I am using Open AI APIs to build my own Chat Bot, however I am unable to find an option where i can upload the documents from which gpt can try to search an answer.
Not sure which model you are using but if the model supports Vision API, you can convert file into image file and send it.
However, in my experience, extracting texts will work a lot better than the case.
Please reference this page to find out the available features on each model:
https://platform.openai.com/docs/models#gpt-4o