Update app.py

app.py

@@ -1,5 +1,6 @@
 import os
 import streamlit as st
+from glob import glob
 from langchain_community.document_loaders import PyPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.vectorstores import FAISS
@@ -7,11 +8,11 @@ from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.chains import RetrievalQA
 from langchain_groq import ChatGroq  # ✅ Correct import
 
-# Set up Streamlit UI
+# Set page config
 st.set_page_config(page_title="SMEHelpBot 🤖", layout="wide")
 st.title("🤖 SMEHelpBot – Your AI Assistant for Small Businesses")
 
-# Set Groq API key (use .streamlit/secrets.toml or environment variable)
+# Load API key
 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")
@@ -19,46 +20,49 @@ if not GROQ_API_KEY:
 
 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 about the uploaded document:")
+# Load all PDFs from the 'docs' folder
+pdf_paths = glob("docs/*.pdf")
 
-if uploaded_file:
-    with open("temp.pdf", "wb") as f:
-        f.write(uploaded_file.read())
+if not pdf_paths:
+    st.warning("📁 Please place some PDF files in the `docs/` folder.")
+    st.stop()
+
+st.info(f"📄 Loaded {len(pdf_paths)} document(s) from `docs/`")
+
+# Load and split all PDFs
+documents = []
+for path in pdf_paths:
+    loader = PyPDFLoader(path)
+    documents.extend(loader.load())
 
-    # 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)
 
-    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-    chunks = splitter.split_documents(documents)
+# Create vector store from chunks
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+vectorstore = FAISS.from_documents(chunks, embeddings)
+retriever = vectorstore.as_retriever()
 
-    # Create vector store
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-    vectorstore = FAISS.from_documents(chunks, embeddings)
-    retriever = vectorstore.as_retriever()
+# Set up LLM with Groq
+llm = ChatGroq(temperature=0.3, model_name="llama3-8b-8192")
 
-    # Load Groq LLaMA3
-    llm = ChatGroq(temperature=0.3, model_name="llama3-8b-8192")
+# Build QA chain
+qa_chain = RetrievalQA.from_chain_type(
+    llm=llm,
+    chain_type="stuff",
+    retriever=retriever,
+    return_source_documents=True
+)
 
-    # Set up RetrievalQA chain
-    qa_chain = RetrievalQA.from_chain_type(
-        llm=llm,
-        chain_type="stuff",
-        retriever=retriever,
-        return_source_documents=True
-    )
+# Ask question
+user_question = st.text_input("💬 Ask your question about SME documents:")
 
-    # Handle user query
-    if user_question:
-        with st.spinner("🤔 Thinking..."):
-            result = qa_chain({"query": user_question})
-            st.success("✅ Answer:")
-            st.write(result["result"])
+if user_question:
+    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 ask a question to get started.")
+        with st.expander("📄 Source Snippets"):
+            for i, doc in enumerate(result["source_documents"]):
+                st.markdown(f"**Source {i+1}:**\n{doc.page_content[:300]}...")