Gpt

app.py

@@ -1,87 +1,252 @@
-import os
 import gradio as gr
-import google.generativeai as genai
-
-# Configure Gemini API (key must be set in Hugging Face Space secrets)
-genai.configure(api_key=os.getenv("GEMINI_API_KEY"))
-
-# ---------- PROMPTS ----------
-TRANSCRIPTION_PROMPT = """
+import os
+import io
+from google import generativeai as genai
+
+def process_exam_papers(question_paper, marking_scheme, answer_sheet, api_key, progress=gr.Progress()):
+    """
+    Process uploaded exam papers and return transcription and grading
+    """
+    if not api_key:
+        return "Please provide a valid Gemini API key.", "", "Ready"
+    
+    if not all([question_paper, marking_scheme, answer_sheet]):
+        return "Please upload all three files.", "", "Ready"
+    
+    try:
+        # Configure Gemini API
+        genai.configure(api_key=api_key)
+        
+        progress(0.1, desc="Uploading files to Gemini...")
+        
+        # Upload files to Gemini
+        qp_file = genai.upload_file(path=question_paper.name, display_name="Question Paper")
+        ms_file = genai.upload_file(path=marking_scheme.name, display_name="Marking Scheme")
+        ans_file = genai.upload_file(path=answer_sheet.name, display_name="Answer Sheet")
+        
+        progress(0.3, desc="Files uploaded. Starting transcription...")
+        
+        # Transcription instructions
+        transcription_instructions = """
 Persona:
-You are an expert transcriptionist specializing in scientific and mathematical documents. 
-Your primary goal is to convert handwritten mathematical work into a perfectly formatted, 
-machine-readable Markdown document using LaTeX for all mathematical notation.
-
-Rules:
-- Transcribe exactly what is written, do not correct errors.
-- Use $...$ for inline math, $$...$$ for block math.
-- Ignore struck-through text.
-- Preserve structure: bold for Q numbers (**1.**), step-by-step math with \\begin{align*}.
-- If a symbol is ambiguous, mark as [x?].
-Output must be a clean Markdown string.
+You are an expert transcriptionist specializing in scientific and mathematical documents. Your primary goal is to convert handwritten mathematical work into a perfectly formatted, machine-readable Markdown document using LaTeX for all mathematical notation.
+
+Core Task:
+Your task is to transcribe the provided handwritten student solutions into a single, clean Markdown string.
+
+Key Directives & Rules:
+Absolute Fidelity: Transcribe exactly what is written. Do NOT correct mathematical errors, logical fallacies, or spelling mistakes. Your role is purely that of a scribe, not a grader or editor.
+
+LaTeX for All Math: All mathematical content—including single variables, numbers in equations, fractions, exponents, roots, and symbols—must be enclosed in LaTeX delimiters. Use inline $ ... $ for math within text and block $$ ... $$ for standalone equations.
+
+Handle Strikethroughs: Completely ignore and omit any text, numbers, or expressions that have been struck through by the student. Do not include them in the final output.
+
+Preserve Structure:
+Use Markdown bolding (e.g., **1.**, **2a.**) to clearly separate each question or sub-part.
+Maintain the vertical, step-by-step flow of the student's derivations. For multi-line aligned equations, use the \\begin{align*} ... \\end{align*} environment within a $$ ... $$ block.
+
+Handle Ambiguity: If a character or symbol is genuinely illegible or ambiguous, make your best interpretation and enclose it in square brackets. For example, if a variable could be u or v, write [u?].
+
+Output Format:
+The final output must be a single Markdown string.
+Ensure all LaTeX renders correctly and the structure is clean and readable.
+
+Comprehensive Example:
+If the student's handwritten work for a question looks like this:
+7. Find the value of y.
+y = (x² + 3) / 2
+for x = 3
+y = (3² + 3) / 2
+y = (6+3) / 2
+y = (9 + 3) / 2
+y = 12 / 2
+y = 6
+
+Your expected output should be:
+**7.**
+
+Find the value of y.
+$$
+y = \\frac{x^2 + 3}{2}
+$$
+for $x = 3$
+$$
+\\begin{align*}
+y &= \\frac{3^2 + 3}{2} \\\\
+y &= \\frac{9 + 3}{2} \\\\
+y &= \\frac{12}{2} \\\\
+y &= 6
+\\end{align*}
+$$
 """
-
-GRADING_PROMPT = """
-You are an official examiner. Grade the student transcription using the question paper 
-and the official marking scheme.
-
-Rules:
-1. Apply marks exactly as per the markscheme (M1, A1, etc.).
-2. M marks must be earned before A marks.
-3. Justify each awarded or withheld mark with clear reasoning.
-4. Classify all errors as Conceptual Error, Silly Mistake, or None.
-5. Follow dependency between M and A strictly.
-6. Do not give marks outside the markscheme.
-Output must be a structured grading report with reasoning.
+        
+        # Initialize Gemini model for transcription
+        model = genai.GenerativeModel(
+            "gemini-2.5-pro",
+            generation_config={"temperature": 0}
+        )
+        
+        progress(0.4, desc="Transcribing handwritten answers...")
+        
+        # Generate transcription
+        response = model.generate_content([
+            transcription_instructions,
+            ans_file
+        ])
+        
+        # Extract transcription safely
+        student_transcription = getattr(response, "text", None)
+        if not student_transcription:
+            student_transcription = response.candidates[0].content.parts[0].text
+        
+        progress(0.7, desc="Transcription complete. Starting grading process...")
+        
+        # Return transcription first, then continue with grading
+        yield student_transcription, "⏳ Grading in progress...", "Grading"
+        
+        # Grading system instructions
+        grading_system = """
+Instructions to Examiners:
+Abbreviations:
+- M: Marks for correct Method.
+- A: Marks for Answer or Accuracy (often depends on preceding M mark).
+- R: Marks for clear Reasoning.
+- AG: Answer given in the question; no marks awarded.
+- FT: Follow Through; award marks for correct method/answer using incorrect earlier results.
+
+Marking Rules:
+1. Always follow the markscheme annotations (M1, A2, etc.).
+2. M marks must be earned before dependent A marks are awarded (no M0 followed by A1 unless explicitly allowed).
+3. If M and A marks are on the same line (e.g., M1A1), M is for the method attempt, A is for correct values.
+4. Multiple A marks on the same line are awarded independently unless otherwise noted.
+5. Do not split M2, A3, etc. unless instructed.
+6. "Show that" responses do not need to restate the AG line unless noted.
+7. Once a correct answer is seen, ignore further incorrect working unless it affects a later part (then apply FT as appropriate).
+8. Do not award the final A mark if an incorrect approximation is used in the same part.
+
+Error Avoidance:
+- **No incorrect mark allocation:** Do not award marks unless they are explicitly justified by the markscheme.
+- **No misclassification of errors:** Distinguish correctly between "Conceptual Errors" and "Silly Mistakes."
+- **Follow markscheme logic exactly:** Especially regarding when to withhold accuracy marks if method marks are not earned.
 """
-
-# ---------- STEP 1: TRANSCRIPTION ----------
-def transcribe(ans_file):
-    try:
-        ans_uploaded = genai.upload_file(path=ans_file.name, display_name="Answer Sheet")
-
-        model = genai.GenerativeModel("gemini-2.5-pro", generation_config={"temperature": 0})
-        resp = model.generate_content([TRANSCRIPTION_PROMPT, ans_uploaded])
-
-        transcription = getattr(resp, "text", None) or resp.candidates[0].content.parts[0].text
-        return transcription
+        
+        # Now start grading using the transcribed text
+        # Generate grading
+        grading_response = model.generate_content([
+            f"You are an official examiner. Use the following grading system and rules to assess the answers:\n\n{grading_system}\n\n"
+            "Your output must:\n"
+            "1. Apply marks exactly as per the markscheme.\n"
+            "2. Justify each awarded or withheld mark with reference to the grading rules.\n"
+            "3. Identify and classify all errors accurately (Conceptual Error, Silly Mistake, or None).\n"
+            "4. Follow the dependency between M and A marks strictly.\n"
+            "5. Avoid giving marks that the markscheme does not allow.\n"
+            "6. Provide a step-by-step reasoning for each mark awarded or withheld, explaining your thought process clearly.\n",
+            qp_file,
+            ms_file,
+            student_transcription  # Use the transcribed text, not the original PDF
+        ])
+        
+        progress(0.9, desc="Finalizing grading results...")
+        
+        # Extract grading safely
+        grading_text = getattr(grading_response, "text", None)
+        if not grading_text and grading_response.candidates:
+            grading_text = grading_response.candidates[0].content.parts[0].text
+        elif not grading_text:
+            grading_text = "No Response"
+        
+        progress(1.0, desc="Complete!")
+        
+        # Return final results
+        yield student_transcription, grading_text, "Complete"
+        
     except Exception as e:
-        return f"❌ Error during transcription: {e}"
-
-# ---------- STEP 2: GRADING ----------
-def grade(qp_file, ms_file, transcription):
-    try:
-        qp_uploaded = genai.upload_file(path=qp_file.name, display_name="Question Paper")
-        ms_uploaded = genai.upload_file(path=ms_file.name, display_name="Marking Scheme")
-
-        model = genai.GenerativeModel("gemini-2.5-pro", generation_config={"temperature": 0})
-        resp = model.generate_content([GRADING_PROMPT, qp_uploaded, ms_uploaded, transcription])
-
-        grading = getattr(resp, "text", None) or resp.candidates[0].content.parts[0].text
-        return grading
-    except Exception as e:
-        return f"❌ Error during grading: {e}"
-
-# ---------- GRADIO APP ----------
-with gr.Blocks(title="📘 AI Teacher Assistant") as demo:
-    gr.Markdown("## 📘 AI Teacher Assistant\nUpload exam documents to transcribe and grade student answers step by step.")
-
+        yield f"Error processing files: {str(e)}", "", "Error"
+
+# Create Gradio interface
+with gr.Blocks(title="Exam Paper Grading System", theme=gr.themes.Soft()) as demo:
+    gr.Markdown("""
+    # 📚 Automated Exam Paper Grading System
+    
+    Upload your question paper, marking scheme, and answer sheet to get automated transcription and grading using Google's Gemini AI.
+    """)
+    
     with gr.Row():
-        qp_file = gr.File(label="Upload Question Paper (PDF)", type="filepath")
-        ms_file = gr.File(label="Upload Mark Scheme (PDF)", type="filepath")
-        ans_file = gr.File(label="Upload Student Answer Sheet (PDF)", type="filepath")
-
-    # Step 1: Transcription
-    transcribe_btn = gr.Button("Step 1: Transcribe Answer Sheet")
-    transcription_out = gr.Markdown(label="📄 Student Transcription")
-
-    # Step 2: Grading
-    grade_btn = gr.Button("Step 2: Grade the Student")
-    grading_out = gr.Textbox(label="✅ Grading Report (Step-by-Step)", lines=20)
-
-    # Button Logic
-    transcribe_btn.click(fn=transcribe, inputs=[ans_file], outputs=[transcription_out])
-    grade_btn.click(fn=grade, inputs=[qp_file, ms_file, transcription_out], outputs=[grading_out])
+        with gr.Column():
+            gr.Markdown("### 📋 Upload Files")
+            api_key = gr.Textbox(
+                label="Gemini API Key",
+                placeholder="Enter your Google Gemini API key",
+                type="password"
+            )
+            question_paper = gr.File(
+                label="Question Paper (PDF)",
+                file_types=[".pdf"]
+            )
+            marking_scheme = gr.File(
+                label="Marking Scheme (PDF)",
+                file_types=[".pdf"]
+            )
+            answer_sheet = gr.File(
+                label="Answer Sheet (PDF)",
+                file_types=[".pdf"]
+            )
+            
+            process_btn = gr.Button(
+                "🚀 Process Papers",
+                variant="primary",
+                size="lg"
+            )
+    
+    with gr.Row():
+        with gr.Column():
+            gr.Markdown("### 📝 Student Answer Transcription")
+            transcription_output = gr.Textbox(
+                label="Transcribed Answers",
+                lines=15,
+                max_lines=25,
+                show_copy_button=True,
+                placeholder="Transcribed answers will appear here first..."
+            )
+        
+        with gr.Column():
+            gr.Markdown("### ✅ Grading Results")
+            grading_output = gr.Textbox(
+                label="Detailed Grading",
+                lines=15,
+                max_lines=25,
+                show_copy_button=True,
+                placeholder="Grading results will appear here after transcription is complete..."
+            )
+    
+    # Add status indicator
+    with gr.Row():
+        status_display = gr.Textbox(
+            label="Status",
+            value="Ready",
+            interactive=False,
+            show_label=True
+        )
+    
+    # Set up the processing function
+    process_btn.click(
+        fn=process_exam_papers,
+        inputs=[question_paper, marking_scheme, answer_sheet, api_key],
+        outputs=[transcription_output, grading_output, status_display]
+    )
+    
+    gr.Markdown("""
+    ### 📖 How to Use:
+    1. **Get a Gemini API Key**: Visit [Google AI Studio](https://makersuite.google.com/app/apikey) to get your free API key
+    2. **Upload PDFs**: Upload your question paper, marking scheme, and student answer sheet
+    3. **Process**: Click the "Process Papers" button to get transcription and grading
+    4. **Review**: Check the transcribed answers and detailed grading results
+    
+    ### ⚠️ Notes:
+    - All uploaded files are processed securely and not stored permanently
+    - The system transcribes exactly what's written (including errors) for accurate grading
+    - LaTeX mathematical notation is automatically formatted for clarity
+    """)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

requirements.txt

@@ -1,4 +1,4 @@
-gradio
-PyPDF2
-pandas
-google-generativeai
+gradio>=4.0.0
+google-generativeai>=0.3.0
+PyPDF2>=3.0.0
+pandas>=1.5.0