Use ChatGPT from Delphi

阿里云国内75折回扣微信号：monov8

阿里云国际，腾讯云国际，低至75折。AWS 93折免费开户实名账号代冲值优惠多多微信号：monov8 飞机：@monov6

For a couple of weeks now, ChatGPT is the talk of the town.

In record time, millions of users signed up and tested the new AI NLP service from OpenAI and are amazed by the answers for questions it comes up with.

For us Delphi developers, it's even more fun having the ability to go a step further and automate sending questions and getting answers from a Delphi app. This is possible thanks to the ChatGPT REST API.

We'd liked to present simple code here that shows how this can be done in any type of Delphi app (or even Lazarus Object Pascal app) on any platform. To ensure this code can be used in Windows, macOS, iOS, Android, Linux apps, we opted to use the TTMSFNCCloudBase class from TMS FNC Core. This offers a rich interface to perform REST API requests from any platform and any framework. To get started with the OpenAI ChatGPT API, request your API key here: https://beta.openai.com/account/api-keys

The code to ask questions and get answer from ChatGPT from a Delphi app is with TMS FNC TTMSCloudBase as simple as:

view plain text

uses
System.JSON, VCL.TMSFNCCloudBase;
function AskChatGPT(AQuestion: string): string;
var
LCb: TTMSFNCCloudBase;
LPostdata: string;
LJsonValue: TJsonValue;
LJsonArray: TJsonArray;
LJSonString: TJsonString;
begin
Result := '';
LPostData := '{' +
'"model": "text-davinci-003",'+
'"prompt": "' + AQuestion + '",'+
'"max_tokens": 2048,'+
'"temperature": 0'+
'}';
// create instance of TMS FNC Cloud Base class
LCb := TTMSFNCCloudBase.Create;
try
// Use JSON for the REST API calls and set API KEY via Authorization header
LCb.Request.AddHeader('Authorization','Bearer ' + CHATGPT_APIKEY);
LCb.Request.AddHeader('Content-Type','application/json');
// Select HTTPS POST method, set POST data and specify endpoint URL
LCb.Request.Method := rmPOST;
LCb.Request.PostData := LPostData;
LCb.Request.Host := 'https://api.openai.com';
LCb.Request.Path := 'v1/completions';
// Execute the HTTPS POST request synchronously (last param Async = false)
LCb.ExecuteRequest(nil,nil,false);
// Process returned JSON when request was successful
if Lcb.RequestResult.Success then
begin
LJsonValue := TJSonObject.ParseJSONValue(Lcb.RequestResult.ResultString);
LJsonValue := LJsonValue.GetValue<TJSonValue>('choices');
if LJsonValue is TJSonArray then
begin
LJSonArray := LJsonValue as TJSonArray;
LJSonString := LJSonArray.Items[0].GetValue<TJSONString>('text');
Result := LJSonString.Value;
end
else
end
else
raise Exception.Create('HTTP response code: ' + LCb.RequestResult.ResponseCode.ToString);
finally
LCb.Free;
end;
end;

With this code, using ChatGPT from a Delphi app becomes as simple as:

view plain text

procedure TForm1.Button1Click(Sender: TObject);
begin
Memo1.Lines.Text := AskChatGPT(Edit1.Text);
end;

When you want to use this in a FireMonkey cross-platform app, all you need to do is change in the uses list VCL.TMSFNCCloudBase to FMX.TMSFNCCloudBase. Or when you want to use this from Lazarus, change the unit name to LCLTMSFNCCloudBase.

Note that we do not mention TMS WEB Core here that TMS FNC also supports. This is because OpenAI specifies that the API key cannot be used in a web client application where this key would be visible to anyone.

You can get the app full source to replicate this test from Github. Make sure to download & install TMS FNC Core as well.

While playing a little bit with ChatGPT from the Delphi app, here are some of the answers it came up with:

And this was a question asked in connection with our TMS VCL TAdvStringGrid component and surprisingly, the answer is pretty spot-on and accurate. Who knows that shortly ChatGPT will make our support engineers redundant? :)