[F/OS] 🧠 Artificial Intelligence and OpenAI!

Keep in mind that I used the model Ada for this. If you want a more clever answer, switch to DaVinci, but prices increase. Check the Pricing section for more info.

1 Like

It looks nice!
If I just could turn that into working in App Inventor and make a Dall-e edit call :sweat_smile:
But my coding experience in Java and extensions are nearly not existing :innocent:

1 Like

I used Gordon Lu's extension to create an App using ChatGPT API which seems to work okay. Called "Write Like Jane Austin" available on Google Play.

2 Likes

Hi,

Thank you for your post, but did you kind of miss the whole point of the effort to integrate the ChatGPT API into an MIT app?

Peter

Yes indeed. I overlooked the Play Store link and didn't suspect that you were advertising an app here. :upside_down_face:

Hello everyone,

I am excited to announce the :star2: version 3 update of this extension, including many changes, new features and resolved bugs!

I have rolled out a lot of new stuff in this release and fixed some previous bugs. Next time if you find any bugs, please don't hesitate to report them! I don't have a lot of time updating the two new blocks for the documentation...I'm sorry.

:jigsaw: New blocks

  • Two new blocks for editing text! I have now enabled a GPT API that allows you to ask the system to edit the input text according to your instructions. You can make it fix spelling mistakes, punctuate text, and more!

    image image

:star2: New features

  • Enabled the size parameter in the GenerateImage block!

    image

  • Enabled multi-line features for outputs in the RespondedToChat event. Now, you can get formatted poems and text! Thank you @manyone for suggesting this.

  • Enabled the temperature parameter in the Chat method and deprecated the informative parameter. Thank you @manyone for suggesting this.

    image

  • Included the block parameter in the Error event so that you can now find the block that caused the error.

    image

:beetle: Bugs fixed

  • Fixed an issue with line-breakers in input instructions. Thank you @Sam_M for reporting the bug!

:name_badge: Renames

I have decided to rename a lot of blocks because there are new blocks coming in next releases, and some of the names are too vague.

  • GotImageGeneratedImage

  • GotResponseRespondedToChat

:bookmark_tabs: Plans for next release

  • In the next release, I will update the API to GPT 3.5. This will change the models that you use and probably their pricings (I've heard that they are 10 times cheaper than DaVinci). The reason that I won't include it in this release is that there are too many changes and I don't want to bring them all at once.

  • I will include the moderation API allowing the bot to spot errors in the given text, such as inappropriate language.

:handbag: Help wanted

If anyone knows how to access the OpenAI Codex machine, please contact me by messaging.

6 Likes

Hi,
I noticed that the API is for one person, how do you solve the problem if you deliver it on google play?
Do you ask each user to provide his API key?

1 Like

perhaps have the user enter his/her api key. Then enter the apiKey into this Block
image
with appropriate code for the user to enter the apiKey ?

Also other Blocks have an api slot:
image etc. See Gordon's documentation.

1 Like

Sure, for demos it's fine.
However it's not very easy to build something generally available that requires each user to go and grab an API key.
For example, when Microsoft says it offers GPT4 features inside Word and Excel I don't thnik they will ask users to get an API key.
Unless OpenAI provides for sharable API key but I did not see this in the docs.

No, you were intended to provide the API key, not the user. Since the quota is not unlimited and you will have to pay sometime, you can ask users to pay for this, put ads to earn revenue, or limit the amount of messages each user can send.

Google are at it too!

I was not able to find you app, is it hidden somewhere? Is it possible to have the APK? thanks.

Hi Gordon,thank you so much for your hard work. I love it. I was just asking..When will the API will be updated? I tried to use the ''generateImage'' block,but it's giving me error,I'm assuming API are out of date due to GPT 3.5...

Hello everyone,

As I've said, the GenerateImage is outdated and may not work becuase I believe the API needs a new upgrade. This extension is using GPT 3, I'm working on a fix to upgrade to GPT 3.5.

Please search the topic for similar questions from now on. This is not a bad thing, but I'm tired of countless emails and PMs asking the same question. I really do not want to reply so many times because it's pointless.

@Francesco_Sessa, @Tr_ng_Tr_nh_D_c, @Stephen_Wong, this should answer your questions. If you have any questions, do ask, but please read the topic and the replies. Thanks for using the extension and supporting me!

Hello, I'm from Brazil, I did it but it only takes English, he doesn't understand the questions in Portuguese and only answers in English, how do I translate it into my language? please help me.

Hi,

You can use the Translator component to translate your input into English, and the response back into Portuguese.

1 Like

Can't wait for the 3.5 version. Great work Gordon!!!

1 Like

Yeah,I read the whole topic just after sending the message to you,I'm sorry for that. As I imagined,it's due to ChatGPT upgrade. However I wanted to say thank you for the great work. Keep up :wink:

1 Like

No, of course not, I have to manually upgrade it.

Thanks everyone!

Hello everyone,

I'm diagnosed of having tracheitis. Normally it would take two weeks or so for me to recover as I have other diseases that come with me as well, such as asthma.

I'm really sorry, I would have to take rest for two weeks or so and will not be able to do so. I'll still try my best to work on my bed to update this extension.

I'm sorry.

1 Like