Agent is not forwarding the file as binary to tools

General
1

I am developing a document processing agent using Ollama. It works as below,

  1. User upload the file image or pdf to a chat / Playground
  2. Document processing agent configured with Ollama llama3.2 llm and custom OCR tool
  3. Customer OCR tool should get the uploaded image / pdf, using Surya OCR to covert into text
  4. Document processing agent process the text returned by Custom OCR tool and send the text to LLM

When I test this via playground, Custom OCR tool receive the input data as [img-0]. It’s not receiving the binary also not the file type. Can you guide/direct me how to achieve this?

2

Hey @Balakumaran
Thanks for reaching out and for using Agno! I’ve looped in the right engineers to help with your question. We usually respond within 24 hours, but if this is urgent, just let us know, and we’ll do our best to prioritize it.
Appreciate your patience—we’ll get back to you soon!

3

Hey @Monali
Appreciate your support.

It will be great if it can be prioritized.We are stuck on this.

Thanks,