markdown

app.py

@@ -1,34 +1,39 @@
 import os
 import gradio as gr
 import google.generativeai as genai
-from reportlab.platypus import SimpleDocTemplate, Paragraph
-from reportlab.lib.styles import getSampleStyleSheet
-from reportlab.lib.pagesizes import A4
+from markdown_pdf import MarkdownPdf, Section
 
 # -------------------- CONFIG --------------------
 genai.configure(api_key=os.getenv("GEMINI_API_KEY"))
 
 # ---------- PROMPTS ----------
-TRANSCRIPTION_PROMPT = """ Your Role: You are an expert technical transcriber specializing in mathematical and scientific documents. Your mission is to convert handwritten solutions from a provided image or PDF into a clean, accurate, and logically structured Markdown format.
+TRANSCRIPTION_PROMPT = """Your Role: You are an expert technical transcriber specializing in mathematical and scientific documents. Your mission is to convert handwritten solutions from a provided image or PDF into a clean, accurate, and logically structured Markdown format.
 Primary Objective: Preserve the author's intended solution path while filtering out all mistakes, corrections, and extraneous marks. The final output must be perfectly formatted and easy to follow.
+
 Core Instructions:
 Hierarchical Structure:
-Identify all questions and subquestions based on their numbering (e.g., 1. a), ### i)).
-Use ## for main questions (e.g., ## Question 1).
-Use ### for subquestions (e.g., ### a), ### i)).
-If a question number appears out of its logical sequence, transcribe it with the label provided in the source.
+- Identify all questions and subquestions based on their numbering (e.g., 1. a), i)).
+- Use ## for main questions (e.g., ## Question 1).
+- Use ### for subquestions (e.g., ### a), ### i)).
+- If a question number appears out of its logical sequence, transcribe it with the label provided in the source.
+
 What to Exclude (Content Filtration):
-Mistakes: Completely ignore and do not transcribe any number, variable, or expression that has been struck through, scribbled over, or crossed out. Transcribe only the corrected, final version.
-Extraneous Marks: Do not include any doodles, underlines (unless part of a fraction), or stray marks not relevant to the solution.
+- Mistakes: Completely ignore and do not transcribe any number, variable, or expression that has been struck through, scribbled over, or crossed out. Transcribe only the corrected, final version.
+- Extraneous Marks: Do not include any doodles, underlines (unless part of a fraction), or stray marks not relevant to the solution.
+
 Crucial Distinction: Cancellations vs. Step Cuts:
-Term Cancellation: This is a valid mathematical step where terms cancel each other out (e.g., +2x and -2x, or a term divided by itself).
-Action: Transcribe the step where the cancellation occurs. Immediately after that line, add a concise, bracketed note explaining what was cancelled.
-Step Cut: This is when the author skips intermediate algebraic or arithmetic steps (e.g., jumping from 2b = 2 directly to b = 1).
-Action: Transcribe the steps exactly as they appear. Do not invent or add the missing steps. The logical jump in the transcribed output serves to represent the step cut.
+- Term Cancellation: This is a valid mathematical step where terms cancel each other out (e.g., +2x and -2x, or a term divided by itself).
+  Action: Transcribe the step where the cancellation occurs. Immediately after that line, add a concise, bracketed note explaining what was cancelled.
+- Step Cut: This is when the author skips intermediate algebraic or arithmetic steps (e.g., jumping from 2b = 2 directly to b = 1).
+  Action: Transcribe the steps exactly as they appear. Do not invent or add the missing steps. The logical jump in the transcribed output serves to represent the step cut.
+
 Formatting and Special Cases:
-Equations: Enclose all mathematical equations and multi-line calculations in Markdown code blocks for clarity and proper rendering.
-Illegibility: If a specific word or number is impossible to read, use the placeholder [illegible].
-Graphs: Do not attempt to recreate graphs. Instead, describe them textually. Note the type of curve (e.g., parabola, polynomial) and list any labeled key points like intercepts, vertices, or asymptotes."""
+- Equations: Enclose all mathematical equations and multi-line calculations in Markdown code blocks for clarity and proper rendering.
+- Illegibility: If a specific word or number is impossible to read, use the placeholder [illegible].
+- Graphs: Do not attempt to recreate graphs. Instead, describe them textually. Note the type of curve (e.g., parabola, polynomial) and list any labeled key points like intercepts, vertices, or asymptotes.
+"""
+
+# Full 9-rule grading prompt (point 9 is Presentation; "Calculators" section removed)
 GRADING_PROMPT = """Instructions to Examiners 
 
 Abbreviations:  
@@ -108,16 +113,13 @@ Implied marks appear in brackets, e.g. (M1), and can only be awarded if correct
 - More than one solution: mark only the first response unless candidate specifies otherwise.  
 """
 
-
-# ---------- HELPER: Save to PDF ----------
+# ---------- HELPER: Save to PDF using markdown-pdf ----------
 def save_as_pdf(text, filename="output.pdf"):
-    styles = getSampleStyleSheet()
-    doc = SimpleDocTemplate(filename, pagesize=A4)
-    story = [Paragraph(p, styles["Normal"]) for p in text.split("\n")]
-    doc.build(story)
+    pdf = MarkdownPdf()
+    pdf.add_section(Section(text, toc=False))
+    pdf.save(filename)
     return filename
 
-
 # ---------- STEP 1: TRANSCRIPTION ----------
 def transcribe(ans_file):
     try:
@@ -135,7 +137,6 @@ def transcribe(ans_file):
     except Exception as e:
         return f"❌ Error during transcription: {e}", None
 
-
 # ---------- STEP 2: GRADING ----------
 def grade(qp_file, ms_file, transcription):
     try:
@@ -143,18 +144,39 @@ def grade(qp_file, ms_file, transcription):
         ms_uploaded = genai.upload_file(path=ms_file, 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)
-        if not grading and resp.candidates:
-            grading = resp.candidates[0].content.parts[0].text
+        # Prompt that embeds the full 9 rules and enforces a structured grading table
+        structured_instructions = (
+            "You are an official examiner. Use the following grading rules strictly:\n\n"
+            f"{GRADING_PROMPT}\n\n"
+            "OUTPUT FORMAT (use GitHub-flavored Markdown table):\n\n"
+            "| Student wrote | Marks Awarded | Reason (reference the rules; specify error type: A : All Good , B : Silly Mistake , C : Conceptual Error , D : Hard question ,  E : Not Applicable) |\n"
+            "|---|---|---|\n"
+            "Then, after the table, provide a short 'Summary & Final Mark' section with totals and any FT usage noted.\n\n"
+            "Guidelines:\n"
+            "1) Apply marks exactly as per the markscheme.\n"
+            "2) Justify each awarded or withheld mark with explicit references to the numbered rules.\n"
+            "3) Classify all errors (Conceptual Error, Silly Mistake, Misread, or None).\n"
+            "4) Enforce dependency between M and A marks (no A awarded if M not earned) and indicate FT when applied.\n"
+            "5) Do not invent marks that are not present in the markscheme.\n"
+            "6) Provide step-by-step reasoning for each mark awarded or withheld.\n"
+        )
+
+        response = model.generate_content([
+            structured_instructions,
+            qp_uploaded,      # uploaded question paper
+            ms_uploaded,      # uploaded marking scheme
+            transcription     # student's transcription
+        ])
+
+        grading = getattr(response, "text", None)
+        if not grading and response.candidates:
+            grading = response.candidates[0].content.parts[0].text
 
         pdf_path = save_as_pdf(grading, "grading.pdf")
         return grading, pdf_path
     except Exception as e:
         return f"❌ Error during grading: {e}", None
 
-
 # ---------- GRADIO APP ----------
 with gr.Blocks(title="LeadIB AI Grading") as demo:
     gr.Markdown("## LeadIB AI Grading\nUpload exam documents to transcribe and grade student answers step by step.")