Made edits on chainlit.md and added answers to app.py

app.py

@@ -13,8 +13,36 @@ from aimakerspace.openai_utils.chatmodel import ChatOpenAI
 import chainlit as cl
 import pymupdf  
 
+# QUESTION #1:
+# Why do we want to support streaming? What about streaming is important, or useful?
+
+# ANSWER #1:
+# From a UX perspective, streaming allows LLMs to feel responsive to
+# end users especially when a response is taking several seconds. 
+# especially when the response threshold is about 200-300ms
+
+
+# QUESTION #2:
+# Why are we using User Session here? What about Python makes us need to use this? Why not just store everything in a global variable?
+
+# ANSWER #2: 
+# Using User Sessions allows us to avoid conflicts, e.g. 3 concurrent users updating a single global variable. 
+# This keeps the code functioning and scalable
+# From a UX perspective, User Sessions allows for data separation which leads to personalization which 
+# Improves the overall user experience and response quality with LLMs
+
 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 kind, helpful and polite AI. 
+You speak the same way as how kind doctors are portrayed on TV and movies.
+
+Use the following context to extract and synthesize information to answer the user's question as accurately as possible. 
+Make sure that you think through each step. 
+
+If the answer is not found in the context:
+1. Politely inform the user that the information is not available.
+2. If possible, suggest where they might find more information or how they could rephrase their question for better clarity.
+
+Always aim to provide clear, concise, and helpful responses."""
 system_role_prompt = SystemRolePrompt(system_template)
 
 user_prompt_template = """\
@@ -23,9 +51,12 @@ Context:
 
 Question:
 {question}
+
+Please provide a clear and concise answer that you have thought through based on the above context.
 """
 user_role_prompt = UserRolePrompt(user_prompt_template)
 
+
 class RetrievalAugmentedQAPipeline:
     def __init__(self, llm: ChatOpenAI(), vector_db_retriever: VectorDatabase) -> None:
         self.llm = llm

chainlit.md

@@ -1,3 +1,3 @@
-# Welcome to Chat with Your Text File
+# Welcome to Doc Doc: Talk to Your Documents
 
-With this application, you can chat with an uploaded text file that is smaller than 2MB!
+Upload any .txt or PDF file that's less than 2MB and start chatting with your documents in a few seconds!