[F/OS] 🧠 Artificial Intelligence and OpenAI!

[arunkarana]

So for a new account, they give 18$ right? Is there any expiry date for this amount if not used?

[gordonlu310]

For a new account that has a unique phone number, yes. You will have 12 months to spend this $18 credit, and you will have to pay again if you spent all of this or if 12 months are up.

[arunkarana]

Thanks for the help.

[arunkarana]

I just created a new account with a new number and it gets only $5, this amount will get expire on 1 August. We get Four months to use this amount.

The App is now working!!

[gordonlu310]

Hmm...interesting. Let me check the details again.

[Azzard]

er what does that mean

Expire 1st may?

[gordonlu310]

Yes.

[Azzard]

Not 12 month as you said ...

But I wanted to thank you for this fabulous extension too

[gordonlu310]

I haven't been updated for a long time because of business and now hospital. That was written in around January or February.

Since when did you sign up? I'll check the new pricing plans.

[Azzard]

I pray that you are well sir Excuse​:pray:

Last month

It take a time to generate picture, and i dont know if it work

[gordonlu310]

Hmm...ok, so we get different credits here. Let me see...

[Lakshya]

How to download old version?

[gordonlu310]

You should see a History section below the Downloads. This only contains V2.

[gordonlu310]

Good news: I'm back. I'm now instantly catching up and fixing everything I can.

Bad news: The API key that was provided generously by a user has expired, unfortunately. I'm unable to register myself because I have a Hong Kong phone number. If you would like to help me out for a few days by providing me an API key, I'd be extremely grateful. Thank you.

---

Thank you [edit: name removed on request] and @AyProductions for kindly sharing with me the API keys. Couldn't do it without you two!

[AyProductions]

You're welcome!

[Sohan74]

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

I can give you API key . contact me

[gordonlu310]

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

[Azzard]

Bonjour

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

[gordonlu310]

Hello everyone,

Just an update of what I'm doing.

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

Fixed the GenerateImage error!

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.

[gordonlu310]

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.