Update app.py

app.py

@@ -45,30 +45,42 @@ async def initialize(file_path, question):
         # Identify key sentences or phrases
         key_phrases = answer.split(". ")  # Split answer into sentences for more precise matching
         
-        relevant_pages = set()
+        # Score each page based on the presence of key phrases
+        page_scores = [0] * len(pages)
         for i, page in enumerate(pages):
             for phrase in key_phrases:
                 if phrase.lower() in page.page_content.lower():
-                    relevant_pages.add(i+1)  # Add page number if phrase is found
-
-        if relevant_pages:
-            page_numbers = ', '.join(str(p) for p in sorted(relevant_pages))
-            source_str = f"Relevant pages: {page_numbers}"
+                    page_scores[i] += 1
+        
+        # Determine the maximum score and get top pages
+        max_score = max(page_scores)
+        top_pages = [i+1 for i, score in enumerate(page_scores) if score == max_score]
+        
+        # Limit to the top 2 pages
+        num_top_pages = 2
+        top_pages = sorted(top_pages)[:num_top_pages]
+        
+        # Generate links for each top page
+        file_name = os.path.basename(file_path)
+        page_links = [f"[Page {p}](file://{os.path.abspath(file_path)}#page={p})" for p in top_pages]
+        page_links_str = ', '.join(page_links)
+        
+        if top_pages:
+            source_str = f"Top relevant page(s): {page_links_str}"
         else:
-            source_str = "Relevant pages: Not found in specific page"
+            source_str = "Top relevant page(s): Not found in specific page"
 
         # Create a clickable link for the document
-        file_name = os.path.basename(file_path)
-        source_link = f"[{file_name}](file://{os.path.abspath(file_path)})"
+        source_link = f"[Document: {file_name}](file://{os.path.abspath(file_path)})"
         
-        return f"Answer: {answer}\n{source_str}\n[Document: {source_link}]"
+        return f"Answer: {answer}\n{source_str}\n{source_link}"
     else:
         return "Error: Unable to process the document. Please ensure the PDF file is valid."
 
 # Define Gradio Interface
 input_file = gr.File(label="Upload PDF File")
 input_question = gr.Textbox(label="Ask about the document")
-output_text = gr.Textbox(label="Answer and Relevant Pages")
+output_text = gr.Textbox(label="Answer and Top Pages")
 
 async def pdf_qa(file, question):
     if file is None:
@@ -79,3 +91,4 @@ async def pdf_qa(file, question):
 
 # Create Gradio Interface with share=True to enable a public link
 gr.Interface(fn=pdf_qa, inputs=[input_file, input_question], outputs=output_text, title="PDF Question Answering System", description="Upload a PDF file and ask questions about the content.").launch(share=True)
+the content.").launch(share=True)