GPT-4 with vision available

Contribute Feature
,
1

In the AI plugin settings I can see this list of AI bots I can enable:

image
image676×189 2.54 KB

I wonder if the gpt-4-turbo bot is ‘gpt-4-turbo-preview’ or ‘gpt-4-vision-preview’
I.e. does it have vision?
If it’s ‘gpt-4-turbo-preview’ will vision be also added? I think it would be useful since since e.g. a screenshot can help the bot to understand a user’s query.

Weekly Summary of AI topics
2

I don’t know the answer, and yet Vision is same as 4, it has a lot of issues and can be problematic. But AFAIK there should be own model for Vision and Discourse doesn’t use its own naming style.

3

FYI this is supported in Discourse Chatbot 🤖 (for “Basic” mode)

1 Like
4

(Without RAG that makes it a bit toothless; otherwise it gives a lot of fun)

2 Likes
5

Please call Sam Altman :phone: , he needs to add functions to the vision model.

3 Likes
6

At the moment gpt-4-turbo == gpt-4-0125-preview aka no vision.

@keegan is exploring some vision integration here:

Particularly adding captions to images via vision apis (both open and closed models)

I do really like the “demo” power of … starting a PM with bot, uploading an image and asking about it, but need to think through flow cause we would need to switch in and out of models.

Maybe a concept of “auto tool” can work here, so if we see an upload we automatically route to tool and then back to the main model… will have a think.

Technically wiring this up is not too complex within our architecture.

2 Likes
7

Thanks Sam!

According to Vision - OpenAI API

Vision and turbo should be mostly the same (not sure though, haven’t tested thoroughly yet).

1 Like