[F/OS] 🧠 Artificial Intelligence and OpenAI!

Continuing the discussion from [F/OS] :brain: Artificial Intelligence and OpenAI!:

I can give you API key . contact me

Thanks, but I've already gotten 2 keys. Sorry for the inconvenience.


Est-ce que le component pour générer une image fonctionne?

Hello everyone,

Just an update of what I'm doing.

:white_check_mark: Updated the Chat block to GPT 3.5 and GPT 4. You can choose from different 3.5 and 4 models.

:white_check_mark: Fixed the GenerateImage error!

:white_check_mark: Checked the EditText block, still working.

All I have to do is to add a moderation block that allows you to check if there are any issues with a piece of text, such as offensive language.


Hello everyone,

Sorry for the late reply. I have finally updated this extension to :star2: version 4, with bug fixes, new features and new blocks!

:star2: New features

  • Fixed the image generation error! It now should work as usual.

  • Updated the Chat block to the latest GPT 3.5 and GPT 4. You will no longer be able to use the GPT 3 models if you update this extension. Unfortunately, because of naming conventions and naming issues (no dots and hyphens allowed) I'm unable to put a helper block for this. The Model helper block should disappear; please now use this list for the model parameter. For example, if I want to use the model gpt-4, I would enter B1 as the model parameter.

    A1: gpt-3.5-turbo
    A2: gpt-3.5-turbo-0301

    B1: gpt-4
    B2: gpt-4-0314
    B3: gpt-4-32k
    B4: gpt-4-32k-0314

:jigsaw: New blocks



The moderation API is a service provided by OpenAI that allows you to check whether a text contains inappropriate or offensive information. Put the text that you want to analyze in the input parameter, and supply the block with an API key.

Parameters: input = text, apiKey = text



This event is fired when OpenAI has moderated the text you inputted in the ModerateText block! 'flagged' refers to whether the text contains indecent information in general.

  • categoryFlags includes a dictionary of 7 types of inappropriate information (hate, hate/threatening, self-harm, sexual, sexual/minors, violence, violence/graphic). These 7 are the keys of the dictionary. Corresponding to them are boolean values for whether the text has this type of inappropriate information. Sample response:

  • categoryScores includes the same 7 types as the keys, but corresponding to them are decimals from 0 to 1. Values closer to 0 mean that the text violates less in this category; vice versa.

Parameters: flagged = boolean, categoryFlags = dictionary, categoryScores = dictionary

I will update the entire documentation tomorrow morning.


Hello! Is there an option for me to make it automatically check something about the system and then get the tokens I have spent, because my friends could also just reach the limit of my account and then I would need to pay for it?

1 Like

I see that a Python library does this but I can't find anything else about the topic. I will find out. Thanks!

1 Like

Gordon, thank you wery much for this. Great work!

Is there a way to use system role with it's dedicated content that would be predefined (not for mobile app end users to change)?. I am refering to Chat option, and I see that currently only user role is supported.


1 Like

Implementing the system role is possible with a modification to the block. Thanks!

Do you have some plans do develope this, or how can I help you develop this? :grin:

I can add this in a new release along with the stream feature.


Hi, could you help me with this error, I have no idea what I'm doing wrong ://

Are you using the iOS companion? You cannot use extensions on iOS.

Yeah... So, just so we're clear, if I'm using an Android, is it supposed to work? Thanks btw :))

It should.

Cool, thanks :DD

1 Like

B1 not working .
error : model not found

Please show your blocks.

1 Like

Do other models starting with B work for you?