Update app.py

app.py

@@ -107,17 +107,10 @@ def complete_workflow(query):
     try:
         context_data = search_documents(query)
 
-        # print("Context Data")
-        
-        # [print(doc) for doc in context_data]
-
         reranked = rerank(query, context_data)
 
         context_data= []
-        
-        # print("\n\n reranked data")
-        # print(reranked.data)
-
+   
         for i, entry in enumerate(reranked.data):  # Access the 'data' attribute
             context_data.append({
                 'chunk_id': entry['document']['chunk_id'],
@@ -127,10 +120,6 @@ def complete_workflow(query):
                 'page_number': str(entry['document']['page_number']),
                 'score': str(entry['score'])
             })
-
-        # print("\n\n New Context Data")
-        # [print(doc) for doc in context_data]
-
         
         document_titles = list({os.path.basename(doc["title"]) for doc in context_data})  # Get only file names
         formatted_titles = " " + "\n".join(document_titles)
@@ -158,51 +147,6 @@ def complete_workflow(query):
         return {"results": [], "total_results": 0}, f"Error in workflow: {str(e)}"
 
 
-async def async_complete_workflow(query):
-    try:
-        search_task = asyncio.to_thread(search_documents, query)
-        context_data = await search_task  # Run search in parallel
-
-        rerank_task = asyncio.to_thread(rerank, query, context_data)
-        reranked = await rerank_task  # Run rerank in parallel
-
-        # Process results
-        context_data = [
-            {
-                'chunk_id': entry['document']['chunk_id'],
-                'doc_id': entry['document']['doc_id'],
-                'title': entry['document']['title'],
-                'text': entry['document']['text'],
-                'page_number': str(entry['document']['page_number']),
-                'score': str(entry['score'])
-            }
-            for entry in reranked.data
-        ]
-
-        # Generate responses
-        output_tasks = [asyncio.to_thread(generate_output, doc["text"], query) for doc in context_data]
-        outputs = await asyncio.gather(*output_tasks)  # Run LLM calls in parallel
-
-        results = {
-            "results": [
-                {
-                    "natural_language_output": outputs[i],
-                    "chunk_id": doc["chunk_id"],
-                    "document_id": doc["doc_id"],
-                    "title": doc["title"],
-                    "text": doc["text"],
-                    "page_number": doc["page_number"],
-                    "score": doc["score"],
-                }
-                for i, doc in enumerate(context_data)
-            ],
-            "total_results": len(context_data)
-        }
-
-        return results
-    except Exception as e:
-        return {"results": [], "total_results": 0}, f"Error in workflow: {str(e)}"
-
 def gradio_app():
     with gr.Blocks(css=".result-output {width: 150%; font-size: 16px; padding: 10px;}") as app:
         gr.Markdown("### Intelligent Document Search Prototype-v0.1.2 ")