EmbedThis

Appearance

OpenAI Responses API ​

​OpenAI's Responses is newly introduced API designed to help developers create advanced AI agents and workflows capable of performing tasks cloud-based tasks like web searches, file retrievals, and computer operations on behalf of users. This API streamlines the integration of OpenAI models with built-in tools, eliminating the need for multiple APIs or external services. ​

Features of the Responses API: ​

Built-in Tools: The API offers tools such as web search, file search, and computer use, enabling agents to access real-time information, retrieve specific documents, and perform tasks on a user's device. ​ OpenAI Developer Community

Simplified Development: By combining the simplicity of Chat Completions with enhanced tool usage and state management, the Responses API facilitates the creation of more dynamic and capable AI experiences. ​

API Tour ​

Here is an example calling the Responses API to ask a simple question. This example uses file search (aka RAG) to augment the pre-trained knowledge of the LLM.

c
#include "ioto.h"

void example(void)
{
    cchar *vectorId = "PUT_YOUR_VECTOR_ID_HERE";
    char  buf[1024];

    /*
        SDEF is used to catentate literal strings into a single string.
        SFMT is used to format strings with variables.
        jsonParse converts the string into a json object.
     */
    Json *request = jsonParse(SFMT(buf, SDEF({
        model: 'gpt-4o-mini',
        input: 'What is the capital of the moon?',
        tools: [{
            type: 'file_search',
            vector_store_ids: ['%s'],
        }],
    }), vectorId), 0);

    Json *response = openaiResponses(request);

    // Extract the LLM response text from the json payload
    text = jsonGet(response, "output_text", 0);
    printf("Response: %s\n", text);

    jsonFree(request);
    jsonFree(response);
}

The openaiResponses API takes a JSON object which represents the Response parameters. The SDEF macro is a convenience to make it easier to define JSON objects in C code. The SFMT macro expands printf style expressions. The jsonParse API parses the supplied string and returns an Ioto Json object which can be passed to the openaiResponses API.

If you are using local tools, you can pass an "agent" callback as the 2nd parameter to the openaiResponses API. This callback is invoked when the LLM needs to invoke a local tool. The callback is passed the tool name and the request and response JSON objects. The callback should return a string containing the results of the tool call.

The response object returned by the openaiResponses API is a JSON object that can be queried using the Ioto JSON library jsonGet API. The output_text field contains the complete response output text.

Consult the Responses API for parameter details.

See the ai app in the Ioto Agent source download for an example response.html web page that uses the Responses API.

References ​

Consult the OpenAI documentation for API details: