Comments

Carlitus created an issue. See original summary.

Julien Alombert’s picture

Hi Carlitus,
my schedule is quite busy but I will try to get started as soon as possible.
If you want to help it's ok of course :) !

Julien Alombert’s picture

Hi Carlitus,
image generation is up !
Can you try it and get back to me here?

Thank you

carlitus’s picture

Of course, i will try it. And sorry for not replying the previus message.

Julien Alombert’s picture

No problem :)
The dev is on main branch now (9.x-1.0) i juste push a last fix this morning :)

carlitus’s picture

Hi Julien,

I don't think 9.x can be used to install it with composer yet, or at least I don't see it. Maybe it's a matter of time before it comes out.

I've also tried from gitlab, but I don't have permissions, can I do something to get those permissions or only the people responsible for each module can?

thanks.

Julien Alombert’s picture

Hi Carlitus,
it's my first module on drupal.org so i don't know everything about how to set access for all.
What branch can you clone ? 1.0.x ?

carlitus’s picture

In gitlab i cannot clone or download any branch.

And in drupal.org i see only the dev release.

d.o releases

do. releases

carlitus’s picture

I have already seen how to test branch 9.x-1.0

First of all thank you very much for all the work, I love it.

I attach a couple of screenshots.

ARticle about future cats 1

Article about future cats 2

I have not seen how to tell you the number of words for the article. is it the number of tokens? If so that didn't work for me.

It would also be very interesting to be able to generate images independently, from the media browser.

Julien Alombert’s picture

StatusFileSize
new129.86 KB

Hi Carlitus,

for yes this is the number of tokens, and it is possible that it take effect only with some models.
In the documentation we can read:
The token count of your prompt plus max_tokens cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096).

Obviously it does not work with text-ada for example. But it works with Davinci.
In addition I made a filter on the list of models available because I'm not sure it's a good thing to display them all (see screenshot) there are really a lot.

I will replace davinci-002 by davinci-003 (the newest).

I will investigate how it could be possible to add something that can generate a media file from the media browser, it's a very cool idea !!
Thank a lot for your feedback !

Julien Alombert’s picture

Hi carlitus,

for now i don't really know how to integrate with the modale from media library, but i add a image generation menu (in Content menu).
on 9.x-1.0, I add the media creation too, so you will retrieve your generated image from article or from Image generation inside your library.

For adding the form inside the media library popup i tried form alter and it's ok to have the form inside, but this isn't working for now, maybe i'll need help for that ^^

Hope you like the new feature ;)

carlitus’s picture

I will take a look asap. Thanks!

kevinquillen’s picture

Project: OpenAi API » OpenAI / ChatGPT Integration

Migrating to new project.

d0t101101’s picture

Looking forward to seeing this working again with the Content Generation feature of the latest DEV branch!

kevinquillen’s picture

There is both an internal form and ECA action for this now. This will need to be a CKEditor action in the future.

kevinquillen’s picture

Status: Active » Fixed

Status: Fixed » Closed (fixed)

Automatically closed - issue fixed for 2 weeks with no activity.