Ability to paste and chat with an image?
huytd opened this issue · comments
First of all, thank you so much for building Perplexica! It's superhelpful to be able to use something like Perplexity with Ollama.
I have a feature request: It would be great if Perplexica allow the user to paste an image to chat with.
![image](https://private-user-images.githubusercontent.com/613943/333743745-9bc2a0aa-6662-4e9d-9efe-4be028888269.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MjIzNTQ2MjcsIm5iZiI6MTcyMjM1NDMyNywicGF0aCI6Ii82MTM5NDMvMzMzNzQzNzQ1LTliYzJhMGFhLTY2NjItNGU5ZC05ZWZlLTRiZTAyODg4ODI2OS5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNzMwJTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDczMFQxNTQ1MjdaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT1lN2FhMGU2MWU4ZTI0MjRhZmI4NjZhN2U4YWNjNTNjNTg1ZGQ1YzVlNWEyYmZjOTNhMGU2ZDExMmY1NDEyM2RkJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.WXYNtfQ9z0UUPYQNS1TJbMOj6khs6PhAOYtFSvR0RSg)
I know not all models support multimodal but for models than can (GPT-4o, LLaVA,...), it would be very useful!
At least, I rarely see any open source AI search engine do this.
Hi, this feature is under development and will be released soon.
Thank you so much!!!!!!