gifted-gpt

gifted-gpt

Gifted-Gpt is a Free Chat GPT4 npm package, No API key or auth needed, All Models Included as well as Image Generators.

This package can be used in both Typescript and CommonJS/ModuleJS environments.

🛠️ Installation

Using npm:

npm install gifted-gpt

Using yarn:

yarn add gifted-gpt

🎯 Examples

📤 Chat completion

With the chatCompletion function, you will be able to obtain a textual response to a conversation with some context, using providers and models designed for this task. In addition, you will be able to manipulate the answer before converting it to a stream or force the AI to give you a certain answer by generating several retries.

⚙️ Basic usage

Simple fetch

It will capture the messages and the context, and any provider will respond with a string.

const { GiftedGpt } = require("gifted-gpt");
const gpt4 = new GiftedGpt();
const messages = [
    { role: "user", content: "Hi, what's up?"}
];
gpt4.chatCompletion(messages).then(console.log);
// Hello! I'm here to help you with anything you need. What can I do for you today? 😊

Note: The conversation needs to include at least one message with the role user to provide a proper answer.

Give your instructions

You can provide your own instructions for the conversation before it starts using the system role.

const { GiftedGpt } = require("gifted-gpt");
const gpt4 = new GiftedGpt();
const messages = [
    { role: "system", content: "You're an expert bot in poetry."},
    { role: "user", content: "Hi, write me something."}
];
gpt4.chatCompletion(messages).then(console.log);
/*
Sure, I can write you a poem. Here is a short one: 
The Wind:
The wind is a curious thing,
It can make you dance and sing,
It can make you feel alive,
And help you thrive.
...
*/

Follow up on the conversation context

const { GiftedGpt } = require("gifted-gpt");
const gpt4 = new GiftedGpt();
const messages = [
    { role: "system", content: "You're a math teacher."},
    { role: "user", content: "How much is 2 plus 2?" },
    { role: "assistant", content: "2 plus 2 equals 4." },
    { role: "user", content: "You're really good at math!" },
    { role: "assistant", content: "Thank you! I'm glad I could help you with your math question." },
    { role: "user", content: "What was the first question I asked you?" }
];

gpt4.chatCompletion(messages).then(console.log);
// The first question you asked me was "How much is 2 plus 2?".

Note: AI responses use the assistant role and an appropriate conversation structure alternates between the user and the assistant, as seen in the previous example.

✏️ RESUME: Conversation roles

Role	Description
system	Used for providing instructions and context prior to the conversation.
user	Used to identify user messages
assistant	Used to identify AI messages

🔩 Add configurable options

Basic options

You can select any provider, model, debug mode and a proxy URL if you want.

const { GiftedGpt } = require("gifted-gpt");
const gpt4 = new GiftedGpt();
const messages = [
    { role: "user", content: "Hi, what's up?"}
];
const options = {
    provider: gpt4.providers.GPT,
    model: "gpt-3.5-turbo",
    debug: true,
    proxy: ""
};

(async() => {
	const text = await gpt4.chatCompletion(messages, options);	
	console.log(text);
})();
/*
[provider] » √  success   Provider found: GPT
[model] » √  success   Using the model: gpt-3.5-turbo
[provider] » √  success   Data was successfully fetched from the GPT provider

In the realm of words, where verses dance and rhyme,
I shall craft a poem, a moment frozen in time.
With ink as my brush, I paint a vivid scene,
Where dreams and emotions intertwine, serene.
Through lines and stanzas, I'll weave a tale,
Of love, of loss, of hope that will never fail.
So close your eyes, and let your heart unfurl,
As I conjure a poem, a gift for your soul to swirl. 💕🌹
*/

Note: You can specify the provider, model, debug, and proxy options according to your needs; they are entirely optional.

Advanced options

You can force an expected response using retry, and manipulate the final response using output.

const { GiftedGpt } = require("gifted-gpt");
const gpt4 = new GiftedGpt();
const messages = [
    { role: "system", content: "You're an expert bot in poetry."},
    { role: "user", content: "Let's see, write a single paragraph-long poem for me." },
];
const options = {
    model: "gpt-4",
    debug: true,
	retry: {
        times: 3,
        condition: (text) => {
            const words = text.split(" ");
            return words.length > 10;
        }
    },
    output: (text) => {
        return text + " 💕🌹";
    }
};

(async() => {
    const text = await gpt4.chatCompletion(messages, options);	
    console.log(text);
})();
/* 
[provider] » √  success   Provider found: GPT
[model] » √  success   Using the model: gpt-4
[fetch] » √  success   [1/3] - Retry #1
[output] » √  success   Output function runtime finalized.

I'll try to create that.
Is what you asked me to say
I hope it brings you joy
And your heart it does employ 💕🌹
*/

Note: Retry will execute the fetch operation consecutively N times until it finishes, or the condition function indicates true. The output function only edits the final response.

What is the difference between basic options and advanced options?

If you decide to use the retry, output option, or both, keep in mind that these options involve preprocessing before delivering the ultimate response. The impact on performance and response times may vary depending on the functions you employ.

📝 Streaming

When using the stream option, the chatCompletion function will return an object with the streamable data and the name of the provider.

Basic usage

const { GiftedGpt } = require("gifted-gpt");
const gpt4 = new GiftedGpt();
const messages = [
    { role: "system", content: "You're an expert bot in poetry."},
    { role: "user", content: "Let's see, write a single paragraph-long poem for me." },
];
const options = {
    provider: gpt4.providers.ChatBase,
    stream: true
};

(async() => {
    const response = await gpt4.chatCompletion(messages, options);	
    console.log(response);
})();
/*
{ 
    data: <ref *1> BrotliDecompress { ... }, 
    name: "ChatBase" 
}
*/

So, how you should handle the streamable data?

I highly recommend you to use the integrated chunkProcessor function so that you don't have to format each chunk into a single string format response.

const { GiftedGpt, chunkProcessor } = require("gifted-gpt");
const gpt4 = new GiftedGpt();
const messages = [
    { role: "system", content: "You're an expert bot in poetry."},
    { role: "user", content: "Let's see, write a single paragraph-long poem for me." },
];
const options = {
    provider: gpt4.providers.ChatBase,
    stream: true
};

(async() => {
    const response = await gpt4.chatCompletion(messages, options);
    let text = "";
    for await (const chunk of chunkProcessor(response)) {
        text += chunk;
    }
    console.log(text);
})();
/* 
I'll try to create that.
To keep your worries at bay.
A smile on your face,
And a heart full of grace.
*/

Stream on postprocessing

When employing retry, output option, or both, you have the flexibility to select the size of each streamed chunk.

const { GiftedGpt, chunkProcessor } = require("gifted-gpt");
const gpt4 = new GiftedGpt();
const messages = [
    { role: "system", content: "You're an expert bot in poetry."},
    { role: "user", content: "Let's see, write a single paragraph-long poem for me." },
];
const options = {
    provider: gpt4.providers.Bing,
    stream: true,
    chunkSize: 15,
    retry: {
        times: 3,
        condition: (text) => {
            const words = text.split(" ");
            return words.length > 10;
        }
    },
    output: (text) => {
        return text + " 💕🌹";
    }
};

(async() => {
    const response = await gpt4.chatCompletion(messages, options);
    for await (const chunk of chunkProcessor(response)) {
        console.log(chunk);    
    }
})();
/*
I'll try to cre
ate that. 
  Is what you a
sked me to say
n    I hope it
brings you joy
n    And makes
your heart feel
 gay 💕🌹
*/

Note: The chunkSize feature is effective only when the stream option is activated along with the retry/output option.

✏️ RESUME: Configurable options

Option	Type	Description
provider	g4f.providers.any	Choose the provider to use for chat completions.
model	string	Choose the model to use by a provider that supports it
debug	boolean	Enable or disable debug mode.
proxy	string	Specify a proxy as a URL with a string in the host:port format.
retry	object	Execute the fetch operation N times in a row until it finishes or the callback function returns true.
retry.times	number	Specify the number of times the fetch operation will execute as a limit.
retry.condition	function: boolean	Callback function that receives a string as the text for each instance the fetch operation is running. This function should return a boolean.
output	function: string	Callback function that receives a string as the final text response so you can edit it. This function executes after the retry fetch operations. This function should return a string.
conversationStyle	string	Choose the conversation style to use. This option is only supported by the Bing provider.
markdown	boolean	Determine if the response should be in markdown format or not.
stream	boolean	Determine if the data should be streamed in parts or not.
chunkSize	number	Determine the size of chunks streamed. This only works if the stream option is true and if using retry or condition.

🚀 Chat completion providers

Website	Provider	GPT-3.5	GPT-4	Stream	Status
GPT.ai	gpt4.providers.GPT	✔️	✔️	❌
chatbase.co	gpt4.providers.ChatBase	✔️	❌	✔️
bing.com	gpt4.providers.Bing	❌	✔️	✔️

📚 Chat completion models

Model	Providers that support it
gpt-4	gpt4.providers.GPT, gpt4.providers.Bing
gpt-4-0613	gpt4.providers.GPT
gpt-4-32k	gpt4.providers.GPT
gpt-4-0314	gpt4.providers.GPT
gpt-4-32k-0314	gpt4.providers.GPT
gpt-3.5-turbo	gpt4.providers.GPT, gpt4.providers.ChatBase
gpt-3.5-turbo-16k	gpt4.providers.GPT
gpt-3.5-turbo-0613	gpt4.providers.GPT
gpt-3.5-turbo-16k-0613	gpt4.providers.GPT
gpt-3.5-turbo-0301	gpt4.providers.GPT
text-davinci-003	gpt4.providers.GPT
text-davinci-002	gpt4.providers.GPT
code-davinci-002	gpt4.providers.GPT
gpt-3	gpt4.providers.GPT
text-curie-001	gpt4.providers.GPT
text-babbage-001	gpt4.providers.GPT
text-ada-001	gpt4.providers.GPT
davinci	gpt4.providers.GPT
curie	gpt4.providers.GPT
babbage	gpt4.providers.GPT
ada	gpt4.providers.GPT
babbage-002	gpt4.providers.GPT
davinci-002	gpt4.providers.GPT

📡 Translation

With the translation function, you can convert a text to a target language using AI.

Usage

const { GiftedGpt } = require("gifted-gpt");

const gpt4 = new GiftedGpt();
const options = {
    text: "Hello World",
    source: "en",
    target: "ko"
};

(async() => {
    const text = await gpt4.translation(options);
    console.log(text);
})();
/* 
{
  source: { code: 'en', lang: 'English' },
  target: { code: 'ko', lang: '한국어' },
  translation: { parts: [ [Object] ], result: '안녕하세요 세계' }
}
*/

Note: You need to identify the language source ID and included it by your own, in the future this will be solved with AI, and you wouldn't need to specify it.

✏️ RESUME: Translation options

Option	Type	Required	Description
provider	g4f.providers.any	❌	Choose the provider to use for translations.
debug	boolean	❌	Enable or disable debug mode.
text	string	✔️	Specify the text to translate
source	string	✔️	Specify the source text language.
target	string	✔️	Specify the target language to translate.

🌏 Languages available

Provider	Status	Languages supported
gpt4.providers.TranslateAI		https://rentry.co/3qi3wqnr

📷 Image generation (BETA)

With the imageGeneration function, you will be able to generate images from a text input and optional parameters that will provide you with millions of combinations to stylize each of the images.

Cartoon style example

const { GiftedGpt } = require("gifted-gpt");
const fs = require("fs");

const gpt4 = new GiftedGpt();
(async() => {
    const base64Image = await gpt4.imageGeneration("A squirrel", { 
        debug: true,
        provider: gpt4.providers.Emi
    });	
    fs.writeFile('image.jpg', base64Image, { encoding: 'base64' }, function(err) {
      if (err) return console.error('Error writing the file: ', err);
      console.log('The image has been successfully saved as image.jpg.');
    });
})();

Paint style example

const { GiftedGpt } = require("gifted-gpt");
const fs = require("fs");

const gpt4 = new GiftedGpt();
(async() => {
    const base64Image = await gpt4.imageGeneration("A village", { 
        debug: true,
        provider: gpt4.providers.Pixart,
        providerOptions: {
            height: 512,
            width: 512,
            samplingMethod: "SA-Solver"
        }
    });	
    fs.writeFile('image.jpg', base64Image, { encoding: 'base64' }, function(err) {
      if (err) return console.error('Error writing the file: ', err);
      console.log('The image has been successfully saved as image.jpg.');
    });
})();

Realistic style example

const { GiftedGpt } = require("gifted-gpt");
const fs = require("fs");

const gpt4 = new GiftedGpt();
(async() => {
    const base64Image = await gpt4.imageGeneration("A colorfull photo of a young lady", { 
        debug: true,
        provider: gpt4.providers.Prodia,
        providerOptions: {
            model: "ICantBelieveItsNotPhotography_seco.safetensors [4e7a3dfd]",
            samplingSteps: 15,
            cfgScale: 30
        }
    });	
    fs.writeFile('image.jpg', base64Image, { encoding: 'base64' }, function(err) {
      if (err) return console.error('Error writing the file: ', err);
      console.log('The image has been successfully saved as image.jpg.');
    });
})();

✏️ RESUME: Image generation options

Option	Type	Description
debug	boolean	Enable or disable debug mode.
provider	gpt4.providers.any	Choose the provider to use for image generations.
providerOptions	object	Use provider options supported by any provider

Note: The value of providerOptions should be an object containing instructions for image generation, such as the base model, image style, sampling methods, among others. Not all providers support the same instructions, so refer to the following list.

✏️ RESUME: Image generation provider options

Option	Type	Description	Limits	Providers that support it
model	string	Choose a model as a base for generation.	🤖 Check lists	Prodia, ProdiaStableDiffusion, ProdiaStableDiffusionXL
negativePrompt	string	Indicate the provider of what not to do.	None	Pixart, PixartLCM, Prodia, ProdiaStableDiffusion, ProdiaStableDiffusionXL
imageStyle	string	Specify the draw style.	🎨 Check lists	Pixart, PixartLCM
height	number	Specify the image height.	🧮 Check lists	Pixart, PixartLCM, ProdiaStableDiffusion, ProdiaStableDiffusionXL
width	number	Specify the image width.	🧮 Check lists	Pixart, PixartLCM, ProdiaStableDiffusion, ProdiaStableDiffusionXL
samplingSteps	number	Specify the number of iterations. A higher number results in more quality.	🧮 Check lists	Prodia, ProdiaStableDiffusion, ProdiaStableDiffusionXL
samplingMethod	string	Choose a sampling method to control the diversity, quality, and coherence of images.	✒️ Check lists	Pixart, Prodia, ProdiaStableDiffusion, ProdiaStableDiffusionXL
cfgScale	number	Specify the Classifier-Free Guidance to control how closely the generated image adheres to the given text prompt.	🧮 Check lists	Pixart Prodia, ProdiaStableDiffusion, ProdiaStableDiffusionXL
dpmInferenceSteps	number	Specify the DPM Inference Steps for refining object detection accuracy	🧮 Check lists	Pixart
saGuidanceScale	number	Specify the Style-Aware Guidance Scale for fine-tuning style and composition	🧮 Check lists	Pixart StableDiffusionPlus
saInferenceSteps	number	Specify the Style-Aware Inference Steps for refining or adjusting the generated image during style transfer or style-based image synthesis.	🧮 Check lists	Pixart
lcmInferenceSteps	number	Specify the LCM Inference Steps for enhancing the generation of images with AI by leveraging latent consistency models	🧮 Check lists	PixartLCM
useGpu	boolean	Determine whether to use the GPU for generation	None	Dalle2
promptImprovement	boolean	Determine whether the prompt should be enhanced using AI.	None	Dalle2

🤖 Image generation models

Provider	Models supported
Prodia	https://rentry.co/b6i53fnm
ProdiaStableDiffusion	https://rentry.co/pfwmx6y5
ProdiaStableDiffusionXL	https://rentry.co/wfhsk8sv

🎨 Image generation styles

Provider	Image styles supported
Pixart	https://rentry.co/hcggg36n
PixartLCM	https://rentry.co/gzxa3wv2

✒️ Image generation sampling methods

Provider	Sampling methods supported
Pixart	https://rentry.co/x7i8gko9
Prodia	https://rentry.co/8bwtqeh9
ProdiaStableDiffusion	https://rentry.co/iyrkxmzr
ProdiaStableDiffusionXL	https://rentry.co/p2ad6y3f

🧮 Number type options

Provider	Number type options and values supported
Pixart	Option Default Min Max height 1024 256 2048 width 1024 256 2048 dpmInferenceSteps 14 5 40 saGuidanceScale 3 1 10 saInferenceSteps 25 10 40 cfgScale 4.5 1 10
PixartLCM	Option Default Min Max height 1024 256 2048 width 1024 256 2048 lcmInferenceSteps 9 1 30
Prodia	Option Default Min Max samplingSteps 7 0 20 cfgScale 25 1 30
ProdiaStableDiffusion	Option Default Min Max height 512 50 1024 width 512 50 1024 samplingSteps 25 1 30 cfgScale 7 1 20
ProdiaStableDiffusionXL	Option Default Min Max height 1024 512 1536 width 1024 512 1536 samplingSteps 25 1 30 cfgScale 7 1 20
StableDiffusionPlus	Option Default Min Max saGuidanceScale 9 0 50

🖼️ Image generation providers

Provider	Status	Default style
Pixart		Realistic with a touch of exaggeration, characterized by detailed textures, vibrant colors, and enhanced features.
PixartLCM		Exhibits a detailed and vibrant use of color, creating a visually rich and textured representation. It’s a blend of realism with a touch of artistic interpretation.
Emi		Characterized by a colorful and whimsical animation, reminiscent of a children’s storybook illustration.
Dalle		Realistic, capturing intricate details and textures to depict a lifelike representation.
DalleMini		Leans towards the abstract, with a digital artistry touch that emphasizes detailed textures and vibrant colors. It captures the essence of the subject through the use of shape, color, and form rather than attempting to represent it accurately.
Dalle2		Characterized by its semi-realism, with a focus on fine details, vivid colors, and natural lighting.
Prodia		Can be described as “photorealistic”. This term refers to artwork that is extremely detailed and lifelike, closely resembling a high-resolution photograph.
ProdiaStableDiffusion		Photorealistic, capturing intricate details and textures to mimic the appearance of a real-life scene.
ProdiaStableDiffusionXL		Semi-realistic, meticulously incorporating fine details and textures to emulate the semblance of a real-world scenario.
StableDiffusionLite		Can be described as folk art. It exhibits a naive perspective, lacks realistic proportions, and evokes simplicity.
StableDiffusionPlus		Impressionism, characterized by visible brushstrokes, open composition, emphasis on light in its changing qualities, and ordinary subject matter.

Note

It's important to review the possibilities that each provider offers within their limitations, in order to access more detailed creations. However, it's possible that at some point you might combine options that are not supported by the provider you're using at that moment. In such cases the image generation won't stop; instead (and as long as you're using the debug option), you'll receive a warning alerting you to the error.