We are excited to announce that our platform supports images with OpenAI’s models. You can check-out this public prompt interaction example. You would have to set your model to gpt-4-vision-preview first since it’s the only model supporting image interpretation.

Prompt interaction explained

Our platform combines the data received both from the PDF file(s) and the image(s) and then feeds them to the OpenAI API along with any prompt input and/or context of your choosing.

Limitations

You may combine the example above with any amount of images and PDF/text files. You can also use any derivative of that context as future context in either rooms or solo session prompts!

Keep in touch

More exciting updates and guides are coming soon! Stay tuned, perhaps drop us a follow and keep on exploring prompting.