Update app.py

app.py

@@ -201,50 +201,79 @@ def generate_output(context, query):
 #     except Exception as e:
 #         return {"results": []}, f"Error in workflow: {str(e)}"
 
-
 def complete_workflow(query):
     try:
-        # 🔹 Step 1: Perform Hybrid Search (Vector + BM25)
-        context_data, combined_context = hybrid_search_documents(query)
-
-        # 🔹 Step 2: Generate LLM-based Natural Language Output
-        llm = ChatOpenAI(model="gpt-4", openai_api_key=openai.api_key, temperature=0.7)
-        prompt_template = """
-        Use the following context to answer the question as accurately as possible:
-        
-        Context: {context}
-        Question: {question}
+        context_data, combined_context = search_documents(query)
         
-        Answer:
-        """
-        prompt = prompt_template.format(context=combined_context, question=query)
-        response = llm([HumanMessage(content=prompt)])
+        document_titles = list({os.path.basename(doc["title"]) for doc in context_data})  # Get only file names
+        formatted_titles = " " + "\n".join(document_titles)
 
-        # 🔹 Step 3: Format Results
-        document_titles = list({os.path.basename(doc["title"]) for doc in context_data})  # Extract unique file names
-        formatted_titles = "\n".join(document_titles)
+        total_results = len(context_data)  # Count the total number of results
 
         results = {
             "results": [
                 {
-                    "natural_language_output": response.content,
+                    "natural_language_output": generate_output(doc["relevant_text"], query),
                     "chunk_id": doc["chunk_id"],
-                    "document_id": doc["doc_id"],
+                    "document_id": doc["doc_id"],  # Assuming doc_id is the UUID
                     "title": doc["title"],
                     "relevant_text": doc["relevant_text"],
                     "page_number": doc["page_number"],
                     "score": doc["score"],
-                    "method": doc["method"],  # "vector" or "bm25"
                 }
                 for doc in context_data
             ],
-            "total_results": len(context_data),  # Return total number of retrieved results
+            "total_results": total_results  # Added total_results field
         }
 
-        return results, formatted_titles  # Return both results and formatted document titles
+        return results, formatted_titles  # Return results and formatted document titles
     except Exception as e:
         return {"results": [], "total_results": 0}, f"Error in workflow: {str(e)}"
 
+
+# def complete_workflow(query):
+#     try:
+#         # 🔹 Step 1: Perform Hybrid Search (Vector + BM25)
+#         context_data, combined_context = hybrid_search_documents(query)
+
+#         # 🔹 Step 2: Generate LLM-based Natural Language Output
+#         llm = ChatOpenAI(model="gpt-4", openai_api_key=openai.api_key, temperature=0.7)
+#         prompt_template = """
+#         Use the following context to answer the question as accurately as possible:
+        
+#         Context: {context}
+#         Question: {question}
+        
+#         Answer:
+#         """
+#         prompt = prompt_template.format(context=combined_context, question=query)
+#         response = llm([HumanMessage(content=prompt)])
+
+#         # 🔹 Step 3: Format Results
+#         document_titles = list({os.path.basename(doc["title"]) for doc in context_data})  # Extract unique file names
+#         formatted_titles = "\n".join(document_titles)
+
+#         results = {
+#             "results": [
+#                 {
+#                     "natural_language_output": response.content,
+#                     "chunk_id": doc["chunk_id"],
+#                     "document_id": doc["doc_id"],
+#                     "title": doc["title"],
+#                     "relevant_text": doc["relevant_text"],
+#                     "page_number": doc["page_number"],
+#                     "score": doc["score"],
+#                     "method": doc["method"],  # "vector" or "bm25"
+#                 }
+#                 for doc in context_data
+#             ],
+#             "total_results": len(context_data),  # Return total number of retrieved results
+#         }
+
+#         return results, formatted_titles  # Return both results and formatted document titles
+#     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 ")