Update app.py

app.py

@@ -1,8 +1,10 @@
 import streamlit as st
 import os
 
-# HF Spaces secret
-os.environ["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"] = st.secrets["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"]
+# YOUR API KEY - DIRECTLY EMBEDDED (Line 5)
+API_KEY = "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"
+
+os.environ["OPENAI_API_KEY"] = API_KEY
 
 from langchain_openai import ChatOpenAI, OpenAIEmbeddings
 from langchain_community.document_loaders import TextLoader
@@ -13,25 +15,43 @@ from langchain_core.output_parsers import StrOutputParser
 
 @st.cache_resource
 def get_chatbot():
-    # Load or create vector store
+    # Auto-create knowledge.txt if missing
+    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.
+
+You are a B.Tech Computer Science student preparing for AI/ML internships.
+Key skills: DSA (LeetCode, GFG), 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
+            """)
+
+    # Create vector store if missing
     if not os.path.exists("faiss_index"):
-        with open("knowledge.txt", "r") as f:
-            content = f.read()
-        docs = [content]  # Simple doc
-        
+        loader = TextLoader("knowledge.txt")
+        docs = loader.load()
         text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-        splits = text_splitter.create_documents([content])
+        splits = text_splitter.split_documents(docs)
         
         embeddings = OpenAIEmbeddings()
         vectorstore = FAISS.from_documents(splits, embeddings)
         vectorstore.save_local("faiss_index")
-    
+
     # Load retriever
     embeddings = OpenAIEmbeddings()
     vectorstore = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
     retriever = vectorstore.as_retriever()
-    
-    # LLM
+
+    # LLM setup
     llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
     
     prompt = ChatPromptTemplate.from_template(
@@ -51,29 +71,37 @@ def get_chatbot():
     
     return rag_chain
 
-# UI
+# Main UI
 st.title("🧠 RAG Chatbot")
+st.info("💡 Answers questions about SR University, AI internships, your projects")
+
 chatbot = get_chatbot()
 
 if "messages" not in st.session_state:
     st.session_state.messages = []
 
-# Show chat history
+# Display chat history
 for message in st.session_state.messages:
     with st.chat_message(message["role"]):
         st.markdown(message["content"])
 
-# Chat input
-if prompt := st.chat_input("Ask about your knowledge base..."):
+# New message input
+if prompt := st.chat_input("Ask about university, internships, projects..."):
     # Add user message
     st.session_state.messages.append({"role": "user", "content": prompt})
     with st.chat_message("user"):
         st.markdown(prompt)
     
-    # Generate response
+    # Generate and display response
     with st.chat_message("assistant"):
-        with st.spinner("Searching knowledge base..."):
+        with st.spinner("Searching your knowledge base..."):
             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()