chat_gpt_sdk 3.1.4

create chat bot and other bot with ChatGPT SDK Support GPT-4 , 3.5 and SSE Generate Prompt (Stream)

ChatGPT Application with flutter

ChatGPT is a chat-bot launched by OpenAI in November 2022. It is built on top of OpenAI's GPT-3.5 family of large language models, and is fine-tuned with both supervised and reinforcement learning techniques.

Unofficial

"community-maintained” library.

OpenAI Powerful Library Support GPT-4

Features

• ✅ Install Package
• ✅ Create OpenAI Instance
• ✅ Change Access Token
• ✅ Complete Text
  • Complete with Future
  • Support Server Sent Event
• ✅ Chat Complete GPT-4
  • Support GPT3.5 and GPT-4
  • Support Server Sent Event
  • Support Function Calling
  • Chat Complete Image Input
• ✅ Assistants API
  • Create assistant
  • Create assistant file
  • List assistants
  • List assistant files
  • Retrieve assistant
  • Retrieve assistant file
  • Modify assistant
  • Delete assistant
  • Delete assistant file
  • Using Assistants V2
• Threads
  • Create thread
  • Retrieve thread
  • Modify thread
  • Delete thread
  • Using Thread V2
• Messages
  • Create message
  • List messages
  • List message files
  • Retrieve message
  • Retrieve message file
  • Modify message
  • Using Message V2
• Runs
  • Create run
  • Create thread and run
  • List runs
  • List run steps
  • Retrieve run
  • Retrieve run step
  • Modify run
  • Submit tool outputs to run
  • Cancel a run
• ✅ Error Handle
• ✅ Example Q&A
• ✅ Generate Image With Prompt
• ✅ Editing
  • Edit Prompt
  • Edit Image
  • Variations
• ✅ Cancel Generate
  • Stop Generate Prompt
  • Stop Edit
  • Stop Embedding
• ✅ File
  • Get File
  • Upload File
  • Delete File
  • Retrieve File
  • Retrieve Content File
• ✅ Audio
  • Audio Translate
  • Audio Transcribe
  • Create speech
• ✅ Embedding
• ✅ Fine-Tune
  • Create Fine Tune
  • Fine Tune List
  • Fine Tune List Stream (SSE)
  • Fine Tune Get by Id
  • Cancel Fine Tune
  • Delete Fine Tune
  • Fine-Tune Deprecate
  • New Fine-Tune Job
• ✅ Moderations
  • Create Moderation
• ✅ Model And Engine
• ✅ Translate Example
• ✅ Video Tutorial
• ✅ Docs

Install Package

chat_gpt_sdk: 3.1.4

Create OpenAI Instance

• Parameter
  • Token
    • Your secret API keys are listed below. Please note that we do not display your secret API keys again after you generate them.
    • Do not share your API key with others, or expose it in the browser or other client-side code. In order to protect the security of your account, OpenAI may also automatically rotate any API key that we've found has leaked publicly.
    • https://beta.openai.com/account/api-keys
• OrgId
  • Identifier for this organization sometimes used in API requests
  • https://beta.openai.com/account/org-settings

final openAI = OpenAI.instance.build(token: token,baseOption: HttpSetup(receiveTimeout: const Duration(seconds: 5)),enableLog: true);

Change Access Token

openAI.setToken('new-access-token');
///get token
openAI.token;

Complete Text

• Text Complete API

  • Translate Method
    • translateEngToThai
    • translateThaiToEng
    • translateToJapanese
  • Model
    • kTranslateModelV3
    • kTranslateModelV2
    • kCodeTranslateModelV2
      • Translate natural language to SQL queries.
      • Create code to call the Stripe API using natural language.
      • Find the time complexity of a function.
  • https://beta.openai.com/examples

• Complete with Feature

  void _translateEngToThai() async{
  final request = CompleteText(
          prompt: translateEngToThai(word: _txtWord.text.toString()),
          maxToken: 200,
          model: TextDavinci3Model());

  final response = await openAI.onCompletion(request: request);
  
  ///cancel request
  openAI.cancelAIGenerate();
  print(response);
}

• Complete with FutureBuilder

Future<CTResponse?>? _translateFuture;

_translateFuture = openAI.onCompletion(request: request);

///ui code
FutureBuilder<CTResponse?>(
 future: _translateFuture,
 builder: (context, snapshot) {
   final data = snapshot.data;
   if(snapshot.connectionState == ConnectionState.done) return something 
   if(snapshot.connectionState == ConnectionState.waiting) return something
   return something
})

• GPT 3 with SSE

 void completeWithSSE() {
  final request = CompleteText(
          prompt: "Hello world", maxTokens: 200, model: TextDavinci3Model());
  openAI.onCompletionSSE(request: request).listen((it) {
    debugPrint(it.choices.last.text);
  });
}

Chat Complete (GPT-4 and GPT-3.5)

• Chat Complete

  void chatComplete() async {
    final request = ChatCompleteText(messages: [
      Map.of({"role": "user", "content": 'Hello!'})
    ], maxToken: 200, model: Gpt4ChatModel());

    final response = await openAI.onChatCompletion(request: request);
    for (var element in response!.choices) {
      print("data -> ${element.message?.content}");
    }
  }

• GPT 4 with SSE

 void chatCompleteWithSSE() {
  final request = ChatCompleteText(messages: [
    Map.of({"role": "user", "content": 'Hello!'})
  ], maxToken: 200, model: Gpt4ChatModel());

  openAI.onChatCompletionSSE(request: request).listen((it) {
    debugPrint(it.choices.last.message?.content);
  });
}

• Support SSE(Server Send Event)
  • GPT-3.5 Turbo

 void chatCompleteWithSSE() {
  final request = ChatCompleteText(messages: [
    Map.of({"role": "user", "content": 'Hello!'})
  ], maxToken: 200, model: GptTurboChatModel());

  openAI.onChatCompletionSSE(request: request).listen((it) {
    debugPrint(it.choices.last.message?.content);
  });
}

• Chat Complete

  void chatComplete() async {
    final request = ChatCompleteText(messages: [
      Map.of({"role": "user", "content": 'Hello!'})
    ], maxToken: 200, model: Gpt41106PreviewChatModel());

    final response = await openAI.onChatCompletion(request: request);
    for (var element in response!.choices) {
      print("data -> ${element.message?.content}");
    }
  }

• Chat Complete Function Calling

  void gptFunctionCalling() async {
    final request = ChatCompleteText(
      messages: [
        Messages(
                role: Role.user,
                content: "What is the weather like in Boston?",
                name: "get_current_weather"),
      ],
      maxToken: 200,
      model: Gpt41106PreviewChatModel(),
      tools: [
        {
          "type": "function",
          "function": {
            "name": "get_current_weather",
            "description": "Get the current weather in a given location",
            "parameters": {
              "type": "object",
              "properties": {
                "location": {
                  "type": "string",
                  "description": "The city and state, e.g. San Francisco, CA"
                },
                "unit": {
                  "type": "string",
                  "enum": ["celsius", "fahrenheit"]
                }
              },
              "required": ["location"]
            }
          }
        }
      ],
      toolChoice: 'auto',
    );

    ChatCTResponse? response = await openAI.onChatCompletion(request: request);
}

• Chat Complete Image Input

  void imageInput() async {
  final request = ChatCompleteText(
    messages: [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "What’s in this image?"},
          {
            "type": "image_url",
            "image_url": {"url": "image-url"}
          }
        ]
      }
    ],
    maxToken: 200,
    model: Gpt4VisionPreviewChatModel(),
  );

  ChatCTResponse? response = await openAI.onChatCompletion(request: request);
  debugPrint("$response");
}

Assistants

• Create Assistant

  void createAssistant() async {
  final assistant = Assistant(
    model: Gpt4AModel(),
    name: 'Math Tutor',
    instructions:
    'You are a personal math tutor. When asked a question, write and run Python code to answer the question.',
    tools: [
      {
        "type": "code_interpreter",
      }
    ],
  );
  await openAI.assistant.create(assistant: assistant);
}

• Create Assistant File

void createAssistantFile() async {
  await openAI.assistant.createFile(assistantId: '',fileId: '',);
}

• List assistants

  void listAssistant() async {
  final assistants = await openAI.assistant.list();
  assistants.map((e) => e.toJson()).forEach(print);
}

• List assistants files

  void listAssistantFile() async {
  final assistants = await openAI.assistant.listFile(assistantId: '');
  assistants.data.map((e) => e.toJson()).forEach(print);
}

• Retrieve assistant

  void retrieveAssistant() async {
  final assistants = await openAI.assistant.retrieves(assistantId: '');
}

• Retrieve assistant file

  void retrieveAssistantFiles() async {
  final assistants = await openAI.assistant.retrievesFile(assistantId: '',fileId: '');
}

• Modify assistant

  void modifyAssistant() async {
  final assistant = Assistant(
    model: Gpt4AModel(),
    instructions:
    'You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.',
    tools: [
      {
        "type": "retrieval",
      }
    ],
    fileIds: [
      "file-abc123",
      "file-abc456",
    ],
  );
  await openAI.assistant.modifies(assistantId: '', assistant: assistant);
}

• Delete assistant

  void deleteAssistant() async {
  await openAI.assistant.delete(assistantId: '');
}

• Delete assistant file

  void deleteAssistantFile() async {
  await openAI.assistant.deleteFile(assistantId: '',fileId: '');
}

• Using assistant v2

openAI.assistant.v2;

Threads

• Create threads

///empty body
  void createThreads()async {
  await openAI.threads.createThread(request: ThreadRequest());
}

///with message
void createThreads() async {
  final request = ThreadRequest(messages: [
    {
      "role": "user",
      "content": "Hello, what is AI?",
      "file_ids": ["file-abc123"]
    },
    {
      "role": "user",
      "content": "How does AI work? Explain it in simple terms."
    },
  ]);

  await openAI.threads.createThread(request: request);
}

• Retrieve thread

 void retrieveThread()async {
  final mThread = await openAI.threads.retrieveThread(threadId: 'threadId');
}

• Modify thread

  void modifyThread() async {
  await openAI.threads.modifyThread(threadId: 'threadId', metadata: {
    "metadata": {
      "modified": "true",
      "user": "abc123",
    },
  });
}

• Delete thread

  void deleteThread() async {
  await openAI.threads.deleteThread(threadId: 'threadId');
}

• Using Thread V2

openAI.threads.v2;

Messages

• Create Message

void createMessage() async {
  final request = CreateMessage(
    role: 'user',
    content: 'How does AI work? Explain it in simple terms.',
  );
  await openAI.threads.messages.createMessage(
    threadId: 'threadId',
    request: request,
  );
}

• List messages

  void listMessage()async {
  final mMessages = await openAI.threads.messages.listMessage(threadId: 'threadId');
}

• List message files

  void listMessageFile() async {
  final mMessagesFile = await openAI.threads.messages.listMessageFile(
    threadId: 'threadId',
    messageId: '',
  );
}

• Retrieve message

  void retrieveMessage() async {
  final mMessage = await openAI.threads.messages.retrieveMessage(
    threadId: 'threadId',
    messageId: '',
  );
}

• Retrieve message file

void retrieveMessageFile() async {
  final mMessageFile = await openAI.threads.messages.retrieveMessageFile(
    threadId: 'threadId',
    messageId: '',
    fileId: '',
  );
}

• Modify message

  void modifyMessage() async {
  await openAI.threads.messages.modifyMessage(
    threadId: 'threadId',
    messageId: 'messageId',
    metadata: {
      "metadata": {"modified": "true", "user": "abc123"},
    },
  );
}

• Using Message V2

openAI.threads.v2.messages;

Runs

• Create run

void createRun() async {
    final request = CreateRun(assistantId: 'assistantId');
    await openAI.threads.runs.createRun(threadId: 'threadId', request: request);
  }

• Create thread and run

  void createThreadAndRun() async {
    final request = CreateThreadAndRun(assistantId: 'assistantId', thread: {
      "messages": [
        {"role": "user", "content": "Explain deep learning to a 5 year old."}
      ],
    });
    await openAI.threads.runs.createThreadAndRun(request: request);
  }

• List runs

 void listRuns() async {
   final mRuns = await openAI.threads.runs.listRuns(threadId: 'threadId');
  }

• List run steps

void listRunSteps() async {
   final mRunSteps = await openAI.threads.runs.listRunSteps(threadId: 'threadId',runId: '',);
  }

• Retrieve run

void retrieveRun() async {
   final mRun = await openAI.threads.runs.retrieveRun(threadId: 'threadId',runId: '',);
  }

• Retrieve run step

 void retrieveRunStep() async {
   final mRun = await openAI.threads.runs.retrieveRunStep(threadId: 'threadId',runId: '',stepId: '');
  }

• Modify run

void modifyRun() async {
    await openAI.threads.runs.modifyRun(
      threadId: 'threadId',
      runId: '',
      metadata: {
        "metadata": {"user_id": "user_abc123"},
      },
    );
  }

• Submit tool outputs to run

  void submitToolOutputsToRun() async {
    await openAI.threads.runs.submitToolOutputsToRun(
      threadId: 'threadId',
      runId: '',
      toolOutputs: [
        {
          "tool_call_id": "call_abc123",
          "output": "28C",
        },
      ],
    );
  }

• Cancel a run

  void cancelRun() async {
    await openAI.threads.runs.cancelRun(
      threadId: 'threadId',
      runId: '',
    );
  }

Error Handle

///using catchError
 openAI.onCompletion(request: request)
    .catchError((err){
      if(err is OpenAIAuthError){
        print('OpenAIAuthError error ${err.data?.error?.toMap()}');
      }
      if(err is OpenAIRateLimitError){
        print('OpenAIRateLimitError error ${err.data?.error?.toMap()}');
      }
      if(err is OpenAIServerError){
        print('OpenAIServerError error ${err.data?.error?.toMap()}');
      }
      });

///using try catch
 try {
   await openAI.onCompletion(request: request);
 } on OpenAIRateLimitError catch (err) {
   print('catch error ->${err.data?.error?.toMap()}');
 }

///with stream
 openAI
        .onCompletionSSE(request: request)
        .transform(StreamTransformer.fromHandlers(
          handleError: (error, stackTrace, sink) {
              if (error is OpenAIRateLimitError) {
              print('OpenAIRateLimitError error ->${error.data?.message}');
              }}))
        .listen((event) {
          print("success");
        });

Q&A

• Example Q&A
  • Answer questions based on existing knowledge.

final request = CompleteText(prompt:'What is human life expectancy in the United States?'),
                model: TextDavinci3Model(), maxTokens: 200);

 final response = await openAI.onCompletion(request:request);

• Request

Q: What is human life expectancy in the United States?

• Response

A: Human life expectancy in the United States is 78 years.

Generate Image With Prompt

• Generate Image

  • prompt
    • A text description of the desired image(s). The maximum length is 1000 characters.
  • n
    • The number of images to generate. Must be between 1 and 10.
  • size
    • The size of the generated images. Must be one of 256x256, 512x512, or 1024x1024.
  • response_format
    • The format in which the generated images are returned. Must be one of url or b64_json.
  • user
    • A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

• Generate with feature

  void _generateImage() {
  const prompt = "cat eating snake blue red.";

  final request = GenerateImage( model: DallE2(),prompt, 1,size: ImageSize.size256,
          responseFormat: Format.url);
  final response = openAI.generateImage(request);
  print("img url :${response.data?.last?.url}");
}

Edit

• Edit Prompt

void editPrompt() async {
    final response = await openAI.editor.prompt(EditRequest(
        model: CodeEditModel(),
        input: 'What day of the wek is it?',
        instruction: 'Fix the spelling mistakes'));

    print(response.choices.last.text);
  }

• Edit Image

 void editImage() async {
  final response = await openAI.editor.editImage(EditImageRequest(
          image: FileInfo("${image?.path}", '${image?.name}'),
          mask: FileInfo('file path', 'file name'),
          size: ImageSize.size1024,
          prompt: 'King Snake'),
          model: DallE3(),);

  print(response.data?.last?.url);
}

• Variations

  void variation() async {
  final request =
  Variation(model: DallE2(),image: FileInfo('${image?.path}', '${image?.name}'));
  final response = await openAI.editor.variation(request);

  print(response.data?.last?.url);
}

Cancel Generate

• Stop Generate Prompt

 _openAI
        .onChatCompletionSSE(request: request, onCancel: onCancel);

///CancelData
CancelData? mCancel;
void onCancel(CancelData cancelData) {
  mCancel = cancelData;
}

mCancel?.cancelToken.cancel("canceled ");

• Stop Edit

  • image
  • prompt

openAI.edit.editImage(request,onCancel: onCancel);

///CancelData
CancelData? mCancel;
void onCancel(CancelData cancelData) {
  mCancel = cancelData;
}

mCancel?.cancelToken.cancel("canceled edit image");

• Stop Embedding

openAI.embed.embedding(request,onCancel: onCancel);

///CancelData
CancelData? mCancel;
void onCancel(CancelData cancelData) {
  mCancel = cancelData;
}

mCancel?.cancelToken.cancel("canceled embedding");

• Stop Audio
  • translate
  • transcript

openAI.audio.transcribes(request,onCancel: onCancel);

///CancelData
CancelData? mCancel;
void onCancel(CancelData cancelData) {
  mCancel = cancelData;
}

mCancel?.cancelToken.cancel("canceled audio transcribes");

• Stop File
  • upload file
  • get file
  • delete file

openAI.file.uploadFile(request,onCancel: onCancel);

///CancelData
CancelData? mCancel;
void onCancel(CancelData cancelData) {
  mCancel = cancelData;
}

mCancel?.cancelToken.cancel("canceled uploadFile");

File

• Get File

void getFile() async {
  final response = await openAI.file.get();
  print(response.data);
}

• Upload File

void uploadFile() async {
  final request = UploadFile(file: FileInfo('file-path', 'file-name'),purpose: 'fine-tune');
  final response = await openAI.file.uploadFile(request);
  print(response);
}

• Delete File

  void delete() async {
  final response = await openAI.file.delete("file-Id");
  print(response);
}

• Retrieve File

  void retrieve() async {
  final response = await openAI.file.retrieve("file-Id");
  print(response);
}

• Retrieve Content File

  void retrieveContent() async {
  final response = await openAI.file.retrieveContent("file-Id");
  print(response);
}

Audio

• Audio Translate

void audioTranslate() async {
  final mAudio = File('mp3-path');
  final request =
  AudioRequest(file: FileInfo(mAudio.path, 'name'), prompt: '...');

  final response = await openAI.audio.translate(request);
}

• Audio Transcribe

void audioTranscribe() async {
  final mAudio = File('mp3-path');
  final request =
  AudioRequest(file: FileInfo(mAudio.path, 'name'), prompt: '...');

  final response = await openAI.audio.transcribes(request);
}

• Create speech

  void createSpeech() async {
  final request = SpeechRequest(
          model: 'tts-1', input: 'The quick brown fox jumped over the lazy dog.');

  final List<int> response = await openAI.audio
          .createSpeech(request: request);
}

Embedding

• Embedding

void embedding() async {
  final request = EmbedRequest(
          model: TextSearchAdaDoc001EmbedModel(),
          input: 'The food was delicious and the waiter');

  final response = await openAI.embed.embedding(request);

  print(response.data.last.embedding);
}

Fine Tune

• Create Fine Tune

void createTineTune() async {
  final request = CreateFineTuneJob(trainingFile: 'The ID of an uploaded file');
  final response = await openAI.fineTune.createFineTuneJob(request);
}

• Fine Tune List

 void tineTuneList() async {
    final response = await openAI.fineTune.listFineTuneJob();
  }

• Fine Tune List Stream

 void tineTuneListStream() {
    openAI.fineTune.listFineTuneJobStream('fineTuneId').listen((it) {
      ///handled data
    });
  }

• Fine Tune Get by Id

void tineTuneById() async {
    final response = await openAI.fineTune.retrieveFineTuneJob('fineTuneId');
  }

• Cancel Fine Tune

  void tineTuneCancel() async {
    final response = await openAI.fineTune.cancel('fineTuneId');
  }

• Delete Fine Tune

 void deleteTineTune() async {
    final response = await openAI.fineTune.delete('model');
  }

Moderations

• Create Moderation

  void createModeration() async {
  final response = await openAI.moderation
          .create(input: 'input', model: TextLastModerationModel());
}

Model&Engine

• Model List
  • 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.
  • https://beta.openai.com/docs/api-reference/models

final models = await openAI.listModel();

• Engine List
  • Lists the currently available (non-finetuned) models, and provides basic information about each one such as the owner and availability.
  • https://beta.openai.com/docs/api-reference/engines

final engines = await openAI.listEngine();

Translate App

ChatGPT Demo App

Video Tutorials

• Flutter Chat bot

• Flutter Generate Image

Docs (Support Thai)