Request: Prioritize multimodal image recognition release

[stepbystepcode]

Hi shantoislamdev, appreciate the ongoing work—README notes this feature is in development. Could you please prioritize and share an ETA for multimodal image recognition (image + text)? It’s critical for upcoming workflows (OCR, charts/screenshots understanding). Thanks!

[shantoislamdev]

Hi @stepbystepcode , thanks for the kind words and for raising this, I really appreciate the interest and feedback.

Multimodal image recognition (image + text) is definitely planned and already on the roadmap. However, it’s a fairly complex feature and I’m currently juggling multiple projects, so progress is slower than I’d like. Because of that, I can’t confidently provide a concrete ETA right now.

That said, this feature is important, and I’d love to move it forward faster. If anyone is interested in contributing or collaborating on this part (OCR, charts/screenshots understanding, etc.), contributions would be very welcome 💝

I’ll keep the README and issues updated as development progresses. Thanks again for your patience and support!