fix recommended order of multimodal inputs

README.md

@@ -621,11 +621,11 @@ def chat_with_image(client: openai.OpenAI, model_name: str):
         {
             'role': 'user',
             'content': [
-                {'type': 'text', 'text': 'Describe this image in detail.'},
                 {
                     'type': 'image_url',
                     'image_url': {'url': f'data:image/png;base64, {image_base64}'},
                 },
+                {'type': 'text', 'text': 'Describe this image in detail.'},
             ],
         }
     ]
@@ -667,11 +667,11 @@ def chat_with_video(client: openai.OpenAI, model_name:str):
         {
             "role": "user",
             "content": [
-                {"type": "text","text": "Describe the video in detail."},
                 {
                     "type": "video_url",
                     "video_url": {"url": f"data:video/mp4;base64,{video_base64}"},
                 },
+                {"type": "text","text": "Describe the video in detail."},
             ],
         }
     ]