Update app.py

app.py

@@ -1,41 +1,14 @@
 import torch
 import gradio as gr
+from transformers import pipeline
 from transformers import T5ForConditionalGeneration, T5Tokenizer
-import fitz  # PyMuPDF for extracting text from PDF
 
-# Load the model and tokenizer
 model_path = 'Sibinraj/T5-finetuned-dialogue_sumxx'
 model = T5ForConditionalGeneration.from_pretrained(model_path)
 tokenizer = T5Tokenizer.from_pretrained(model_path)
 
-def extract_text_from_pdf(pdf_path):
-    """
-    Extracts text from a given PDF file.
-    
-    Args:
-        pdf_path (str): Path to the PDF file.
-    
-    Returns:
-        str: Extracted text from the PDF.
-    """
-    text = ""
-    with fitz.open(pdf_path) as doc:
-        for page in doc:
-            text += page.get_text()
-    return text
-
 def summarize_text(text, max_length, show_length):
-    """
-    Summarizes the given text using a T5 model.
-    
-    Args:
-        text (str): The text to summarize.
-        max_length (int): The maximum length of the summary.
-        show_length (bool): Whether to show the length of the summary.
-    
-    Returns:
-        str: The summarized text.
-    """
+    # Preprocess the text
     inputs = tokenizer.encode(
         "summarize: " + text,
         return_tensors='pt',
@@ -44,6 +17,7 @@ def summarize_text(text, max_length, show_length):
         padding='max_length'
     )
     
+    # Generate the summary
     summary_ids = model.generate(
         inputs,
         max_length=max_length + 20,  # Allow some buffer
@@ -53,8 +27,10 @@ def summarize_text(text, max_length, show_length):
         early_stopping=True
     )
     
+    # Decode the summary
     summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
     
+    # Trim the summary to the desired length
     summary_words = summary.split()
     if len(summary_words) > max_length:
         summary = ' '.join(summary_words[:max_length])
@@ -70,54 +46,26 @@ def summarize_text(text, max_length, show_length):
         additional_summary = tokenizer.decode(additional_tokens[0], skip_special_tokens=True)
         summary += ' ' + ' '.join(additional_summary.split()[len(summary_words):max_length])
     
+    # If show_length is True, append the length of the summary
     if show_length:
         summary_length = len(summary.split())
         summary = f"{summary}\n\n(Summary length: {summary_length} words)"
     
     return summary
 
-def handle_input(input_type, text, pdf, max_length, show_length):
-    """
-    Handles the user input based on the selected input type.
-    
-    Args:
-        input_type (str): The type of input (text or PDF).
-        text (str): The text input.
-        pdf (UploadedFile): The uploaded PDF file.
-        max_length (int): The maximum length of the summary.
-        show_length (bool): Whether to show the length of the summary.
-    
-    Returns:
-        str: The summarized text.
-    """
-    if input_type == 'Text':
-        return summarize_text(text, max_length, show_length)
-    elif input_type == 'PDF':
-        extracted_text = extract_text_from_pdf(pdf.name)
-        return summarize_text(extracted_text, max_length, show_length)
-
-
-# Define examples for text input
-examples_text = [
-    ['Text', 'The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.', None, 50, False],
-    ['Text', '#Person1#: Is this the workshop to prepare for an interview? #Person2#: This is the interview class. Welcome to our class. #Person1#: I am really excited to be taking this workshop so that I can get ready for my interview next week. #Person2#: We are all learning things that will help us in our interview. What do you think are some important considerations going into your interview? #Person1#: I think that we should dress neatly and appropriately. #Person2#: Yes. Second, as you can imagine, attitude and friendliness go a long way. #Person1#: Yes, and I always feel much better when I am friendly. #Person2#: Believe it or not, the interviewers are as interested in your questions as they are in your answers. #Person1#: Any more hints as to what I should do in an interview? #Person2#: Always be honest with your answers. The interviewers really do want to know if you will be a good fit for them.', None, 50, False]
-]
-
-# Define the Gradio interface
 interface = gr.Interface(
-    fn=handle_input,
+    fn=summarize_text,
     inputs=[
-        gr.Radio(['Text', 'PDF'], label='Input Type', type='value'),
-        gr.Textbox(lines=10, placeholder='Enter Text Here...', label='Input Text', visible=True),
-        gr.File(label='Upload PDF', type='filepath', visible=True),
+        gr.Textbox(lines=10, placeholder='Enter Text Here...', label='Input text'),
         gr.Slider(minimum=10, maximum=150, step=1, label='Max Length'),
-        gr.Checkbox(label='Show summary length', value=False)
+        gr.Checkbox(label='Show summary length')
     ],
     outputs=gr.Textbox(label='Summarized Text'),
-    title='Text or PDF Summarizer using T5-finetuned-dialogue_sumxx',
-    examples=examples_text                                                                                                                                                                                                                                                              
-
+    title='Text Summarizer using T5-finetuned-dialogue_sumxx',
+    examples=[
+        ['The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building, and the tallest structure in Paris. Its base is square, measuring 125 metres (410 ft) on each side. During its construction, the Eiffel Tower surpassed the Washington Monument to become the tallest man-made structure in the world, a title it held for 41 years until the Chrysler Building in New York City was finished in 1930. It was the first structure to reach a height of 300 metres. Due to the addition of a broadcasting aerial at the top of the tower in 1957, it is now taller than the Chrysler Building by 5.2 metres (17 ft). Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France after the Millau Viaduct.', 50, 50],
+        ['#Person1#: Is this the workshop to prepare for an interview? #Person2#: This is the interview class. Welcome to our class. #Person1#: I am really excited to be taking this workshop so that I can get ready for my interview next week. #Person2#: We are all learning things that will help us in our interview. What do you think are some important considerations going into your interview? #Person1#: I think that we should dress neatly and appropriately. #Person2#: Yes. Second, as you can imagine, attitude and friendliness go a long way. #Person1#: Yes, and I always feel much better when I am friendly. #Person2#: Believe it or not, the interviewers are as interested in your questions as they are in your answers. #Person1#: Any more hints as to what I should do in an interview? #Person2#: Always be honest with your answers. The interviewers really do want to know if you will be a good fit for them.', 50, 50]
+    ]
 )
 
-# Launch the Gradio interface
-interface.launch()
+interface.launch()