Update app.py

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 import os
+import time
 from langchain_community.document_loaders import PyPDFLoader
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_community.embeddings.fastembed import FastEmbedEmbeddings
@@ -7,133 +8,174 @@ from langchain_community.vectorstores import FAISS
 from langchain_huggingface import HuggingFaceEndpoint
 from langchain_core.prompts import ChatPromptTemplate
 
-# --- 1. Model Setup using HF Inference API ---
-# Get the HF token from environment variables (set in Space secrets)
-HF_TOKEN = os.environ.get("HF_TOKEN", "")
+# --- 1. Model Setup ---
+HF_TOKEN = os.environ.get("HF_TOKEN")
 
-if not HF_TOKEN:
-    print("⚠️ Warning: HF_TOKEN not set. The app may not work properly.")
-    print("Please add your Hugging Face token in Space Settings > Repository secrets")
-
-llm = HuggingFaceEndpoint(
-    repo_id="meta-llama/Meta-Llama-3-8B-Instruct",
-    temperature=0.7,
-    max_new_tokens=2000,
-    huggingfacehub_api_token=HF_TOKEN
-)
+# Setup the Model (Llama 3 8B via API)
+if HF_TOKEN:
+    llm = HuggingFaceEndpoint(
+        repo_id="meta-llama/Meta-Llama-3-8B-Instruct",
+        temperature=0.5,
+        max_new_tokens=4096,
+        huggingfacehub_api_token=HF_TOKEN,
+    )
+else:
+    llm = None
 
-# --- 2. The Core Logic ---
+# --- 2. Logic ---
 def generate_question_paper(pdf_file, difficulty, num_questions):
-    if not pdf_file:
-        return "❌ Please upload a PDF file first."
-    
+    # Error Handling for missing token
     if not HF_TOKEN:
-        return "❌ Error: HF_TOKEN not configured. Please add your Hugging Face token in Space Settings > Repository secrets."
+        return "⚠️ Error: HF_TOKEN is missing. Please add it in Space Settings > Secrets.", "Error"
     
+    if not pdf_file:
+        return "⚠️ Please upload a PDF file first.", "Input Error"
+
     try:
-        # A. Load PDF
+        # Progress updates (simulated for UI feedback)
+        yield "📂 Reading PDF...", "Processing"
         loader = PyPDFLoader(pdf_file.name)
         pages = loader.load()
         
         if not pages:
-            return "❌ Error: Could not extract text from PDF. Please ensure it's a valid PDF with text content."
-        
-        # B. Split Text
+            return "❌ Error: The PDF appears to be empty or unreadable.", "Error"
+
+        yield f"✂️ Splitting {len(pages)} pages...", "Processing"
         text_splitter = RecursiveCharacterTextSplitter(
             chunk_size=1000,
             chunk_overlap=100
         )
         chunks = text_splitter.split_documents(pages)
-        
-        # C. Vector Store (FAISS)
+
+        yield "🧠 Analyzing content...", "Embedding"
         embeddings = FastEmbedEmbeddings()
         vector_store = FAISS.from_documents(chunks, embeddings)
         
-        # D. Retrieve Context
-        retriever = vector_store.as_retriever(search_kwargs={"k": 7})
-        context_docs = retriever.invoke("Key concepts and definitions")
+        yield "🔍 Retrieving key concepts...", "Retrieving"
+        retriever = vector_store.as_retriever(search_kwargs={"k": 5})
+        context_docs = retriever.invoke("Summary of key topics, definitions, and important details")
         context_text = "\n\n".join([doc.page_content for doc in context_docs])
-        
-        # E. Prompt
-        template = """You are an expert academic examiner. Create a formal Question Paper based ONLY on the context provided below.
-
-CONTEXT:
-{context}
-
-INSTRUCTIONS:
-- Difficulty: {difficulty}
-- Total Questions: {num_questions}
-- Format:
-  Section A: Multiple Choice Questions (MCQs)
-  Section B: Short Answer Questions
-  Section C: Long Answer/Essay Questions
-- Provide the Answer Key for MCQs at the very end.
 
-Do not output conversational text. Output ONLY the exam paper in a well-formatted structure."""
+        # Prompt
+        template = """
+        You are an expert academic examiner. Create a rigorous Question Paper based ONLY on the provided context.
         
-        prompt = ChatPromptTemplate.from_template(template)
+        CONTEXT:
+        {context}
+        
+        INSTRUCTIONS:
+        - Difficulty: {difficulty}
+        - Total Questions: {num_questions}
+        - Structure:
+          * Part A: Multiple Choice ({num_questions} questions)
+          * Part B: Short Answer (2 questions)
+          * Part C: Essay/Long Answer (1 question)
+        - Include an "Answer Key" section at the very bottom.
         
-        # F. Generate
+        OUTPUT FORMAT:
+        Return valid Markdown. Use bold headers. Do not output conversational filler.
+        """
+        
+        prompt = ChatPromptTemplate.from_template(template)
         chain = prompt | llm
+        
+        yield "✨ Generating final paper...", "Generating"
         response = chain.invoke({
             "context": context_text, 
             "difficulty": difficulty,
             "num_questions": num_questions
         })
         
-        return response
+        yield response, "Complete"
 
     except Exception as e:
-        return f"❌ Error processing PDF: {str(e)}\n\nPlease check:\n1. PDF is valid and contains text\n2. HF_TOKEN is correctly set\n3. You have access to Llama 3"
+        yield f"❌ System Error: {str(e)}", "Failed"
+
+# --- 3. Custom UI ---
+# Custom CSS for a professional look
+custom_css = """
+.container { max-width: 1200px; margin: auto; padding-top: 20px; }
+.header-text { text-align: center; font-family: 'Helvetica', sans-serif; }
+.header-text h1 { color: #2D3748; font-size: 3em; margin-bottom: 0px; }
+.header-text h3 { color: #718096; font-weight: 300; }
+.submit-btn { background: linear-gradient(90deg, #4F46E5 0%, #7C3AED 100%) !important; color: white !important; border: none !important; }
+.status-bar { border: 1px solid #e2e8f0; background: #f7fafc; padding: 10px; border-radius: 8px; color: #4a5568; }
+"""
+
+theme = gr.themes.Soft(
+    primary_hue="indigo",
+    secondary_hue="blue",
+    neutral_hue="slate",
+    text_size="lg"
+)
 
-# --- 3. The UI ---
-with gr.Blocks(title="AI Question Paper Generator") as demo:
-    gr.Markdown("# 📄 AI Question Paper Generator")
-    gr.Markdown("Powered by **Llama 3 (8B)** via Hugging Face Inference API")
-    gr.Markdown("⚡ Fast • 🎯 Accurate • 📚 Context-Aware")
+with gr.Blocks(theme=theme, css=custom_css, title="AI Exam Gen") as demo:
     
-    with gr.Row():
-        with gr.Column(scale=1):
-            pdf_input = gr.File(
-                label="📄 Upload Study Material (PDF)",
-                file_types=[".pdf"]
-            )
-            
-            with gr.Group():
-                difficulty = gr.Radio(
-                    ["Easy", "Medium", "Hard"], 
-                    label="🎚️ Difficulty Level", 
-                    value="Medium"
+    with gr.Column(elem_classes="container"):
+        # Header
+        gr.HTML("""
+            <div class="header-text">
+                <h1>📝 AI Question Paper Generator</h1>
+                <h3>Upload study material, get a formatted exam in seconds.</h3>
+            </div>
+        """)
+        
+        with gr.Row(variant="panel", equal_height=True):
+            # Left Column: Inputs
+            with gr.Column(scale=1):
+                gr.Markdown("### 🛠️ Configuration")
+                pdf_input = gr.File(
+                    label="Upload PDF (Study Notes/Book)",
+                    file_types=[".pdf"],
+                    file_count="single",
+                    height=100
                 )
-                num_questions = gr.Slider(
-                    5, 20, value=10, step=1, 
-                    label="📊 Total Questions"
+                
+                with gr.Group():
+                    difficulty = gr.Radio(
+                        ["Easy", "Medium", "Hard"], 
+                        label="Difficulty Level", 
+                        value="Medium",
+                        info="Adjusts complexity of questions."
+                    )
+                    
+                    num_questions = gr.Slider(
+                        minimum=5, 
+                        maximum=20, 
+                        value=10, 
+                        step=1, 
+                        label="Number of MCQs",
+                        info="How many objective questions?"
+                    )
+                
+                btn = gr.Button("✨ Generate Question Paper", elem_classes="submit-btn", variant="primary")
+                status = gr.Textbox(label="Status", placeholder="Ready", interactive=False, max_lines=1)
+
+            # Right Column: Output
+            with gr.Column(scale=2):
+                gr.Markdown("### 📄 Generated Exam")
+                output = gr.Markdown(
+                    label="Exam Paper", 
+                    value="_Your generated question paper will appear here..._",
+                    show_copy_button=True,
+                    line_breaks=True
                 )
-            
-            btn = gr.Button("✨ Generate Question Paper", variant="primary", size="lg")
-            
-            gr.Markdown("""
-            ### 📝 Instructions:
-            1. Upload a PDF containing study material
-            2. Select difficulty level
-            3. Choose number of questions
-            4. Click Generate!
-            """)
-        
-        with gr.Column(scale=2):
-            output = gr.Markdown(label="Generated Question Paper")
 
+    # Logic
     btn.click(
         fn=generate_question_paper,
         inputs=[pdf_input, difficulty, num_questions],
-        outputs=output
+        outputs=[output, status]
+    )
+
+    # Footer
+    gr.Markdown(
+        """
+        <div style="text-align: center; color: #a0aec0; margin-top: 40px;">
+            Powered by Llama 3 • LangChain • Hugging Face
+        </div>
+        """
     )
-    
-    gr.Markdown("""
-    ---
-    **Note:** This app requires a Hugging Face token with access to Llama 3. 
-    Set `HF_TOKEN` in your Space's repository secrets.
-    """)
 
 if __name__ == "__main__":
     demo.launch()