Update app.py

app.py

@@ -5,42 +5,40 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.vectorstores import FAISS
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.chains import RetrievalQA
-from langchain_community.chat_models import ChatGroq
+from langchain_groq import ChatGroq  # ✅ Correct import for Groq API
 
-# Set Streamlit page config
+# App config
 st.set_page_config(page_title="SMEHelpBot 🤖", layout="wide")
 st.title("🤖 SMEHelpBot – Your AI Assistant for Small Businesses")
 
-# File uploader
-uploaded_file = st.file_uploader("📄 Upload a PDF (e.g., SME policy, business doc, etc.):", type=["pdf"])
-user_question = st.text_input("💬 Ask a question related to your document or SME operations:")
+# API key setup
+GROQ_API_KEY = st.secrets.get("GROQ_API_KEY") or os.getenv("GROQ_API_KEY") or "your_groq_api_key_here"
+os.environ["GROQ_API_KEY"] = GROQ_API_KEY
 
-# Set Groq API key securely (use Streamlit secrets or env var)
-#GROQ_API_KEY = st.secrets.get("GROQ_API_KEY") or os.getenv("GROQ_API_KEY") or "your_groq_api_key_here"
-GROQ_API_KEY = Groq(api_key=os.environ.get("GROQ_API_KEY")) # Initialize client here with 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:")
 
 if uploaded_file:
-    # Save uploaded file temporarily
     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 vector store using MiniLM embeddings
+    # Create embeddings
     embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
     vectorstore = FAISS.from_documents(chunks, embeddings)
     retriever = vectorstore.as_retriever()
 
-    # Set up LLM using Groq + LLaMA3
-    os.environ["GROQ_API_KEY"] = GROQ_API_KEY
+    # Groq LLaMA3 setup
     llm = ChatGroq(temperature=0.3, model_name="llama3-8b-8192")
 
-    # QA chain with retrieval
+    # Retrieval QA
     qa = RetrievalQA.from_chain_type(
         llm=llm,
         chain_type="stuff",
@@ -53,9 +51,9 @@ if uploaded_file:
             result = qa({"query": user_question})
             st.success(result["result"])
 
-            with st.expander("📄 Sources"):
-                for doc in result["source_documents"]:
-                    st.markdown(f"• {doc.page_content[:300]}...")
+            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 begin.")
+    st.info("Upload a PDF and enter a question to get started.")