Update app.py

app.py

@@ -33,7 +33,7 @@ async def initialize(file_path, question):
         
         # Extract content from each page and store along with page number
         page_contexts = [f"Page {i+1}: {page.page_content}" for i, page in enumerate(pages)]
-        context = "\n".join(page_contexts)  # Using the first 30 pages for context
+        context = "\n".join(page_contexts[:30])  # Using the first 30 pages for context
         
         # Load the question-answering chain
         stuff_chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
@@ -52,17 +52,20 @@ async def initialize(file_path, question):
                 if phrase.lower() in page.page_content.lower():
                     page_scores[i] += 1
         
-        # Determine the maximum score
+        # 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]
         
-        # Collect the page numbers with the maximum score
-        relevant_pages = [i+1 for i, score in enumerate(page_scores) if score == max_score]
+        # Optionally, limit the number of top pages to display
+        num_top_pages = 5  # Adjust this value based on your needs
+        if len(top_pages) > num_top_pages:
+            top_pages = sorted(top_pages)[:num_top_pages]
         
-        if relevant_pages:
-            page_numbers = ', '.join(str(p) for p in sorted(relevant_pages))
-            source_str = f"Relevant page(s): {page_numbers}"
+        if top_pages:
+            page_numbers = ', '.join(str(p) for p in sorted(top_pages))
+            source_str = f"Top relevant page(s): {page_numbers}"
         else:
-            source_str = "Relevant page(s): 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)
@@ -75,7 +78,7 @@ async def initialize(file_path, question):
 # 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: