Update app.py

app.py

@@ -5,55 +5,60 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.vectorstores import FAISS
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.chains import RetrievalQA
-from langchain_groq import ChatGroq  # ✅ Correct import for Groq API
+from langchain_groq import ChatGroq  # ✅ Correct import
 
-# App config
+# Set up Streamlit UI
 st.set_page_config(page_title="SMEHelpBot 🤖", layout="wide")
 st.title("🤖 SMEHelpBot – Your AI Assistant for Small Businesses")
 
-# API key setup
-GROQ_API_KEY = st.secrets.get("GROQ_API_KEY") or os.getenv("GROQ_API_KEY") or "your_groq_api_key_here"
+# Set Groq API key (use .streamlit/secrets.toml or environment variable)
+GROQ_API_KEY = st.secrets.get("GROQ_API_KEY") or os.getenv("GROQ_API_KEY")
+if not GROQ_API_KEY:
+    st.error("❌ Please set your GROQ_API_KEY in environment or .streamlit/secrets.toml")
+    st.stop()
+
 os.environ["GROQ_API_KEY"] = GROQ_API_KEY
 
 # Upload PDF
 uploaded_file = st.file_uploader("📄 Upload a PDF (e.g., SME policies, documents):", type=["pdf"])
-user_question = st.text_input("💬 Ask a question based on the document:")
+user_question = st.text_input("💬 Ask a question about the uploaded document:")
 
 if uploaded_file:
     with open("temp.pdf", "wb") as f:
         f.write(uploaded_file.read())
 
+    # Load PDF and split into chunks
     loader = PyPDFLoader("temp.pdf")
     documents = loader.load()
 
-    # Split into chunks
     splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
     chunks = splitter.split_documents(documents)
 
-    # Create embeddings
+    # Create vector store
     embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
     vectorstore = FAISS.from_documents(chunks, embeddings)
     retriever = vectorstore.as_retriever()
 
-    # Groq LLaMA3 setup
+    # Load Groq LLaMA3
     llm = ChatGroq(temperature=0.3, model_name="llama3-8b-8192")
 
-    # Retrieval QA
-    qa = RetrievalQA.from_chain_type(
+    # Set up RetrievalQA chain
+    qa_chain = RetrievalQA.from_chain_type(
         llm=llm,
         chain_type="stuff",
         retriever=retriever,
         return_source_documents=True
     )
 
+    # Handle user query
     if user_question:
-        with st.spinner("Generating answer..."):
-            result = qa({"query": user_question})
-            st.success(result["result"])
+        with st.spinner("🤔 Thinking..."):
+            result = qa_chain({"query": user_question})
+            st.success("✅ Answer:")
+            st.write(result["result"])
 
             with st.expander("📄 Source Snippets"):
                 for i, doc in enumerate(result["source_documents"]):
                     st.markdown(f"**Source {i+1}:**\n{doc.page_content[:300]}...")
-
 else:
-    st.info("Upload a PDF and enter a question to get started.")
+    st.info("📂 Upload a PDF and ask a question to get started.")