npnpatidar
npnpatidar
+1
I support this. marker is the best open source OCR library.
Same issue. This is critical for any usability of agent.  
Thank you. It is working. The issue was with web browser model. It seems all models do not work. Gemini , Mistral etc which are freely available do not work....
Instead of updating **browser_agent.py**, change was required in **models.py**. I have created a [pull](https://github.com/frdel/agent-zero/pull/351) request to enable use of gemini in both embedding as well as browser model.
Also please provide ARM64 docker images also.
Which one you want ? Send the details with screenshot, I will try.