Update app.py

app.py

@@ -81,6 +81,33 @@ def format_answer_string(answer: str):
     
     return formatted_answer
 
+def format_relevant_documents(relevant_docs: list):
+    """
+    This function formats the relevant document metadata and content for readable output.
+    It extracts the heading, page number, and a snippet of the content from each document.
+    """
+    formatted_docs = "Relevant Documents:\n\n"
+    
+    for idx, (doc, score) in enumerate(relevant_docs):
+        # Extract the relevant metadata
+        heading = doc.metadata.get('heading', 'Unnamed Document')
+        page_number = int(doc.metadata.get('page_number', -1))
+        source = doc.metadata.get('source', 'Unknown Source')
+        confidence = round(score, 4)  # Rounding the score for cleaner output
+        
+        # Add the formatted details to the output string
+        formatted_docs += f"Document {idx + 1}:\n"
+        formatted_docs += f"  - Heading: {heading}\n"
+        formatted_docs += f"  - Page Number: {page_number}\n"
+        formatted_docs += f"  - Source: {source}\n"
+        formatted_docs += f"  - Confidence Score: {confidence}\n"
+        
+        # Optionally include a snippet from the content
+        content_snippet = doc.page_content[:200]  # Take the first 200 characters for preview
+        formatted_docs += f"  - Content Snippet: {content_snippet}...\n\n"
+
+    return formatted_docs.strip()
+
 
 # Function to handle PDF processing API call
 def process_pdf(pdf_file):
@@ -195,16 +222,16 @@ with gr.Blocks(css=CSS) as demo:
             outputs=pdf_output
         )
 
-    with gr.Tab("Search"):
-        query_input = gr.Textbox(label="Enter Search Query")
-        search_output = gr.Textbox(label="Search Confidence Result", interactive=False)
+    # with gr.Tab("Search"):
+    #     query_input = gr.Textbox(label="Enter Search Query")
+    #     search_output = gr.Textbox(label="Search Confidence Result", interactive=False)
 
-        search_button = gr.Button("Search")
-        search_button.click(
-            search_api,
-            inputs=query_input,
-            outputs=search_output
-        )
+    #     search_button = gr.Button("Search")
+    #     search_button.click(
+    #         search_api,
+    #         inputs=query_input,
+    #         outputs=search_output
+    #     )
 
     with gr.Tab("Answer with RAG"):
         question_input = gr.Textbox(label="Enter Question for RAG")