" : [ { "type" : "output_text", "text" : "Welcome! How can I assist you today?" } ], 
     "role" : "assistant" } ], "parallel_tool_calls" : true, "previous_response_id" : "abcd", "reasoning" : 
     { "effort" : "abcd", "summary" : "abcd" }, "service_tier" : "default", "store" : true, "temperature" : 1.0, 
     "text" : { "format" : { "type" : "text" } }, "tool_choice" : "auto", "top_p" : 1.0, "truncation" : "disabled", 
     "usage" : { "input_tokens" : 12, "input_tokens_details" : { "cached_tokens" : 0 }, "output_tokens" : 10, 
     "output_tokens_details" : { "reasoning_tokens" : 0 }, "total_tokens" : 22 } }

5. Drag the OpenAI Adapter invoke connection into the integration canvas and configure it as follows.
   1. From the OpenAI LLM Models list, select the model to use (for this example, gpt-4o is selected).
   2. From the Request Type list, select Simple Prompt.
6. In the request mapper, map the source Input element to the target Input element.
   
   

   

   
   
7. In the response mapper, expand the source Body element and target Response Wrapper element.
   
   

   

   
   
8. Perform the following source-to-target mappings.
   
   

   

   
   
9. Specify a business identifier and activate the integration.

   The completed integration looks as follows:
   
   

10. From the Actions menu, select Run.
    The Configure and run page appears.
11. In the Body field of the Request section, enter the following content, then click Run.
    • input: Enter the text input to the model.
    • model: Specify the model ID to generate the response. This is the model you selected when configuring the OpenAI Adapter in the integration.

    {
      "input": "In Which country is San Francisco located",
      "model": "gpt-4o"
    }

    The Body field of the Response section returns the following output. The country in which San Francisco is located is returned.

    {
      "id" : "resp_6845cb5f623881998e1652ac9d60b669087e7c84ef2dd435",
      "object" : "response",
      "created_at" : 1749404511,
      "status" : "completed",
      "model" : "gpt-4o-2024-08-06",
      "output" : [ {
        "id" : "msg_6845cb5fcc0c81998c5e8fe27d92ff66087e7c84ef2dd435",
        "type" : "message",
        "content" : [ {
          "type" : "output_text",
          "text" : "San Francisco is located in the United States."
        } ]
      } ],
      "parallel_tool_calls" : true,
      "reasoning" : {
        "effort" : ""
      },
      "temperature" : 1,
      "text" : {
        "format" : {
          "type" : "text"
        }
      },
      "tool_choice" : "auto",
      "top_p" : 1,
      "truncation" : "disabled"
    }

12. Expand the activity stream to view the flow of the messages sent and received.
    • Message sent by the invoke connection to the OpenAI model:

      
      
      

    • Message received by the invoke connection from the OpenAI model: