Update app.py

app.py

@@ -227,66 +227,58 @@ def ask_question(question, temperature, top_p, repetition_penalty, web_search):
     if not question:
         return "Please enter a question."
 
-    if question in memory_database and not web_search:
-        answer = memory_database[question]
-    else:
-        model = get_model(temperature, top_p, repetition_penalty)
-        embed = get_embeddings()
-
-        if web_search:
-            search_results = google_search(question)
-            context_str = "\n".join([result["text"] for result in search_results if result["text"]])
-
-            # Convert web search results to Document format
-            web_docs = [Document(page_content=result["text"], metadata={"source": result["link"]}) for result in search_results if result["text"]]
+    model = get_model(temperature, top_p, repetition_penalty)
+    embed = get_embeddings()
 
-            # Create a temporary FAISS database for web search results
-            temp_database = FAISS.from_documents(web_docs, embed)
+    # Check if the FAISS database exists, if not create an empty one
+    if os.path.exists("faiss_database"):
+        database = FAISS.load_local("faiss_database", embed, allow_dangerous_deserialization=True)
+    else:
+        database = FAISS.from_documents([], embed)
+        database.save_local("faiss_database")
+
+    if web_search:
+        search_results = google_search(question)
+        web_docs = [Document(page_content=result["text"], metadata={"source": result["link"]}) for result in search_results if result["text"]]
+        
+        # Add web search results to the existing database
+        database.add_documents(web_docs)
+        database.save_local("faiss_database")
+        
+        context_str = "\n".join([doc.page_content for doc in web_docs])
+        
+        prompt_template = """
+        Answer the question based on the following web search results:
+        Web Search Results:
+        {context}
+        Current Question: {question}
+        If the web search results don't contain relevant information, state that the information is not available in the search results.
+        Provide a concise and direct answer to the question without mentioning the web search or these instructions:
+        """
+        prompt_val = ChatPromptTemplate.from_template(prompt_template)
+        formatted_prompt = prompt_val.format(context=context_str, question=question)
+    else:
+        history_str = "\n".join([f"Q: {item['question']}\nA: {item['answer']}" for item in conversation_history])
 
-            retriever = temp_database.as_retriever()
+        if is_related_to_history(question, conversation_history):
+            context_str = "No additional context needed. Please refer to the conversation history."
+        else:
+            retriever = database.as_retriever()
             relevant_docs = retriever.get_relevant_documents(question)
             context_str = "\n".join([doc.page_content for doc in relevant_docs])
 
-            prompt_template = """
-            Answer the question based on the following web search results:
-            Web Search Results:
-            {context}
-            Current Question: {question}
-            If the web search results don't contain relevant information, state that the information is not available in the search results.
-            Provide a concise and direct answer to the question without mentioning the web search or these instructions:
-            """
-            prompt_val = ChatPromptTemplate.from_template(prompt_template)
-            formatted_prompt = prompt_val.format(context=context_str, question=question)
-        else:
-            # Check if the FAISS database exists
-            if os.path.exists("faiss_database"):
-                database = FAISS.load_local("faiss_database", embed, allow_dangerous_deserialization=True)
-            else:
-                return "No FAISS database found. Please upload documents to create the vector store."
-
-            history_str = "\n".join([f"Q: {item['question']}\nA: {item['answer']}" for item in conversation_history])
-
-            if is_related_to_history(question, conversation_history):
-                context_str = "No additional context needed. Please refer to the conversation history."
-            else:
-                retriever = database.as_retriever()
-                relevant_docs = retriever.get_relevant_documents(question)
-                context_str = "\n".join([doc.page_content for doc in relevant_docs])
-
-            prompt_val = ChatPromptTemplate.from_template(prompt)
-            formatted_prompt = prompt_val.format(history=history_str, context=context_str, question=question)
-
-        answer = generate_chunked_response(model, formatted_prompt)
-        answer = re.split(r'Question:|Current Question:', answer)[-1].strip()
+        prompt_val = ChatPromptTemplate.from_template(prompt)
+        formatted_prompt = prompt_val.format(history=history_str, context=context_str, question=question)
 
-        # Remove any remaining prompt instructions from the answer
-        answer_lines = answer.split('\n')
-        answer = '\n'.join(line for line in answer_lines if not line.startswith('If') and not line.startswith('Provide'))
+    answer = generate_chunked_response(model, formatted_prompt)
+    answer = re.split(r'Question:|Current Question:', answer)[-1].strip()
 
-        if not web_search:
-            memory_database[question] = answer
+    # Remove any remaining prompt instructions from the answer
+    answer_lines = answer.split('\n')
+    answer = '\n'.join(line for line in answer_lines if not line.startswith('If') and not line.startswith('Provide'))
 
     if not web_search:
+        memory_database[question] = answer
         conversation_history = manage_conversation_history(question, answer, conversation_history)
 
     return answer