Update app.py

app.py

@@ -1,57 +1,58 @@
+import os
 import streamlit as st
 from langchain_community.document_loaders import PyPDFLoader
+from langchain.text_splitter import CharacterTextSplitter
 from langchain_community.vectorstores import FAISS
-from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.chains import RetrievalQA
-from groq import Groq
-import os
-
-# Set up page
-st.set_page_config(page_title="Chat with PDF")
-
-# Sidebar: enter Groq API key
-st.sidebar.title("Configuration")
-groq_api_key = st.sidebar.text_input("Enter your Groq API Key", type="password")
-
-# Main heading
-st.title("📄 PDF Chatbot using LangChain + FAISS + Groq")
-st.markdown("This app answers your questions based on a predefined PDF.")
-
-# Path to your preloaded PDF
-PDF_PATH = "docs/acca.pdf"
-
-# Process PDF and create retriever (cached)
-@st.cache_resource
-def load_retriever(pdf_path):
-    loader = PyPDFLoader(pdf_path)
-    documents = loader.load_and_split()
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-    db = FAISS.from_documents(documents, embeddings)
-    return db.as_retriever()
-
-# Validate API key
-if not groq_api_key:
-    st.warning("Please enter your Groq API key.")
-else:
-    retriever = load_retriever(PDF_PATH)
-    
-    # Initialize Groq LLM
-    llm = Groq(
-        model="llama3-8b-8192",
-        api_key=groq_api_key,
-        temperature=0.7,
-    )
-
-    # QA chain
-    qa_chain = RetrievalQA.from_chain_type(
-        llm=llm,
-        chain_type="stuff",
-        retriever=retriever
-    )
-
-    # Input field for questions
-    user_input = st.text_input("Ask a question about the PDF:")
-    if user_input:
-        with st.spinner("Generating response..."):
-            answer = qa_chain.run(user_input)
-        st.success(answer)
+from langchain_community.chat_models import ChatGroq
+
+# -------------------------------
+# Sidebar for API key input
+# -------------------------------
+st.set_page_config(page_title="Groq PDF Chatbot")
+st.title("📄 Chat with your PDF using Groq + LLaMA3")
+
+api_key = st.sidebar.text_input("🔑 Enter your Groq API Key", type="password")
+if not api_key:
+    st.warning("Please enter your Groq API key in the sidebar.")
+    st.stop()
+
+os.environ["GROQ_API_KEY"] = api_key
+
+# -------------------------------
+# Load and split the PDF
+# -------------------------------
+pdf_path = "docs/acca.pdf"  # Make sure this file is in your Space
+loader = PyPDFLoader(pdf_path)
+pages = loader.load()
+
+text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+docs = text_splitter.split_documents(pages)
+
+# -------------------------------
+# Vector store using FAISS
+# -------------------------------
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+vectorstore = FAISS.from_documents(docs, embeddings)
+
+# -------------------------------
+# Groq LLM setup
+# -------------------------------
+llm = ChatGroq(temperature=0, model_name="LLaMA3-8b-8192")
+
+qa_chain = RetrievalQA.from_chain_type(
+    llm=llm,
+    retriever=vectorstore.as_retriever(),
+    return_source_documents=True
+)
+
+# -------------------------------
+# User input and response
+# -------------------------------
+query = st.text_input("Ask a question based on the PDF:")
+if query:
+    with st.spinner("Generating answer..."):
+        result = qa_chain.invoke(query)
+        st.subheader("📌 Answer")
+        st.write(result["result"])