Skip to content

A Node-RED node that interacts with OpenAI machine learning models to generate text and image outputs like 'ChatGPT' and 'DALL·E 2'.

License

Notifications You must be signed in to change notification settings

HaroldPetersInskipp/node-red-contrib-chatgpt

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

77 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

node-red-contrib-custom-chatgpt

Platform npm Downloads MIT License

Supercharge your Node-RED flows with AI! Seamlessly integrate with OpenAI's powerful models like GPT-4o, DALL·E 2, and DALL·E 3 to unlock a world of creative possibilities. Create imaginative chatbots, automate content generation, or build AI-driven experiences. The power of AI is just a node away!

Table of Contents

Getting Started

To start using node-red-contrib-custom-chatgpt, you can install it through the built-in Node-RED Palette manager or using npm:

npm install node-red-contrib-custom-chatgpt

Setup

With these, you're ready to configure your node-red-contrib-custom-chatgpt nodes.

Usage

With node-red-contrib-custom-chatgpt, you have the power to select the behavior of the node by setting the Topic property value to gpt4o, image, turbo , or gpt4. You can control the node with a single required message property msg.payload or dynamically set the behavior with incoming messages using read from msg.topic.

When is set to read from msg.topic if msg.topic is left undefined then the message property msg.model can be used to select any model.

For detailed information on the usage of these modes, please refer to the OpenAI API documentation.

  1. When msg.topic is set to gpt4o:

    • [Required] msg.payload should be a well-written prompt that provides enough information for the model to know what you want and how it should respond. Its success generally depends on the complexity of the task and quality of your prompt. A good rule of thumb is to think about how you would write a word problem for a middle schooler to solve.

    • [Optional] msg.history should be an array of objects containing the conversation history. [Default:[]]

  2. When msg.topic is set to image:

    • [Required] msg.payload should be a prompt of text description of the desired image.

    • [Optional] msg.size should be a string of the desired image dimensions. [Default:256x256]

    • [Optional] msg.format should be a string of either b64_json or url. [Default:url] (NOTE: b64_json may be depreciated)

  3. When msg.topic is set to turbo:

    • [Required] msg.payload should be a well-written prompt that provides enough information for the model to know what you want and how it should respond. Its success generally depends on the complexity of the task and quality of your prompt.

    • [Optional] msg.history should be an array of objects containing the conversation history. [Default:[]]

  4. When msg.topic is set to gpt4:

    • [Required] msg.payload should be a well-written prompt that provides enough information for the model to know what you want and how it should respond. Its success generally depends on the complexity of the task and quality of your prompt.

    • [Optional] msg.history should be an array of objects containing the conversation history. [Default:[]]

  5. When msg.topic is set to dalle3:

    • [Required] msg.payload should be a prompt of text description of the desired image.

    • [Optional] msg.size should be a string of the desired image dimensions. [Default:1024x1024]

  6. When msg.topic is set to gpt-4o-mini:

    • [Required] msg.payload should be a well-written prompt that provides enough information for the model to know what you want and how it should respond. Its success generally depends on the complexity of the task and quality of your prompt.

    • [Optional] msg.history should be an array of objects containing the conversation history. [Default:[]]

Additional optional properties

The following optional inputs are supported - msg.max_tokens, msg.suffix, msg.n, msg.temperature, msg.top_p, msg.presence_penalty, msg.frequency_penalty, msg.echo, and msg.API_KEY See the nodes built-in help tab for more information on how they are used.

Examples

We've provided several examples to help you understand the potential and versatility of node-red-contrib-custom-chatgpt. From basic usages like image generation and text editing, to more advanced features like setting behaviors, using optional message properties, and automating Node-RED node creation.

[Old screenshot] Basic usage for image, completion, and edit. Screenshot showcasing basic usage of node-red-contrib-custom-chatgpt for image generation, text completion, and text editing tasks

[Old screenshot] More advanced usage with templates. Screenshot illustrating advanced usage of node-red-contrib-custom-chatgpt with templates

[Old screenshot] Usage of model gpt-3.5-turbo and conversation history. Screenshot demonstrating the usage of gpt-3.5-turbo model with conversation history in node-red-contrib-custom-chatgpt

[New screenshot] Updated example using optional message properties and setting behavior Topic in node edit dialog. Screenshot of an updated example showing the use of optional message properties and setting behavior Topic in node edit dialog with node-red-contrib-custom-chatgpt

[New screenshot] Additional example demonstrating how to generate Node-RED nodes and import them directly into the editor automatically. Screenshot of an additional example demonstrating the generation of Node-RED nodes and their automatic import into the editor using node-red-contrib-custom-chatgpt

External Links

Bugs and Feature Requests

Encountered a bug or have an idea for a new feature? We'd love to hear from you! Feel free to submit an issue on our GitHub page.

Changelog

Stay up-to-date with the latest changes by checking out our CHANGELOG.

License

This project is licensed under the MIT License - see the LICENSE file for details.