OpenAI Chat Completions API: How do I extract the message content from the response?

Question

When receiving a response from OpenAI's text-davinci-003 model, I was able to extract the text from the response with the following PHP code:

$response = $response->choices[0]->text;

Here was the text-davinci-003 response code:

{
  "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7",
  "object": "text_completion",
  "created": 1589478378,
  "model": "text-davinci-003",
  "choices": [
    {
      "text": "\n\nThis is indeed a test",
      "index": 0,
      "logprobs": null,
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 5,
    "completion_tokens": 7,
    "total_tokens": 12
  }
}

I am now trying to alter my code to work with the recently released gpt-3.5-turbo model which returns the response slightly differently:

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "\n\nHello there, how may I assist you today?",
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

My question is, how can I alter the code:

$response = $response->choices[0]->text;

...so that it can grab the content of the response message?

Answer 1

Python:

• If you have the OpenAI Python SDK <v1:

print(response['choices'][0]['message']['content'])

• If you have the OpenAI Python SDK v1:

print(response.choices[0].message.content)

Node.js:

• If you have the OpenAI Node.js SDK v3:

console.log(response.data.choices[0].message.content);

• If you have the OpenAI Node.js SDK v4:

console.log(response.choices[0].message.content);

PHP:

var_dump($response->choices[0]->message->content);

Working example in PHP

If you run test.php, the OpenAI API will return the following completion:

string(40) "

The capital city of England is London."

test.php

<?php
    $ch = curl_init();

    $url = 'https://api.openai.com/v1/chat/completions';

    $api_key = 'sk-xxxxxxxxxxxxxxxxxxxx';

    $query = 'What is the capital city of England?';

    $post_fields = array(
        "model" => "gpt-3.5-turbo",
        "messages" => array(
            array(
                "role" => "user",
                "content" => $query
            )
        ),
        "max_tokens" => 12,
        "temperature" => 0
    );

    $header  = [
        'Content-Type: application/json',
        'Authorization: Bearer ' . $api_key
    ];

    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt($ch, CURLOPT_POST, 1);
    curl_setopt($ch, CURLOPT_POSTFIELDS, json_encode($post_fields));
    curl_setopt($ch, CURLOPT_HTTPHEADER, $header);

    $result = curl_exec($ch);
    if (curl_errno($ch)) {
        echo 'Error: ' . curl_error($ch);
    }
    curl_close($ch);

    $response = json_decode($result);
    var_dump($response->choices[0]->message->content);
?>