Update app.py

app.py

@@ -1,179 +1,97 @@
 import streamlit as st
-import os
-import tempfile
 from langchain_community.document_loaders import PyPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-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"
+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
 )
 
-# Custom CSS for colorful UI
-def local_css(file_name):
-    with open(file_name) as f:
-        st.markdown(f'<style>{f.read()}</style>', unsafe_allow_html=True)
-
-local_css("style.css")
-
-# 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]
-        ..."""
+# 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
     )
-    
-    chain = prompt | llm | StrOutputParser()
-    return chain.invoke({"chapter_title": chapter_title})
 
-# File upload section
-st.subheader("📤 Upload Your Textbook/Notes")
-uploaded_file = st.file_uploader("", type="pdf", accept_multiple_files=False)
+    # 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())
 
-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:")
-    
-    if st.button("Generate Q&A") 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
-)