Openai Chatgpt

How to use the Openai Chatgpt robot skill

Give your robot a personality and conversational ability. This robot skill adds chatbot capability to your robot so you can have meaningful conversations that it will remember. Configure the personality in any way you wish so the robot can prefer specific subjects or have particular opinions.

OpenAI’s mission is to ensure that artificial intelligence benefits all of humanity. This effort is essential to training AI systems to do what humans want. Generative Pre-trained Transformer is an unsupervised Transformer language model commonly known by its abbreviated form Chat GPT robot skill. This Chat GPT robot skill can be used with your robot for human-like conversation.

Screenshot

Disclaimer

Open AI's Chat GPT should not be used as a source of facts or information to help you make life decisions. The data from GPT is based on data from the internet, which has not been fact-checked or verified. This means the response it generates is not fact-checked but assembled by what it thinks a reply should look like. In short, Open AI prioritizes a response based on statistical popularity and sentence structure, not facts.

*Note: Open AI responses should be treated as fiction.

Configuration

The configuration menu has several options. You can add keywords with associated scripts that execute with responses from the Bot. You can also have a script that runs every response received. By default, the All Responses script will speak the response out of the PC speaker.

Words in the "Contains" list can be separated by a comma. The words are compared against the response. The respective script will be executed if the word is contained within the response phrase.



Default Script


By default, the All Responses script from the script tab will speak the response from the PC speaker. If you use an EZB that supports audio output, the command can be edited to Audio.sayEZB() to speak out of the EZB. 

Variables
Variables store the user's request and the bot's response. This allows the robot to speak the response defaulted in the All Response scripts.



Settings
The settings tab has options for configuring the bot behavior and the API key. Obtain an API Key from the OpenAI website and paste it into the appropriate box. When choosing a model, view the pricing and details on their website here: https://openai.com/api/pricing/

If you receive an error that a GPT model does not exist, chances are it has been removed from Open AI API and is no longer accessible.

*Note: The GPT-4 model is available by Open AI as a request-only feature. If you try to use GPT-4, you will receive an error unless you have permission to use it. You must apply to access GPT-4 to use with your Open AI Developer Key. Read more here: https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4





Best Match
This list of words/phrases will be used to guess the best match based on the conversation. This allows your robot to execute a script matching the conversation's subject or tone. The robot can act on being sad or happy based on the type of conversation. Or have the robot dance when discussing a party or favorite music. A few examples provide suggestions for scripts to associate with them.

There is an option to determine what input the match should be based on. By default, the match will use the AI response to provide the most accurate interactive responses. If unchecked, the match will be based on the user's input.



This is a powerful feature because you can describe the best match phrases to execute scripts. For example, you can even have the robot move in a direction. Just make sure that the Personality description of the AI explains that the AI can move. Otherwise, the AI will respond by saying it cannot move, and the response phrase won't match the action.

Personality

You can define the personality of the robot by writing a description. Make the description detailed on how you want the robot to behave. You can even tell the robot what its favorite color will be or favorite movie.

Control Commands

Several ControlCommand() for this robot skill enables interaction with other robot skills. 

Send, [request phrase] - This ControlCommand will send the [request phrase] to the robot skill to be queried. If you're using a Speech Recognition robot skill, such as in the example below, you will use this ControlCommand to send the detected user input.

ResetMemory - This will reset the conversation and memory to the default state. 

API Key

An account is required on the OpenAI website to use the service. Once an account is created, you will have an API key for the robot skill. However, the cost associated with queries is quite low - and may only be a few dollars a month.

1) Visit the OpenAI website and select the API option from the menu. 



2) Press the SIGNUP option to create an account



3) Once the account is created, press your Username icon to view the drop-down. And select the View API Keys option.



4) Copy your API key




5) Paste the API key in the robot skill configuration menu

Demo Example

Here is an example of using the OpenAI chatbot to have verbal conversations. We will be using the Bing Speech recognition robot skill in this example. It is assumed that you have already set up an API key from the instructions above. Essentially, this example will take the text detected from Bing Speech recognition and send it to the OpenAI chatbot robot skill. The OpenAI chatbot robot skill will then speak the chatbot's response.

1) Add the OpenAI chatbot to your ARC project. Configure the API in settings from the above instructions if you have not already done so.



2) Add the Bing Speech Recognition robot skill to your ARC project. 
Project -> Add Control -> Audio -> Bing Speech Recognition



3) Your project will now have both the OpenAI and Bing Speech recognition robot skills



4) Press the Configure button on the Bing Speech recognition robot skill



5) Press the button to edit the script for All Recognized Script



6) We will use JavaScript in this example. When the script editor loads, select the JavaScript tab.



7) Right-click in the editor and navigate the menu to the OpenAI selection. Choose the SEND option



8) A command will be added to the code editor. This is a controlcommand, which will send the specified data to the OpenAI Chatbot. We will edit this command to send the variable containing the Bing Speech Recognition text detected.



9) Highlight the "[requested phrase]" text



10) Delete the "[requested phrase]" text




11) Select the Global Variables tab 



12) Place your cursor where the text you have just erased once was.



13) Now click on the $BingSpeech variable from the Global Variables. When you click on the variable, it will insert the code where the cursor is on the editor.



14) Your line of code should now look like this. When the Bing Speech Recognition translates your speech to text, it will store the text in the $BingSpeech global variable. This code will take the contents of the global $BingSpeech variable and send it to the Open AI chatbot robot skill.

Code:

ControlCommand("OpenAI Chatbot", "Send", getVar("$BingSpeech") );

15) Save the code editor



16) Save the configuration



17) Now press the Start Recording button and speak to the robot. Press the Stop Recording button when you have completed speaking.



18) You are now having a conversation with your robot!

Next Steps

You can add this to any robot and start modifying features to make the robot do specific actions or behaviors based on phrases. Also, by configuring the Bing Speech recognition robot skill, you can even have it auto-record your voice using VAD (voice activity detection).

If your robot has an EZB supporting audio, such as an EZ-Robot v4, you can change the Open AI script to sayEZB() and have the voice come from the robot speaker. There are many things you can do, be creative and have fun!

Error at chat/completions (https://api.openai.com/v1/chat/completions) with HTTP status code: 429. Content: {
  "error": {
    "message": "That model is currently overloaded with other requests. You can retry your request, or Contact Us through our help center at help.openai.com if the error persists. (Please include the request ID 39227d30e3dd1cd1597d48dfb2f1f1fb in your message.)",
    "type": "server_error",
    "param": null,
    "code": null
  }
}

Error at chat/completions (https://api.openai.com/v1/chat/completions) with HTTP status code: BadRequest. Content: {
  "error": {
    "message": "This model's maximum context length is 4097 tokens. However, your messages resulted in 4139 tokens. Please reduce the length of the messages.",
    "type": "invalid_request_error",
    "param": "messages",
    "code": "context_length_exceeded"
  }
}

Error at chat/completions (https://api.openai.com/v1/chat/completions) with HTTP status code: BadRequest. Content: {
  "error": {
    "message": "This model's maximum context length is 4097 tokens. However, your messages resulted in 4139 tokens. Please reduce the length of the messages.",
    "type": "invalid_request_error",
    "param": "messages",
    "code": "context_length_exceeded"
  }
}

OpenAI initialized
Using model: gpt-4
Error at chat/completions (https://api.openai.com/v1/chat/completions) with HTTP status code: NotFound. Content: {
    "error": {
        "message": "The model: `gpt-4` does not exist",
        "type": "invalid_request_error",
        "param": null,
        "code": "model_not_found"
    }
}

Audio.sayEZB(getVar("$OpenAIResponse"));