Update app.py

app.py

@@ -131,21 +131,26 @@ chain = ConversationalRetrievalChain.from_llm(llm, vectorstore.as_retriever(), r
 chat_history = []
 
 def format_prompt(query):
-    # This prompt is designed to guide the LLM to respond in a specified format
+    # Construct a clear and structured prompt to guide the LLM's response
     prompt = f"""
-    You are a helpful assistant with access to a specialized knowledge base. I have a question that I need answered. After providing a brief general response to the question, please return a JSON-formatted output with the following keys:
-    - "question": The original question.
-    - "answer": The detailed answer.
-
-    related questions from database
-    - "question " : related question
-    - "answer" : its answer
-
-    Please answer the following question:
+    You are a knowledgeable assistant with access to a comprehensive database. 
+    I need you to answer my question and provide related information in a specific format.
+
+    Here's what I need:
+    1. A brief, general response to my question.
+    2. A JSON-formatted output containing:
+       - "question": The original question.
+       - "answer": The detailed answer.
+       - "related_questions": A list of related questions and their answers, each as a dictionary with the keys:
+         - "question": The related question.
+         - "answer": The related answer.
+
+    Here's my question:
     {query}
     """
     return prompt
 
+
 def qa_infer(query):
     formatted_prompt = format_prompt(query)
     result = chain({"question": formatted_prompt, "chat_history": chat_history})