Update app.py

app.py

@@ -5,19 +5,13 @@ import os
 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
-from langchain.text_splitter import CharacterTextSplitter
-from langchain.vectorstores import FAISS
-from langchain.prompts import ChatPromptTemplate
-from langchain_core.output_parsers import StrOutputParser
+from langchain_openai import ChatOpenAI
+import tiktoken
 
 @st.cache_resource
 def get_chatbot():
-    # Auto-create knowledge base
-    if not os.path.exists("knowledge.txt"):
-        with open("knowledge.txt", "w") as f:
-            f.write("""
+    # Simple knowledge base - no complex splitting
+    knowledge = """
 SR University is located in Warangal, Telangana, India. 
 Computer Science program focuses on AI/ML, DSA, Java/Python, AWS/Azure, software engineering.
 
@@ -30,59 +24,45 @@ Internship tips:
 3. Apply startups: AngelList, Y Combinator
 4. Practice system design, behavioral interviews
 5. Target: Google, Microsoft, Hyderabad/Bangalore startups
-            """)
-
-    # Create FAISS index if missing
-    if not os.path.exists("faiss_index"):
-        loader = TextLoader("knowledge.txt")
-        docs = loader.load()
-        text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-        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 = ChatOpenAI(model="gpt-4o-mini", temperature=0)
-    prompt = ChatPromptTemplate.from_template(
-        "Answer using ONLY this context:\n{context}\n\nQuestion: {question}\nAnswer:"
-    )
     
-    def rag_chain(query):
-        context_docs = retriever.invoke(query)
-        context = "\n".join([doc.page_content for doc in context_docs])
-        chain = (
-            {"context": lambda x: context, "question": lambda x: query} 
-            | prompt | llm | StrOutputParser()
-        )
-        return chain.invoke(query)
+    def rag_chat(query):
+        prompt = f"""
+        Use ONLY this context to answer: 
+        {knowledge}
+        
+        Question: {query}
+        
+        Answer concisely and accurately:
+        """
+        return llm.invoke(prompt).content
     
-    return rag_chain
+    return rag_chat
 
+# UI
 st.title("🧠 RAG Chatbot")
-st.info("💡 Ask about SR University, AI internships, projects...")
+st.info("💡 Answers about SR University, AI internships, projects")
 
 chatbot = get_chatbot()
+
 if "messages" not in st.session_state:
     st.session_state.messages = []
 
+# Chat history
 for message in st.session_state.messages:
     with st.chat_message(message["role"]):
         st.markdown(message["content"])
 
-if prompt := st.chat_input("Ask a question..."):
+# New message
+if prompt := st.chat_input("Ask about university, internships..."):
     st.session_state.messages.append({"role": "user", "content": prompt})
     with st.chat_message("user"):
         st.markdown(prompt)
     
     with st.chat_message("assistant"):
-        with st.spinner("Thinking..."):
+        with st.spinner("Answering..."):
             response = chatbot(prompt)
             st.markdown(response)