[F/OS] 🧠 Artificial Intelligence and OpenAI!

[Gordon_Lu]

Hello everyone,

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

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

New blocks

ModerateText

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

ModeratedText

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.

[Clevetar]

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?

[Gordon_Lu]

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

[Darko]

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.

Thanks

[Gordon_Lu]

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

[Darko]

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

[Gordon_Lu]

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

[irv.cantu]

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

[Gordon_Lu]

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

[irv.cantu]

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

[Gordon_Lu]

It should.

[irv.cantu]

Cool, thanks :DD

[MINHAJUL_HASAN]

B1 not working .
error : model not found

[Gordon_Lu]

Please show your blocks.

[MINHAJUL_HASAN]

[Gordon_Lu]

Do other models starting with B work for you?

[MINHAJUL_HASAN]

A1 and A2 Is perfectly working

[Gordon_Lu]

It should. I'm asking if B2, B3 or B4 work for you.

[MINHAJUL_HASAN]

but i don't know why B1,B2,B3,B4 not working.

[Gordon_Lu]

Hmm...the last time I tested with the B models they worked. I'll see what happens when I get home.