Update app.py

app.py

@@ -1,97 +1,253 @@
 import streamlit as st
+import os
+import tempfile
 from langchain_community.document_loaders import PyPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.vectorstores import FAISS
-from langchain.chains import ConversationalRetrievalChain
-from langchain.llms import HuggingFaceHub
-from langchain.memory import ConversationBufferMemory
-import os
-
-# App title and color theme
-st.set_page_config(page_title="📘 PDF Q&A Agent", layout="centered", page_icon="📘")
-
-st.markdown(
-    \"\"\"
-    <div style="background-color:#E3E8FF;padding:10px;border-radius:10px">
-    <h2 style="color:#3C3C88;text-align:center">📘 Student PDF Assistant</h2>
-    <p style="color:#444;text-align:center">Ask questions from your uploaded PDF and generate Q&A for chapters!</p>
-    </div>
-    \"\"\", unsafe_allow_html=True
+from langchain_community.vectorstores import FAISS
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.chat_models import ChatOllama
+from langchain.chains import RetrievalQA
+from langchain.prompts import PromptTemplate
+from langchain_core.runnables import RunnablePassthrough
+from langchain_core.output_parsers import StrOutputParser
+import base64
+
+# Set page config
+st.set_page_config(
+    page_title="EduQuery - Smart PDF Assistant",
+    page_icon="📚",
+    layout="wide",
+    initial_sidebar_state="collapsed"
 )
 
-# Upload PDF
-uploaded_file = st.file_uploader("📎 Upload your PDF file", type=["pdf"])
-
-if uploaded_file:
-    # Save PDF temporarily
-    with open("uploaded.pdf", "wb") as f:
-        f.write(uploaded_file.read())
-
-    st.success("✅ PDF uploaded successfully!")
-
-    # Load and split PDF
-    loader = PyPDFLoader("uploaded.pdf")
-    pages = loader.load_and_split()
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=800, chunk_overlap=150)
-    chunks = text_splitter.split_documents(pages)
-
-    # Embedding
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-    vectordb = FAISS.from_documents(chunks, embeddings)
-
-    # Load Open Source LLM from Hugging Face (Mistral or any lightweight LLM)
-    repo_id = "mistralai/Mistral-7B-Instruct-v0.1"
-    llm = HuggingFaceHub(repo_id=repo_id, model_kwargs={"temperature":0.5, "max_new_tokens":500})
-
-    # Memory and Chain
-    memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
-    qa_chain = ConversationalRetrievalChain.from_llm(
-        llm, retriever=vectordb.as_retriever(), memory=memory
+# Embedded CSS for colorful UI
+st.markdown("""
+<style>
+body {
+    background-color: #f0f2f6;
+}
+
+.stApp {
+    max-width: 1200px;
+    margin: 0 auto;
+    padding: 2rem;
+}
+
+.header {
+    background: linear-gradient(135deg, #6a11cb 0%, #2575fc 100%);
+    color: white;
+    padding: 2rem;
+    border-radius: 15px;
+    margin-bottom: 2rem;
+    text-align: center;
+}
+
+.header h1 {
+    font-size: 2.5rem;
+    margin-bottom: 0.5rem;
+}
+
+.stButton>button {
+    background: linear-gradient(135deg, #6a11cb 0%, #2575fc 100%);
+    color: white;
+    border: none;
+    border-radius: 25px;
+    padding: 0.5rem 1.5rem;
+    font-weight: bold;
+    transition: all 0.3s ease;
+}
+
+.stButton>button:hover {
+    transform: scale(1.05);
+    box-shadow: 0 5px 15px rgba(0,0,0,0.1);
+}
+
+.stTextInput>div>div>input {
+    border-radius: 25px;
+    padding: 0.75rem 1.5rem;
+}
+
+.stChatMessage {
+    padding: 1.5rem;
+    border-radius: 20px;
+    margin-bottom: 1rem;
+    max-width: 80%;
+}
+
+.stChatMessage[data-testid="user"] {
+    background: linear-gradient(135deg, #43e97b 0%, #38f9d7 100%);
+    margin-left: auto;
+}
+
+.stChatMessage[data-testid="assistant"] {
+    background: linear-gradient(135deg, #4facfe 0%, #00f2fe 100%);
+    margin-right: auto;
+}
+
+.qa-box {
+    background: linear-gradient(135deg, #fff1eb 0%, #ace0f9 100%);
+    padding: 1.5rem;
+    border-radius: 15px;
+    margin-top: 1rem;
+    box-shadow: 0 5px 15px rgba(0,0,0,0.05);
+}
+
+.footer {
+    text-align: center;
+    color: #6c757d;
+    padding-top: 1.5rem;
+    font-size: 0.9rem;
+}
+</style>
+""", unsafe_allow_html=True)
+
+# Header with gradient
+st.markdown("""
+<div class="header">
+    <h1>📚 EduQuery</h1>
+    <p>Smart PDF Assistant for Students</p>
+</div>
+""", unsafe_allow_html=True)
+
+# Initialize session state
+if "vector_store" not in st.session_state:
+    st.session_state.vector_store = None
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# Model selection
+MODEL_NAME = "nous-hermes2"  # Best open-source model for instruction following
+
+# PDF Processing
+def process_pdf(pdf_file):
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
+        tmp_file.write(pdf_file.getvalue())
+        tmp_path = tmp_file.name
+    
+    loader = PyPDFLoader(tmp_path)
+    docs = loader.load()
+    
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=1000,
+        chunk_overlap=200,
+        length_function=len
+    )
+    chunks = text_splitter.split_documents(docs)
+    
+    embeddings = HuggingFaceEmbeddings(model_name="BAAI/bge-base-en-v1.5")
+    vector_store = FAISS.from_documents(chunks, embeddings)
+    
+    os.unlink(tmp_path)
+    return vector_store
+
+# RAG Setup
+def setup_qa_chain(vector_store):
+    llm = ChatOllama(model=MODEL_NAME, temperature=0.3)
+    
+    custom_prompt = """
+    You are an expert academic assistant. Answer the question based only on the following context:
+    {context}
+    
+    Question: {question}
+    
+    Provide a clear, concise answer with page number references. If unsure, say "I couldn't find this information in the document".
+    """
+    
+    prompt = PromptTemplate(
+        template=custom_prompt,
+        input_variables=["context", "question"]
+    )
+    
+    retriever = vector_store.as_retriever(search_kwargs={"k": 3})
+    
+    qa_chain = (
+        {"context": retriever, "question": RunnablePassthrough()}
+        | prompt
+        | llm
+        | StrOutputParser()
+    )
+    
+    return qa_chain
+
+# Generate questions from chapter
+def generate_chapter_questions(vector_store, chapter_title):
+    llm = ChatOllama(model=MODEL_NAME, temperature=0.7)
+    
+    prompt = PromptTemplate(
+        input_variables=["chapter_title"],
+        template="""
+        You are an expert educator. Generate 5 important questions and answers about '{chapter_title}' 
+        that would help students understand key concepts. Format as:
+        
+        Q1: [Question]
+        A1: [Answer with page reference]
+        
+        Q2: [Question]
+        A2: [Answer with page reference]
+        ..."""
     )
+    
+    chain = prompt | llm | StrOutputParser()
+    return chain.invoke({"chapter_title": chapter_title})
 
-    # Chat Interface
-    st.markdown("---")
-    st.markdown("💬 **Ask a question from the PDF:**")
-
-    if "chat_history" not in st.session_state:
-        st.session_state.chat_history = []
-
-    question = st.text_input("Type your question here...", key="user_input")
-
-    if question:
-        result = qa_chain.run(question)
-        st.session_state.chat_history.append(("You", question))
-        st.session_state.chat_history.append(("Bot", result))
-
-    # Show chat history
-    for sender, msg in st.session_state.chat_history[::-1]:
-        st.markdown(f"**{sender}:** {msg}")
-
-    # Question Generation Button
-    st.markdown("---")
-    if st.button("📚 Generate Q&A from all chapters"):
-        st.info("Generating questions and answers from the content...")
-        questions = [
-            "What is the main idea of this chapter?",
-            "What are the key points discussed?",
-            "Can you summarize this section?",
-            "Are there any definitions or terms introduced?"
-        ]
-        for i, chunk in enumerate(chunks[:3]):  # Limit to first 3 chunks for demo
-            st.markdown(f"**Chapter Section {i+1}:**")
-            for q in questions:
-                answer = llm.invoke(q + "\\n" + chunk.page_content[:1000])
-                st.markdown(f"**Q:** {q}")
-                st.markdown(f"**A:** {answer}")
-                st.markdown("---")
-
-"""
-
-# Save both files to /mnt/data for user download or deployment
-with open("/mnt/data/requirements.txt", "w") as f:
-    f.write(requirements_txt.strip())
-
-with open("/mnt/data/app.py", "w") as f:
-    f.write(app_py.strip())
+# File upload section
+st.subheader("📤 Upload Your Textbook/Notes")
+uploaded_file = st.file_uploader("", type="pdf", accept_multiple_files=False, label_visibility="collapsed")
 
+if uploaded_file:
+    with st.spinner("Processing PDF..."):
+        st.session_state.vector_store = process_pdf(uploaded_file)
+    st.success("PDF processed successfully! You can now ask questions.")
+
+# Main content columns
+col1, col2 = st.columns([1, 2])
+
+# Chapter-based Q&A Generator
+with col1:
+    st.subheader("🔍 Generate Chapter Questions")
+    chapter_title = st.text_input("Enter chapter title/section name:", key="chapter_input")
+    
+    if st.button("Generate Q&A", key="generate_btn") and chapter_title and st.session_state.vector_store:
+        with st.spinner(f"Generating questions about {chapter_title}..."):
+            questions = generate_chapter_questions(
+                st.session_state.vector_store, 
+                chapter_title
+            )
+            st.markdown(f"<div class='qa-box'>{questions}</div>", unsafe_allow_html=True)
+    elif chapter_title and not st.session_state.vector_store:
+        st.warning("Please upload a PDF first")
+
+# Chat interface
+with col2:
+    st.subheader("💬 Ask Anything About the Document")
+    
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+    
+    if prompt := st.chat_input("Your question..."):
+        if not st.session_state.vector_store:
+            st.warning("Please upload a PDF first")
+            st.stop()
+            
+        st.session_state.messages.append({"role": "user", "content": prompt})
+        with st.chat_message("user"):
+            st.markdown(prompt)
+            
+        with st.chat_message("assistant"):
+            with st.spinner("Thinking..."):
+                qa_chain = setup_qa_chain(st.session_state.vector_store)
+                response = qa_chain.invoke(prompt)
+            st.markdown(response)
+            st.session_state.messages.append({"role": "assistant", "content": response})
+
+# Footer
+st.markdown("---")
+st.markdown(
+    """
+    <div class="footer">
+        <p>EduQuery - Helping students learn smarter • Powered by Nous-Hermes2 and LangChain</p>
+    </div>
+    """,
+    unsafe_allow_html=True
+)