Add detailed logging and improve system prompt

app.py

@@ -13,7 +13,14 @@ from aimakerspace.openai_utils.chatmodel import ChatOpenAI
 import chainlit as cl
 
 system_template = """\
-Use the following context to answer a users question. If you cannot find the answer in the context, say you don't know the answer."""
+You are a helpful AI assistant that answers questions based on the provided context. 
+Your task is to:
+1. Carefully read and understand the context
+2. Answer the user's question using ONLY the information from the context
+3. If the answer cannot be found in the context, say "I cannot find the answer in the provided context"
+4. If you find partial information, share what you found and indicate if more information might be needed
+
+Remember: Only use information from the provided context to answer questions."""
 system_role_prompt = SystemRolePrompt(system_template)
 
 user_prompt_template = """\
@@ -33,6 +40,10 @@ class RetrievalAugmentedQAPipeline:
     async def arun_pipeline(self, user_query: str):
         # Get more contexts but limit the total length
         context_list = self.vector_db_retriever.search_by_text(user_query, k=3)  # Reduced from 6 to 3
+        print("\nRetrieved contexts:")
+        for i, (context, score) in enumerate(context_list):
+            print(f"\nContext {i+1} (score: {score:.3f}):")
+            print(context[:200] + "..." if len(context) > 200 else context)
         
         # Limit total context length to approximately 3000 tokens (12000 characters)
         context_prompt = ""
@@ -45,11 +56,17 @@ class RetrievalAugmentedQAPipeline:
             context_prompt += context[0] + "\n"
             total_length += len(context[0])
             
-        print(f"Using {len(context_prompt.split())} words of context")
+        print(f"\nUsing {len(context_prompt.split())} words of context")
 
         formatted_system_prompt = system_role_prompt.create_message()
         formatted_user_prompt = user_role_prompt.create_message(question=user_query, context=context_prompt)
 
+        print("\nFinal messages being sent to the model:")
+        print("\nSystem prompt:")
+        print(formatted_system_prompt)
+        print("\nUser prompt:")
+        print(formatted_user_prompt)
+
         async def generate_response():
             async for chunk in self.llm.astream([formatted_system_prompt, formatted_user_prompt]):
                 yield chunk