Update app.py

app.py

@@ -1,16 +1,19 @@
 import os
 import streamlit as st
 from groq import Groq
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.vectorstores import FAISS
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
 from langchain.text_splitter import CharacterTextSplitter
-from langchain.document_loaders import TextLoader, PyPDFLoader
+from langchain_community.document_loaders import TextLoader, PyPDFLoader
 from langchain.chains import RetrievalQA
 from langchain.llms.base import LLM
 from tempfile import NamedTemporaryFile
 
 # Load Groq API key from environment variable
 GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+if not GROQ_API_KEY:
+    st.error("❌ GROQ_API_KEY is not set in environment variables.")
+    st.stop()
 
 # Initialize Groq client
 groq_client = Groq(api_key=GROQ_API_KEY)
@@ -32,8 +35,9 @@ class GroqLLM(LLM):
         return "groq_llm"
 
 # Streamlit UI
-st.title("📚 RAG App with Groq + HuggingFace + Streamlit")
-st.write("Upload a PDF or TXT file, ask a question, and get answers powered by RAG.")
+st.set_page_config(page_title="Groq RAG App", layout="centered")
+st.title("📚 RAG App with Groq + LangChain + FAISS")
+st.write("Upload a PDF or TXT file, ask a question, and get smart answers.")
 
 uploaded_file = st.file_uploader("Upload your document", type=["pdf", "txt"])
 
@@ -42,7 +46,7 @@ if uploaded_file:
         tmp_file.write(uploaded_file.read())
         tmp_path = tmp_file.name
 
-    # Load document
+    # Load document based on file type
     if uploaded_file.type == "application/pdf":
         loader = PyPDFLoader(tmp_path)
     else:
@@ -58,14 +62,15 @@ if uploaded_file:
     embeddings = HuggingFaceEmbeddings()
     db = FAISS.from_documents(texts, embeddings)
 
-    # RAG chain
+    # Set up RAG chain
     retriever = db.as_retriever()
     qa_chain = RetrievalQA.from_chain_type(llm=GroqLLM(), retriever=retriever)
 
-    # Input box
-    query = st.text_input("Ask something about the document:")
+    # Input box for user question
+    query = st.text_input("🔍 Ask a question about the document:")
 
     if query:
-        result = qa_chain.run(query)
+        with st.spinner("Thinking..."):
+            result = qa_chain.run(query)
         st.markdown("### 🧠 Answer:")
         st.success(result)