Update app.py

app.py

@@ -1,7 +1,5 @@
 # Research Paper Summarizer using LangChain and Gradio
-# Updated for Hugging Face Spaces with beautiful Gradio UI
-# Install required packages first:
-# pip install gradio langchain openai pypdf2 reportlab python-dotenv transformers torch
+# Hugging Face Spaces ready – robust chunking for large PDFs
 
 import gradio as gr
 import os
@@ -11,7 +9,6 @@ from io import BytesIO
 from reportlab.lib.pagesizes import letter
 from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
 from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
-from reportlab.lib.units import inch
 import tempfile
 
 # LangChain imports
@@ -20,152 +17,157 @@ from langchain.chains.summarize import load_summarize_chain
 from langchain.docstore.document import Document
 from langchain.llms import OpenAI
 from langchain.chat_models import ChatOpenAI
-
-# Alternative: Use Hugging Face models
 from langchain.llms import HuggingFacePipeline
-from transformers import pipeline
+
+from transformers import pipeline, AutoTokenizer
 
 load_dotenv()
 
+# --- Helper for robust chunking ---
+def chunk_text_for_hf(text, tokenizer, max_tokens=1024, overlap=50):
+    """Split text into chunks compatible with Hugging Face summarizers."""
+    tokens = tokenizer.encode(text)
+    total_tokens = len(tokens)
+    if total_tokens <= max_tokens:
+        return [text]
+    chunks = []
+    start = 0
+    while start < total_tokens:
+        end = min(start + max_tokens, total_tokens)
+        chunk_tokens = tokens[start:end]
+        chunk_text = tokenizer.decode(chunk_tokens, skip_special_tokens=True)
+        chunks.append(chunk_text)
+        start += max_tokens - overlap
+    return chunks
+
+def summarize_long_text_hf(text, summarizer, tokenizer, max_tokens=1024, overlap=50, max_length=150, min_length=40):
+    """Summarize long text by chunking and combining summaries (Hugging Face models)."""
+    text_chunks = chunk_text_for_hf(text, tokenizer, max_tokens, overlap)
+    summaries = []
+    for chunk in text_chunks:
+        summary = summarizer(
+            chunk,
+            max_length=max_length,
+            min_length=min_length,
+            do_sample=False,
+            truncation=True
+        )[0]['summary_text']
+        summaries.append(summary)
+    return " ".join(summaries)
+
 class ResearchPaperSummarizer:
     def __init__(self):
         self.llm = None
         self.model_info = ""
-        
+        self.hf_tokenizer = None
+        self.hf_summarizer = None
+        self.is_hf_pipeline = False
+
     def setup_llm(self, model_choice):
         """Setup LLM based on user choice"""
-        # Check available API keys from environment
         openai_api_key = os.getenv("OPENAI_API_KEY")
         hf_token = os.getenv("HUGGINGFACE_TOKEN")
-        
+        self.is_hf_pipeline = False
         try:
             if "OpenAI" in model_choice:
                 if not openai_api_key:
                     return False, "❌ OpenAI API Key not found in environment variables. Please add OPENAI_API_KEY to your Hugging Face Space settings."
-                
                 os.environ["OPENAI_API_KEY"] = openai_api_key
                 if "GPT-4" in model_choice:
                     self.llm = ChatOpenAI(model_name="gpt-4", temperature=0.3)
-                    self.model_info = "🚀 Using GPT-4 (Premium) - Highest quality summaries"
+                    self.model_info = "🚀 Using GPT-4 (Premium)"
                 else:
                     self.llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0.3)
-                    self.model_info = "🚀 Using GPT-3.5 Turbo - Fast and efficient"
-                    
+                    self.model_info = "🚀 Using GPT-3.5 Turbo"
             else:
-                # Use Hugging Face models (free but slower)
+                self.is_hf_pipeline = True
                 if "BART" in model_choice:
-                    summarizer = pipeline(
-                        "summarization", 
-                        model="facebook/bart-large-cnn",
-                        tokenizer="facebook/bart-large-cnn",
-                        use_auth_token=hf_token if hf_token else None
-                    )
-                    self.model_info = "🤗 Using BART model - Free, optimized for summarization"
+                    model_id = "facebook/bart-large-cnn"
                 else:
-                    summarizer = pipeline(
-                        "summarization", 
-                        model="t5-base",
-                        tokenizer="t5-base",
-                        use_auth_token=hf_token if hf_token else None
-                    )
-                    self.model_info = "🤗 Using T5 model - Free, versatile model"
-                
-                self.llm = HuggingFacePipeline(pipeline=summarizer)
-                
+                    model_id = "t5-base"
+                self.hf_summarizer = pipeline(
+                    "summarization",
+                    model=model_id,
+                    tokenizer=model_id,
+                    use_auth_token=hf_token if hf_token else None
+                )
+                self.hf_tokenizer = AutoTokenizer.from_pretrained(model_id, use_auth_token=hf_token if hf_token else None)
+                self.llm = HuggingFacePipeline(pipeline=self.hf_summarizer)
+                self.model_info = f"🤗 Using {model_id} model"
             return True, f"✅ Model loaded successfully! {self.model_info}"
-            
         except Exception as e:
             return False, f"❌ Error loading model: {str(e)}"
-    
+
     def extract_text_from_pdf(self, pdf_file):
         """Extract text from uploaded PDF"""
         try:
             if pdf_file is None:
                 return None, "❌ No PDF file uploaded"
-                
             pdf_reader = PyPDF2.PdfReader(pdf_file)
             text = ""
             for page in pdf_reader.pages:
-                text += page.extract_text()
-            
+                page_text = page.extract_text()
+                if page_text:
+                    text += page_text
             if not text.strip():
                 return None, "❌ No text could be extracted from the PDF"
-                
             return text, f"✅ Successfully extracted {len(text):,} characters from PDF"
         except Exception as e:
             return None, f"❌ Error reading PDF: {str(e)}"
-    
+
     def create_documents(self, text):
-        """Split text into manageable chunks"""
+        """Split text into manageable chunks for LangChain LLMs"""
         text_splitter = RecursiveCharacterTextSplitter(
             chunk_size=4000,
             chunk_overlap=200,
             length_function=len
         )
-        
         chunks = text_splitter.split_text(text)
         documents = [Document(page_content=chunk) for chunk in chunks]
         return documents
-    
-    def generate_summary(self, documents, summary_type="map_reduce"):
-        """Generate summary using LangChain"""
+
+    def generate_summary(self, documents, summary_type="map_reduce", raw_text=None):
+        """Generate summary using LangChain or robust HF chunking"""
         try:
-            if summary_type == "map_reduce":
-                chain = load_summarize_chain(
-                    self.llm, 
-                    chain_type="map_reduce",
-                    verbose=False
+            # For Hugging Face models, use robust chunking
+            if self.is_hf_pipeline and raw_text and self.hf_summarizer and self.hf_tokenizer:
+                return summarize_long_text_hf(
+                    raw_text, self.hf_summarizer, self.hf_tokenizer,
+                    max_tokens=1024, overlap=50, max_length=150, min_length=40
                 )
+            # For OpenAI or other models, use LangChain summarization chain
+            if summary_type == "map_reduce":
+                chain = load_summarize_chain(self.llm, chain_type="map_reduce", verbose=False)
             elif summary_type == "stuff":
-                chain = load_summarize_chain(
-                    self.llm, 
-                    chain_type="stuff",
-                    verbose=False
-                )
-            else:  # refine
-                chain = load_summarize_chain(
-                    self.llm, 
-                    chain_type="refine",
-                    verbose=False
-                )
-            
+                chain = load_summarize_chain(self.llm, chain_type="stuff", verbose=False)
+            else:
+                chain = load_summarize_chain(self.llm, chain_type="refine", verbose=False)
             summary = chain.run(documents)
             return summary
-            
         except Exception as e:
             return f"❌ Error generating summary: {str(e)}"
-    
+
     def create_structured_summary(self, text, documents):
         """Create a structured summary with different sections"""
         summaries = {}
-        
         # Overall Summary
-        summaries['overall'] = self.generate_summary(documents, "map_reduce")
-        
-        # Key Points - Create a separate prompt for key points
-        if len(text) > 8000:
-            key_points_text = text[:8000]
-        else:
-            key_points_text = text
-            
+        summaries['overall'] = self.generate_summary(documents, "map_reduce", raw_text=text)
+        # Key Points - Use first 8000 chars for key points
+        key_points_text = text[:8000] if len(text) > 8000 else text
         key_points_prompt = f"""
         Extract the 5-7 most important key points from this research paper:
-        
         {key_points_text}
         """
-        
         key_points_docs = [Document(page_content=key_points_prompt)]
-        summaries['key_points'] = self.generate_summary(key_points_docs, "stuff")
-        
+        summaries['key_points'] = self.generate_summary(key_points_docs, "stuff", raw_text=key_points_prompt)
         return summaries
-    
+
     def create_pdf_summary(self, summaries, paper_title="Research Paper Summary"):
         """Create PDF with the summary"""
         buffer = BytesIO()
         doc = SimpleDocTemplate(buffer, pagesize=letter)
         styles = getSampleStyleSheet()
         story = []
-        
         # Title
         title_style = ParagraphStyle(
             'CustomTitle',
@@ -174,30 +176,23 @@ class ResearchPaperSummarizer:
             spaceAfter=30,
             textColor='darkblue'
         )
-        
         story.append(Paragraph(paper_title, title_style))
         story.append(Spacer(1, 12))
-        
         # Overall Summary
         story.append(Paragraph("Overall Summary", styles['Heading2']))
         story.append(Spacer(1, 12))
         story.append(Paragraph(summaries.get('overall', 'No summary available'), styles['Normal']))
         story.append(Spacer(1, 20))
-        
         # Key Points
         if 'key_points' in summaries:
             story.append(Paragraph("Key Points", styles['Heading2']))
             story.append(Spacer(1, 12))
             story.append(Paragraph(summaries['key_points'], styles['Normal']))
-        
         doc.build(story)
         buffer.seek(0)
-        
-        # Save to temporary file for Gradio
         temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.pdf')
         temp_file.write(buffer.getvalue())
         temp_file.close()
-        
         return temp_file.name
 
 # Initialize the summarizer
@@ -205,40 +200,31 @@ summarizer = ResearchPaperSummarizer()
 
 def process_paper(pdf_file, model_choice, summary_type, include_key_points, paper_title):
     """Main function to process the research paper"""
-    
     # Setup model
     success, message = summarizer.setup_llm(model_choice)
     if not success:
         return message, "", "", None
-    
     status_message = message + "\n\n"
-    
     # Extract text from PDF
     text, extract_message = summarizer.extract_text_from_pdf(pdf_file)
     status_message += extract_message + "\n\n"
-    
     if text is None:
         return status_message, "", "", None
-    
     # Create documents
     documents = summarizer.create_documents(text)
     status_message += f"📝 Text split into {len(documents)} chunks for processing\n\n"
-    
     # Generate summary
     status_message += "🔄 Generating summary... Please wait...\n\n"
-    
     try:
         if include_key_points:
             summaries = summarizer.create_structured_summary(text, documents)
             overall_summary = summaries.get('overall', 'No summary generated')
             key_points = summaries.get('key_points', 'No key points generated')
         else:
-            overall_summary = summarizer.generate_summary(documents, summary_type)
+            overall_summary = summarizer.generate_summary(documents, summary_type, raw_text=text)
             key_points = "Key points not requested"
             summaries = {'overall': overall_summary}
-        
         status_message += "🎉 Summary generated successfully!"
-        
         # Generate PDF if title is provided
         pdf_file_path = None
         if paper_title and paper_title.strip():
@@ -247,9 +233,7 @@ def process_paper(pdf_file, model_choice, summary_type, include_key_points, pape
                 status_message += "\n📄 PDF summary created!"
             except Exception as e:
                 status_message += f"\n⚠️ PDF creation failed: {str(e)}"
-        
         return status_message, overall_summary, key_points, pdf_file_path
-        
     except Exception as e:
         return status_message + f"❌ Error during processing: {str(e)}", "", "", None
 
@@ -269,20 +253,17 @@ custom_css = """
         background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
         font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
     }
-    
     .gr-interface {
         background: rgba(255, 255, 255, 0.95);
         backdrop-filter: blur(10px);
         border-radius: 20px;
         box-shadow: 0 20px 40px rgba(0, 0, 0, 0.1);
     }
-    
     .gr-box {
         border-radius: 15px;
         border: 2px solid #e1e5e9;
         background: linear-gradient(145deg, #ffffff, #f0f2f5);
     }
-    
     .gr-button {
         background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
         border: none;
@@ -291,17 +272,14 @@ custom_css = """
         font-weight: bold;
         transition: transform 0.2s;
     }
-    
     .gr-button:hover {
         transform: translateY(-2px);
         box-shadow: 0 5px 15px rgba(102, 126, 234, 0.4);
     }
-    
     .gr-textbox, .gr-dropdown {
         border-radius: 10px;
         border: 2px solid #e1e5e9;
     }
-    
     .gr-file {
         border-radius: 15px;
         border: 3px dashed #667eea;
@@ -311,8 +289,6 @@ custom_css = """
 
 # Create the Gradio interface
 with gr.Blocks(css=custom_css, title="🔬 Research Paper Summarizer", theme=gr.themes.Soft()) as app:
-    
-    # Header
     gr.Markdown(
         """
         # 🔬 Research Paper Summarizer
@@ -322,22 +298,18 @@ with gr.Blocks(css=custom_css, title="🔬 Research Paper Summarizer", theme=gr.
         """,
         elem_classes="header"
     )
-    
     with gr.Row():
         with gr.Column(scale=1):
-            # Input Section
             gr.Markdown("## 📁 Upload & Configure")
-            
             pdf_input = gr.File(
                 label="📄 Upload Research Paper (PDF)",
                 file_types=[".pdf"],
                 elem_classes="file-upload"
             )
-            
             model_choice = gr.Dropdown(
                 choices=[
                     "OpenAI GPT-3.5",
-                    "OpenAI GPT-4", 
+                    "OpenAI GPT-4",
                     "Hugging Face BART",
                     "Hugging Face T5"
                 ],
@@ -345,39 +317,31 @@ with gr.Blocks(css=custom_css, title="🔬 Research Paper Summarizer", theme=gr.
                 label="🤖 Choose AI Model",
                 info="Free models work without API keys"
             )
-            
             model_info = gr.Markdown("")
-            
             summary_type = gr.Dropdown(
                 choices=["map_reduce", "stuff", "refine"],
                 value="map_reduce",
                 label="📋 Summary Method",
                 info="map_reduce: best for long papers | stuff: faster for short papers | refine: iterative improvement"
             )
-            
             include_key_points = gr.Checkbox(
                 label="🔑 Include Key Points",
                 value=True,
                 info="Extract important key points separately"
             )
-            
             paper_title = gr.Textbox(
                 label="📝 Paper Title (for PDF export)",
                 placeholder="Enter the title of your research paper...",
                 info="Optional: Used as title in the generated PDF summary"
             )
-            
             process_btn = gr.Button(
                 "🚀 Generate Summary",
                 variant="primary",
                 size="lg",
                 elem_classes="process-button"
             )
-        
         with gr.Column(scale=2):
-            # Output Section
             gr.Markdown("## 📊 Results")
-            
             status_output = gr.Textbox(
                 label="📈 Processing Status",
                 lines=8,
@@ -385,7 +349,6 @@ with gr.Blocks(css=custom_css, title="🔬 Research Paper Summarizer", theme=gr.
                 interactive=False,
                 show_copy_button=True
             )
-            
             summary_output = gr.Textbox(
                 label="📋 Overall Summary",
                 lines=10,
@@ -394,7 +357,6 @@ with gr.Blocks(css=custom_css, title="🔬 Research Paper Summarizer", theme=gr.
                 show_copy_button=True,
                 placeholder="Your paper summary will appear here..."
             )
-            
             key_points_output = gr.Textbox(
                 label="🔑 Key Points",
                 lines=8,
@@ -403,38 +365,31 @@ with gr.Blocks(css=custom_css, title="🔬 Research Paper Summarizer", theme=gr.
                 show_copy_button=True,
                 placeholder="Key points will be extracted here..."
             )
-            
             pdf_output = gr.File(
                 label="📄 Download PDF Summary",
                 interactive=False
             )
-    
-    # Setup Instructions
     with gr.Accordion("🔧 Setup Instructions for API Keys", open=False):
         gr.Markdown(
             """
             ### For Enhanced Performance (Optional):
-            
             **OpenAI API Setup:**
             1. Get your API key from [OpenAI Platform](https://platform.openai.com/api-keys)
             2. In your Hugging Face Space settings, add: `OPENAI_API_KEY = your_key_here`
             3. Restart your Space to apply changes
-            
+
             **Hugging Face Token Setup:**
             1. Get your token from [HuggingFace Settings](https://huggingface.co/settings/tokens)
             2. Add: `HUGGINGFACE_TOKEN = your_token_here`
             3. Provides access to gated models and higher rate limits
-            
+
             **Note:** Free Hugging Face models work without any API keys but may be slower on first load.
             """
         )
-    
-    # Performance Tips
     with gr.Accordion("💡 Tips for Best Results", open=False):
         gr.Markdown(
             """
             ### Optimization Tips:
-            
             - **📄 File Size:** Smaller PDFs (< 10MB) process faster
             - **🤖 Model Choice:** OpenAI models provide highest quality but require API keys
             - **⚡ Speed:** "stuff" method is fastest for papers under 20 pages
@@ -443,14 +398,11 @@ with gr.Blocks(css=custom_css, title="🔬 Research Paper Summarizer", theme=gr.
             - **📱 Mobile:** Works on mobile devices but desktop recommended for large files
             """
         )
-    
-    # Event handlers
     model_choice.change(
         fn=get_model_info,
         inputs=[model_choice],
         outputs=[model_info]
     )
-    
     process_btn.click(
         fn=process_paper,
         inputs=[
@@ -468,8 +420,6 @@ with gr.Blocks(css=custom_css, title="🔬 Research Paper Summarizer", theme=gr.
         ],
         show_progress=True
     )
-    
-    # Footer
     gr.Markdown(
         """
         ---
@@ -481,7 +431,6 @@ with gr.Blocks(css=custom_css, title="🔬 Research Paper Summarizer", theme=gr.
         elem_classes="footer"
     )
 
-# Launch the app
 if __name__ == "__main__":
     app.launch(
         share=True,
@@ -489,4 +438,5 @@ if __name__ == "__main__":
         debug=True,
         server_name="0.0.0.0",
         server_port=7860
-    )
+    )
+