Update app.py

app.py

@@ -1,91 +1,148 @@
+# app.py
 import streamlit as st
-import os
 from PyPDF2 import PdfReader
-import docx
-from pptx import Presentation
-import openpyxl
-from sentence_transformers import SentenceTransformer
-import faiss
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.chains.question_answering import load_qa_chain
+from langchain.llms import HuggingFacePipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+import tempfile
 
-# -----------------------------
-# Streamlit UI
-# -----------------------------
-st.title("📘 Free Document QA App (Hugging Face)")
+# --- Streamlit page config ---
+st.set_page_config(page_title="📚 Multi PDF Chatbot", layout="wide", page_icon="🤖")
 
-uploaded_file = st.file_uploader("Upload a document (PDF, DOCX, PPTX, XLSX)")
+# --- Header ---
+st.markdown(
+    "<h1 style='text-align: center; color: #2F4F4F;'>📚 Multi-PDF Chat Agent 🤖</h1>",
+    unsafe_allow_html=True
+)
 
-if uploaded_file:
-    st.write(f"Uploaded: {uploaded_file.name}")
+# --- Sidebar Styling ---
+st.markdown(
+    """
+    <style>
+    section[data-testid="stSidebar"] {
+        background-color: #111827;
+        padding: 30px 20px;
+    }
+    .profile-img-container {
+        display: flex;
+        justify-content: center;
+        margin-bottom: 15px;
+    }
+    .profile-img-container img {
+        border-radius: 12px;
+        height: 100px;
+        width: 100px;
+        object-fit: cover;
+        border: 2px solid #4ade80;
+        box-shadow: 0 0 10px rgba(0,0,0,0.5);
+    }
+    .upload-section {
+        background-color: #1f2937;
+        padding: 20px;
+        border-radius: 12px;
+        margin-top: 20px;
+        margin-bottom: 30px;
+    }
+    .upload-section h4 {
+        color: #facc15;
+        margin-bottom: 15px;
+    }
+    .footer {
+        text-align: center;
+        font-size: 13px;
+        color: #9ca3af;
+    }
+    .footer a {
+        color: #facc15;
+        text-decoration: none;
+    }
+    .footer a:hover {
+        color: #ffffff;
+    }
+    </style>
+    """,
+    unsafe_allow_html=True
+)
 
-    # -----------------------------
-    # Extract text
-    # -----------------------------
-    context = ""
-    if uploaded_file.type == "application/pdf":
-        reader = PdfReader(uploaded_file)
-        for page in reader.pages:
-            context += page.extract_text() + "\n"
-    elif uploaded_file.type in ["application/vnd.openxmlformats-officedocument.wordprocessingml.document"]:
-        doc = docx.Document(uploaded_file)
-        for para in doc.paragraphs:
-            context += para.text + "\n"
-    elif uploaded_file.type in ["application/vnd.openxmlformats-officedocument.presentationml.presentation"]:
-        prs = Presentation(uploaded_file)
-        for slide in prs.slides:
-            for shape in slide.shapes:
-                if hasattr(shape, "text"):
-                    context += shape.text + "\n"
-    elif uploaded_file.type in ["application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"]:
-        wb = openpyxl.load_workbook(uploaded_file)
-        for sheet in wb.worksheets:
-            for row in sheet.iter_rows(values_only=True):
-                context += " ".join([str(cell) for cell in row if cell]) + "\n"
-    else:
-        st.warning("Unsupported file type.")
-        context = ""
+# --- Sidebar Layout ---
+with st.sidebar:
+    # Profile image
+    col1, col2, col3 = st.columns([1, 2, 1])
+    with col2:
+        st.image("assets/img/main.png", width=100)
+
+    # Upload PDFs
+    st.markdown('<div class="upload-section">', unsafe_allow_html=True)
+    st.markdown("#### 📁 Upload PDF Files")
+    pdf_docs = st.file_uploader("Drag and drop your PDFs here", accept_multiple_files=True, label_visibility="collapsed")
+    st.markdown('</div>', unsafe_allow_html=True)
+
+    # Footer
+    st.markdown(
+        """
+        <div class="footer">
+            Built with ❤️ by <a href="https://github.com/Danish7861" target="_blank">Danish Shahzad</a>
+        </div>
+        """,
+        unsafe_allow_html=True
+    )
 
-    # -----------------------------
-    # Split into chunks
-    # -----------------------------
-    CHUNK_SIZE = 500  # characters
-    chunks = [context[i:i+CHUNK_SIZE] for i in range(0, len(context), CHUNK_SIZE)]
+# --- Main Logic ---
 
-    # -----------------------------
-    # Embeddings
-    # -----------------------------
-    embed_model = SentenceTransformer('all-MiniLM-L6-v2')
-    embeddings = embed_model.encode(chunks)
+# Store FAISS vector store in session state
+if "vectorstore" not in st.session_state:
+    st.session_state.vectorstore = None
 
-    # FAISS index
-    index = faiss.IndexFlatL2(embeddings.shape[1])
-    index.add(embeddings)
+if pdf_docs:
+    if st.button("📤 Submit & Process"):
+        with st.spinner("Processing PDFs..."):
+            all_text = ""
+            for pdf_file in pdf_docs:
+                pdf_reader = PdfReader(pdf_file)
+                for page in pdf_reader.pages:
+                    all_text += page.extract_text() + "\n"
 
-    # -----------------------------
-    # Load HF model for answering
-    # -----------------------------
-    st.info("Loading model... (this may take a minute)")
-    hf_model_name = "TheBloke/guanaco-7B-GPTQ"  # works on CPU or GPU
-    tokenizer = AutoTokenizer.from_pretrained(hf_model_name)
-    model = AutoModelForCausalLM.from_pretrained(hf_model_name, device_map="auto")
+            # Split text into chunks
+            splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+            chunks = splitter.split_text(all_text)
 
-    # -----------------------------
-    # Ask question
-    # -----------------------------
-    question = st.text_input("Ask a question based on the document:")
+            # Create embeddings
+            embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+            st.session_state.vectorstore = FAISS.from_texts(chunks, embeddings)
+            st.success("✅ PDF content indexed successfully!")
 
-    if question:
-        # Search top relevant chunk
-        q_emb = embed_model.encode([question])
-        D, I = index.search(q_emb, k=2)  # top 2 chunks
-        relevant_text = "\n".join([chunks[i] for i in I[0]])
+# --- Load local LLM ---
+@st.cache_resource(show_spinner=False)
+def load_local_llm():
+    tokenizer = AutoTokenizer.from_pretrained("TheBloke/guanaco-7B-GGML")
+    model = AutoModelForCausalLM.from_pretrained("TheBloke/guanaco-7B-GGML")
+    pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_length=512)
+    return HuggingFacePipeline(pipeline=pipe)
+
+llm = load_local_llm()
+
+# --- Question input ---
+user_question = st.text_input("🔍 Ask something from your uploaded PDFs:")
+if user_question:
+    if st.session_state.vectorstore is None:
+        st.warning("⚠️ Please upload and process PDFs first.")
+    else:
+        with st.spinner("Thinking... 💭"):
+            relevant_docs = st.session_state.vectorstore.similarity_search(user_question)
+            chain = load_qa_chain(llm, chain_type="stuff")
+            answer = chain.run(input_documents=relevant_docs, question=user_question)
+            st.success("Answer:")
+            st.write(answer)
 
-        # Generate answer
-        prompt = f"Answer the question using ONLY the context below.\n\nContext:\n{relevant_text}\n\nQuestion: {question}\nAnswer:"
-        inputs = tokenizer(prompt, return_tensors="pt")
-        with st.spinner("🤖 Generating answer..."):
-            outputs = model.generate(**inputs, max_new_tokens=300)
-        answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
-        st.success("✅ Answer:")
-        st.write(answer)
+# --- Fixed footer ---
+st.markdown(
+    """
+    <div style="position: fixed; bottom: 0; width: 100%; background-color: #2F4F4F; padding: 10px; color: white; text-align: center; font-size: 13px;">
+        📄 Multi-PDF Chatbot | Powered by LangChain, FAISS & Local AI
+    </div>
+    """,
+    unsafe_allow_html=True
+)