关于“使用多模态 Gemini 和多模态 RAG 检查富文档：实验室挑战赛”的评价

DEVASISH V. · 已于 over 1 year前审核

nice

KIRITEN S. · 已于 over 1 year前审核

Aditya . · 已于 over 1 year前审核

22B01A4261 A. · 已于 over 1 year前审核

Aditya V. · 已于 over 1 year前审核

This lab is having so many issues

Chaithhanya Sai K. · 已于 over 1 year前审核

Sai Nomitha Y. · 已于 over 1 year前审核

Dip G. · 已于 over 1 year前审核

good

Rounak _. · 已于 over 1 year前审核

ANSHUL R. · 已于 over 1 year前审核

2165_Rishika P. · 已于 over 1 year前审核

ggjfykujgb

Karthi T. · 已于 over 1 year前审核

Dip G. · 已于 over 1 year前审核

Harsh G. · 已于 over 1 year前审核

Felipe S. · 已于 over 1 year前审核

Divam S. · 已于 over 1 year前审核

Jasnoor K. · 已于 over 1 year前审核

Alejo C. · 已于 over 1 year前审核

1155_Abhinav S. · 已于 over 1 year前审核

Lakshmisha R. · 已于 over 1 year前审核

Task 1.2 has some sort of bug. I cannot get passed it and am getting the following error --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) Cell In[157], line 8 1 # "COMPLETE THE MISSING PART AND RUN THIS CELL" 2 3 # In the last part of this task, you're going to print your contents and responses with the prompt and responses title provided. Use descriptive titles to help organize the output (e.g., "Prompts", "Model Responses") and then display the prompt and responses by using the print() function. 4 5 # Hint: "\n" inserts a newline character for clearer separation between the sections. 7 print("-------Prompt--------") ----> 8 print_multimodal_prompt(contents) 10 print("\n-------Response--------") 11 for response in responses: Cell In[5], line 64, in print_multimodal_prompt(contents) 59 """ 60 Given contents that would be sent to Gemini, 61 output the full multimodal prompt for ease of readability. 62 """ 63 for content in contents: ---> 64 if display_content_as_image(content): 65 continue 66 if display_content_as_video(content): Cell In[5], line 44, in display_content_as_image(content) 42 if not isinstance(content, Image): 43 return False ---> 44 display_images([content]) 45 return True File ~/training-data-analyst/self-paced-labs/gemini/utils/intro_multimodal_rag_utils.py:905, in display_images(images, resize_ratio) 903 # Resize and display each image 904 for img in pil_images: --> 905 original_width, original_height = img.size 906 new_width = int(original_width * resize_ratio) 907 new_height = int(original_height * resize_ratio) AttributeError: 'Image' object has no attribute 'size'

Emmanuel I. · 已于 over 1 year前审核

yes

Saloni S. · 已于 over 1 year前审核

Sukhpreet S. · 已于 over 1 year前审核

Akshay M. · 已于 over 1 year前审核

Vinayak M. · 已于 over 1 year前审核