Delphi OpenAI API

logo

GitHub GitHub

This repositorty contains Delphi implementation over OpenAI public API.

❗This is an unofficial library. OpenAI does not provide any official library for Delphi.

Compatibility

Also, the library is compatible with the following AI APIs (tested):

OpenAI Azure
DeepSeek
YandexGPT
Qwen
GigaChat

and other compatible with the OpenAI API.

What is OpenAI
Installation
Usage
Examples
Requirements
Links
License

<details> <summary> Coverage </summary>

|API|Status| |---|---| |Models|🟢 Done| |Completions (Legacy)|🟢 Done| |Chat|🟢 Done| |Chat Vision|🟢 Done| |Edits|🟢 Done| |Images|🟢 Done| |Embeddings|🟢 Done| |Audio|🟢 Done| |Files|🟢 Done| |Fine-tunes (Depricated)|🟢 Done| |Fine-tuning|🟢 Done| |Moderations|🟢 Done| |Engines (Depricated)|🟢 Done| |Assistants|🟠 In progress| |Threads|🟠 In progress| |Messages|🟠 In progress| |Runs|🟠 In progress|

</details>

What is OpenAI

OpenAI is a non-profit artificial intelligence research organization founded in San Francisco, California in 2015. It was created with the purpose of advancing digital intelligence in ways that benefit humanity as a whole and promote societal progress. The organization strives to develop AI (Artificial Intelligence) programs and systems that can think, act and adapt quickly on their own – autonomously. OpenAI's mission is to ensure safe and responsible use of AI for civic good, economic growth and other public benefits; this includes cutting-edge research into important topics such as general AI safety, natural language processing, applied reinforcement learning methods, machine vision algorithms etc.

The OpenAI API can be applied to virtually any task that involves understanding or generating natural language or code. We offer a spectrum of models with different levels of power suitable for different tasks, as well as the ability to fine-tune your own custom models. These models can be used for everything from content generation to semantic search and classification.

This library provides access to the API of the OpenAI service, on the basis of which ChatGPT works and, for example, the generation of images from text using DALL-E.

Installation

You can install the package from GetIt directly in the IDE. Or, to use the library, just add the root folder to the IDE library path, or your project source path.

Usage

Initialization

To initialize API instance you need to obtain API token from your Open AI organization.

Once you have a token, you can initialize TOpenAI class, which is an entry point to the API.

Due to the fact that there can be many parameters and not all of them are required, they are configured using an anonymous function.

uses OpenAI;

var OpenAI := TOpenAIComponent.Create(Self, API_TOKEN);

uses OpenAI;

var OpenAI: IOpenAI := TOpenAI.Create(API_TOKEN);

Once token you posses the token, and the instance is initialized you are ready to make requests.

Models

List and describe the various models available in the API. You can refer to the Models documentation to understand what models are available and the differences between them.

var Models := OpenAI.Model.List();
try
  for var Model in Models.Data do
    MemoChat.Lines.Add(Model.Id);
finally
  Models.Free;
end;

Review Models Documentation for more info.

Completions

Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.

var Completions := OpenAI.Completion.Create(
  procedure(Params: TCompletionParams)
  begin
    Params.Prompt(MemoPrompt.Text);
    Params.MaxTokens(2048);
  end);
try
  for var Choice in Completions.Choices do
    MemoChat.Lines.Add(Choice.Index.ToString + ' ' + Choice.Text);
finally
  Completions.Free;
end;

Review Completions Documentation for more info.

Chats

Given a chat conversation, the model will return a chat completion response. ChatGPT is powered by gpt-3.5-turbo, OpenAI’s most advanced language model.

Using the OpenAI API, you can build your own applications with gpt-3.5-turbo to do things like:

Draft an email or other piece of writing
Write Python code
Answer questions about a set of documents
Create conversational agents
Give your software a natural language interface
Tutor in a range of subjects
Translate languages
Simulate characters for video games and much more

This guide explains how to make an API call for chat-based language models and shares tips for getting good results.

var Chat := OpenAI.Chat.Create(
  procedure(Params: TChatParams)
  begin
    Params.Messages([TChatMessageBuild.Create(TMessageRole.User, Text)]);
    Params.MaxTokens(1024);
  end);
try
  for var Choice in Chat.Choices do
    MemoChat.Lines.Add(Choice.Message.Content);
finally
  Chat.Free;
end;

Stream mode

OpenAI.Chat.CreateStream(
  procedure(Params: TChatParams)
  begin
    Params.Messages([TchatMessageBuild.User(Buf.Text)]);
    Params.MaxTokens(1024);
    Params.Stream;
  end,
  procedure(Chat: TChat; IsDone: Boolean; var Cancel: Boolean)
  begin
    if (not IsDone) and Assigned(Chat) then
      Writeln(Chat.Choices[0].Delta.Content)
    else if IsDone then
      Writeln('DONE!');
    Writeln('-------');
    Sleep(100);
  end);

Vision

var Chat := OpenAI.Chat.Create(
  procedure(Params: TChatParams)
  begin
    Params.Model('gpt-4-vision-preview');

    var Content: TArray<TMessageContent>;
    Content := Content + [TMessageContent.CreateText(Text)];
    Content := Content + [TMessageContent.CreateImage(FileToBase64('file path'))];

    Params.Messages([TChatMessageBuild.User(Content)]);
    Params.MaxTokens(1024);
  end);
try
  for var Choice in Chat.Choices do
    MemoChat.Lines.Add(Choice.Message.Content);
finally
  Chat.Free;
end;

Review Chat Documentation for more info.

Images

Given a prompt and/or an input image, the model will generate a new image.

var Images := OpenAI.Image.Create(
  procedure(Params: TImageCreateParams)
  begin
    Params.Prompt(MemoPrompt.Text);
    Params.ResponseFormat('url');
  end);
try
  for var Image in Images.Data do
    Image1.Bitmap.LoadFromUrl(Image.Url);
finally
  Images.Free;
end;

Review Images Documentation for more info.

Function Calling

In an API call, you can describe functions to gpt-3.5-turbo-0613 and gpt-4-0613, and have the model intelligently choose to output a JSON object containing arguments to call those functions. The Chat Completions API does not call the function; instead, the model generates JSON that you can use to call the function in your code.

The latest models (gpt-3.5-turbo-0613 and gpt-4-0613) have been fine-tuned to both detect when a function should to be called (depending on the input) and to respond with JSON that adheres to the function signature. With this capability also comes potential risks. We strongly recommend building in user confirmation flows before taking actions that impact the world on behalf of users (sending an email, posting something online, making a purchase, etc).

var Chat := OpenAI.Chat.Create(
  procedure(Params: TChatParams)
  begin
    Params.Functions(Funcs);  //list of functions (TArray<IChatFunction>)
    Params.FunctionCall(TFunctionCall.Auto);
    Params.Messages([TChatMessageBuild.User(Text)]);
    Params.MaxTokens(1024);
  end);
try
  for var Choice in Chat.Choices do
    if Choice.FinishReason = TFinishReason.FunctionCall then
      ProcFunction(Choice.Message.FunctionCall)  // execute function (send result to chat, and continue)
    else
      MemoChat.Lines.Add(Choice.Message.Content);
finally
  Chat.Free;
end;

...

procedure ProcFunction(Func: TChatFunctionCall);
begin
  var FuncResult := Execute(Func.Name, Func.Arguments);  //execute function and get result (json)
  var Chat := OpenAI.Chat.Create(
    procedure(Params: TChatParams)
    begin
      Params.Functions(Funcs);  //list of functions (TArray<IChatFunction>)
      Params.FunctionCall(TFunctionCall.Auto);
      Params.Messages([  //need all history
         TChatMessageBuild.User(Text), 
         TChatMessageBuild.NewAsistantFunc(Func.Name, Func.Arguments), 
         TChatMessageBuild.Func(FuncResult, Func.Name)]);
      Params.MaxTokens(1024);
    end);
  try
    for var Choice in Chat.Choices do
      MemoChat.Lines.Add(Choice.Message.Content);
  finally
    Chat.Free;
  end;
end;

Review Functions Documentation for more info.

Errors

try
  var Images := OpenAI.Image.Creat

DelphiOpenAI

Install / Use

README