Update app.py

app.py

@@ -1,9 +1,8 @@
 import streamlit as st
 import os
 
-# YOUR API KEY - DIRECTLY EMBEDDED (Line 5)
+# YOUR API KEY
 API_KEY = "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"
-
 os.environ["OPENAI_API_KEY"] = API_KEY
 
 from langchain_openai import ChatOpenAI, OpenAIEmbeddings
@@ -15,27 +14,25 @@ from langchain_core.output_parsers import StrOutputParser
 
 @st.cache_resource
 def get_chatbot():
-    # Auto-create knowledge.txt if missing
+    # Auto-create knowledge base
     if not os.path.exists("knowledge.txt"):
         with open("knowledge.txt", "w") as f:
             f.write("""
 SR University is located in Warangal, Telangana, India. 
-The Computer Science program focuses on AI/ML, Data Structures & Algorithms, 
-Java/Python programming, Cloud Computing (AWS/Azure), and software engineering.
+Computer Science program focuses on AI/ML, DSA, Java/Python, AWS/Azure, software engineering.
 
-You are a B.Tech Computer Science student preparing for AI/ML internships.
-Key skills: DSA (LeetCode, GFG), AI projects (robotic arms, drones), 
+B.Tech student preparing for AI/ML internships. Skills: LeetCode, AI projects (robotic arms, drones), 
 cloud certifications, competitive programming.
 
-Internship preparation tips:
-1. Solve 300+ LeetCode problems (Easy:100, Medium:150, Hard:50)
-2. Build 3 portfolio projects: RAG chatbot, object detection, RL agent
-3. Apply to startups via AngelList, Y Combinator jobs
-4. Practice system design and behavioral interviews
-5. Target companies: Google, Microsoft, startups in Hyderabad/Bangalore
+Internship tips:
+1. 300+ LeetCode (Easy:100, Medium:150, Hard:50)
+2. 3 portfolio projects: RAG chatbot, object detection, RL agent
+3. Apply startups: AngelList, Y Combinator
+4. Practice system design, behavioral interviews
+5. Target: Google, Microsoft, Hyderabad/Bangalore startups
             """)
 
-    # Create vector store if missing
+    # Create FAISS index if missing
     if not os.path.exists("faiss_index"):
         loader = TextLoader("knowledge.txt")
         docs = loader.load()
@@ -51,11 +48,10 @@ Internship preparation tips:
     vectorstore = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
     retriever = vectorstore.as_retriever()
 
-    # LLM setup
+    # LLM
     llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
-    
     prompt = ChatPromptTemplate.from_template(
-        "Answer using ONLY this context:\n{context}\n\nQuestion: {question}\n\nAnswer:"
+        "Answer using ONLY this context:\n{context}\n\nQuestion: {question}\nAnswer:"
     )
     
     def rag_chain(query):
@@ -63,45 +59,31 @@ Internship preparation tips:
         context = "\n".join([doc.page_content for doc in context_docs])
         chain = (
             {"context": lambda x: context, "question": lambda x: query} 
-            | prompt 
-            | llm 
-            | StrOutputParser()
+            | prompt | llm | StrOutputParser()
         )
         return chain.invoke(query)
     
     return rag_chain
 
-# Main UI
 st.title("🧠 RAG Chatbot")
-st.info("💡 Answers questions about SR University, AI internships, your projects")
+st.info("💡 Ask about SR University, AI internships, projects...")
 
 chatbot = get_chatbot()
-
 if "messages" not in st.session_state:
     st.session_state.messages = []
 
-# Display chat history
 for message in st.session_state.messages:
     with st.chat_message(message["role"]):
         st.markdown(message["content"])
 
-# New message input
-if prompt := st.chat_input("Ask about university, internships, projects..."):
-    # Add user message
+if prompt := st.chat_input("Ask a question..."):
     st.session_state.messages.append({"role": "user", "content": prompt})
     with st.chat_message("user"):
         st.markdown(prompt)
     
-    # Generate and display response
     with st.chat_message("assistant"):
-        with st.spinner("Searching your knowledge base..."):
+        with st.spinner("Thinking..."):
             response = chatbot(prompt)
             st.markdown(response)
     
-    # Store assistant response
     st.session_state.messages.append({"role": "assistant", "content": response})
-
-# Sidebar info
-with st.sidebar:
-    st.success("✅ RAG Chatbot Live!")
-    st.balloons()