/hxopenai

This is an OpenAI Library for Haxe.

Primary LanguageHaxeMIT LicenseMIT

HxOpenAI

License Version

A Haxe library for interacting with the OpenAI API.

Credits: This library is inspired by the work of FurretDev.

Table of Contents

Installation

You can install the library using the following methods:

  • Method 1: Add it as a dependency in your haxelib.json file:
{
  "dependencies": {
    "hxopenai": "1.0.0"
  }
}
  • Method 2: Install it using Haxelib:

Ideally it would be best to simply haxelib install hxopenai, but there will be an issue with the naming and I haven't submitted the library just yet...

haxelib git hxopenai git@github.com:AxDSan/hxopenai.git

Usage

Import the library in your Haxe code:

import hxopenai.Instance;

Create an instance of the library:

var openai = new Instance();
openai.setApiKey("YOUR_OPENAI_API_KEY");
openai.setOrgId("YOUR_OPENAI_ORG_ID"); /* Optional */

You can obtain a openai api key from https://platform.openai.com/account/api-keys

Make requests to the OpenAI API using the available methods:

var textCompletion = {
  model: "your_model",
  prompt: "your_prompt",
  // Additional parameters...
};

var response = openai.createTextCompletion(textCompletion);

Examples

If you're not a code adept and don't really want to dig the documentation (under construction) here you can find some bites set out for you; Examples on how you can use the library.

// Example 1 - TextCompletion using `text-davinci-003`
import hxopenai.*;

class Main {
    static function main() {
        var openai = new Instance();
        openai.setApiKey("<YOUR-OPENAI-API-KEY>");

        // Create a text completion.
        var textCompletion:Typedefs.TextCompletion = {
            prompt: "Once upon a time",
            max_tokens: 256,
            top_p: 1,
            n: 1,
            stream: false,
            logprobs: null,
            echo: false,
            stop: ["\n"],
            model: "text-davinci-003",
        };

        // Make the request.
        var response = openai.createTextCompletion(textCompletion);

        // Print the response.
        trace(response.choices[0].text);
    }
}
// Example 2 - ChatCompletion using `gpt-3.5-turbo`
import hxopenai.*;

class Main {
    static function main() {
        var openai = new Instance();
        openai.setApiKey("<YOUR-OPENAI-API-KEY>");

        Example usage of createChatCompletion
        var chatCompletion:Typedefs.ChatCompletion = {
            model: "gpt-3.5-turbo",
            messages: [
                {
                    role: "user",
                    content: "Hey there!"
                }
            ]
        };
        var chatCompletionResult = openai.createChatCompletion(chatCompletion);
        var messageContent = chatCompletionResult.choices[0].message.content;
        trace(messageContent);
    }
}

API Reference

Instance

new()

Creates a new instance of the library.

setApiKey(token:String)

Sets the OpenAI token to authenticate API requests.

setOrgId(orgId:String)

Sets the OpenAI organization ID.

makeRequest(endpoint:String, body:Dynamic):Dynamic

Makes a request to the OpenAI API using the specified endpoint and request body.

createTextCompletion(tc:Typedefs.TextCompletion):Dynamic

Creates a text completion request.

createChatCompletion(cc:Typedefs.ChatCompletion):Dynamic

Creates a chat completion request.

createImage(ic:Typedefs.CreateImage):Dynamic

Creates an image generation request.

createEdit(ce:Typedefs.CreateEdit)

Creates an edit request.

Typedefs

This section provides the typedefs used in the library. Refer to the source code for detailed information about each typedef.

Contributing

Contributions are welcome! Please refer to the CONTRIBUTING.md file for guidelines.

License

This library is licensed under the MIT License.