Create app.py

app.py

@@ -0,0 +1,60 @@
+import os
+import streamlit as st
+from langchain_community.document_loaders import PyPDFLoader
+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
+
+# Set Streamlit page 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:")
+
+# 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"
+
+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()
+
+    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    chunks = splitter.split_documents(documents)
+
+    # Create vector store using MiniLM 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
+    llm = ChatGroq(temperature=0.3, model_name="llama3-8b-8192")
+
+    # QA chain with retrieval
+    qa = RetrievalQA.from_chain_type(
+        llm=llm,
+        chain_type="stuff",
+        retriever=retriever,
+        return_source_documents=True
+    )
+
+    if user_question:
+        with st.spinner("Generating answer..."):
+            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]}...")
+
+else:
+    st.info("Upload a PDF and enter a question to begin.")