This is a script for tabular editor that will loop through all the measures in a model and get ChatGPT to write a description of the calculation.

AutoPopulateMeasureDescriptionsFromOpenAI.csx

#r "System.Net.Http"
using System.Net.Http;
using System.Text;
using Newtonsoft.Json.Linq;

// You need to signin to https://platform.openai.com/ and create an API key for your profile then paste that key 
// into the apiKey constant below
const string apiKey =  "<YOUR API KEY HERE>";
const string uri = "https://api.openai.com/v1/chat/completions";  //  Correct endpoint for GPT-4
const string question = "Explain the following calculation in a few sentences in simple business terms without using DAX function names:\n\n";

const int oneMinute = 60000; // the number of milliseconds in a minute
const int apiLimit = 20;     // a free account is limited to 20 calls per minute, change this if you have a paid account
const bool dontOverwrite = true; // this prevents existing descriptions from being overwritten

using (var client = new HttpClient()) {
    client.DefaultRequestHeaders.Clear();
    client.DefaultRequestHeaders.Add("Authorization", "Bearer " + apiKey);

    int callCount = 0;

    List<Measure> myMeasures = new List<Measure>();
    myMeasures.AddRange(Selected.Measures);

    if (myMeasures.Count == 0) {
        myMeasures.AddRange(Model.Tables.Where(t => t.Measures.Count() > 0).SelectMany(t => t.Measures));
    }

    foreach (var m in myMeasures) {
        if (dontOverwrite && !string.IsNullOrEmpty(m.Description)) continue;

        // === Construct valid JSON payload for chat/completions ===
        var messages = new JArray {
            new JObject {
                { "role", "system" },
                { "content", "You are a helpful assistant that explains DAX measures clearly." }
            },
            new JObject {
                { "role", "user" },
                { "content", question + m.Expression }
            }
        };

        var payload = new JObject {
            { "model", "gpt-4" },
            { "messages", messages },
            { "temperature", 0.2 },
            { "max_tokens", 800 }
        };

        var res = client.PostAsync(uri, new StringContent(payload.ToString(), Encoding.UTF8, "application/json"));
        res.Result.EnsureSuccessStatusCode();

        var result = res.Result.Content.ReadAsStringAsync().Result;
        var obj = JObject.Parse(result);
        var desc = obj["choices"][0]["message"]["content"].ToString().Trim();

        m.Description = desc + "\n=====\n" + m.Expression;

        callCount++;
        if (callCount % apiLimit == 0) System.Threading.Thread.Sleep(oneMinute);
    }
}

The previous model looks to have been deprecated.
New Model:
gpt-3.5-turbo-instruct\