import base64 import requests def encode_image_to_base64(image_path): with open(image_path, "rb") as image_file: return base64.b64encode(image_file.read()).decode('utf-8') def perform_ocr(image_path): base64_image = encode_image_to_base64(image_path) response = requests.post( "http://localhost:9000/v1/chat/completions", json={ "model":"minicpmo_2_6", "messages": [ { "role": "user", "content": [ { "type": "image_url", "image_url": { "url": "https://www.nhmagazine.com/content/uploads/2019/05/mtwashingtonFranconia-2-19-18-108-Edit-Edit.jpg" }, }, { "type": "text", "text": "(./) What is shown in this image? Write a detailed response analyzing the scene.", }, ], # "content": "What is your name?", } ], "max_tokens": 256, "frequency_penalty": 1.0, "top_p": 0.1, "temperature": 0, } ) return response.text if __name__ == "__main__": image_path = "../images/plain.jpg" result = perform_ocr(image_path) print(result)