ExamPulse AI: Past-Paper Pattern Analyzer & Study Assistant

Inspiration

I am currently pursuing my undergraduate in computer science. So each semester i face a problem that keeps me overthinking: "What will actually appear on the final exam?"

To prepare, i typically spend hours manually flipping through 3 to 5 years of past exam papers, trying to decipher which chapters appear every year and which questions are cyclical. However, manual revision has huge blind spots:

  • It is time-consuming and unstructured.
  • Diagram-heavy questions (graphs, trees, circuits) and scanned question photos are hard to catalog.
  • Then i endup preparing with unstructured way.

So i built ExamPulse AI to automate this entire process—giving students data-backed clarity on what to study, saving hours of manual prep, and boosting exam confidence.


What It Does

ExamPulse AI is a multimodal AI study assistant and dashboard that:

  1. Ingests Any Format: Accepts digital PDFs, plain text, and smartphone photos/scans (.png, .jpg, .jpeg, .webp).
  2. Understands Diagrams & Multimodal Questions: Natively recognizes charts, binary trees, flowcharts, and circuit diagrams using Gemini Vision.
  3. Identifies Repeating Patterns: Computes exact topic frequency, coverage percentages, and year-over-year heatmaps.
  4. Predicts Upcoming Exam Topics: Generates data-backed predictions for the next exam (rated High, Medium, or Low probability) with detailed rationale.
  5. Generates Instant Model Answers: Produces examiner-grade model answers and key evaluation bullet points for any recurring or predicted question.

How I Built It

I structured the application as a 4-stage hybrid AI & data analysis pipeline:

  1. Multimodal Ingestion (extractor.py): Handles MIME classification, best-effort digital text extraction using pypdf, and automatic year deduction from filenames via regex.
  2. Structured Vision Parsing (analyzer.py): Sends raw document bytes and images directly to Google's Gemini 3.5 Flash-Lite multimodal API. I enforce strict JSON output using Pydantic schemas (response_mime_type="application/json") to categorize each question into:
    • Question summary & normalized topic name
    • Question type (Theory, Numerical, Coding, Case Study)
    • Diagram flag (has_diagram) and visual description (diagram_description)
  3. Quantitative Pattern Engine (pandas): Calculates exact statistics across past exam sessions: $$\text{Topic Share (\%)} = \left( \frac{\text{Questions on Topic}}{\text{Total Questions Analyzed}} \right) \times 100$$ $$\text{Year Coverage (\%)} = \left( \frac{\text{Years Topic Appeared}}{\text{Total Exam Years}} \right) \times 100$$ Topics are algorithmically classified into: Every Year, Recurring, Recent Focus, or Occasional.
  4. Interactive Dashboard (app.py): Built in pure Python with Streamlit and Plotly. Features KPI metric cards, an interactive topic heatmap, expandable model answers with session caching, and an instant Markdown study guide export.

Challenges I Faced & How I Resolved Them (AI-Assisted)

Building a production-ready multimodal pipeline revealed several non-trivial engineering hurdles :

  1. Model Deprecation & High Traffic (503 / 429 Errors): Early iterations hit 404 NOT_FOUND for deprecated model aliases and repeated 503 UNAVAILABLE errors during peak global demand on gemini-3.8-flash. After facing repeated API failures across different model options, I used an AI coding assistant to run real-time diagnostic benchmarks on my active account quotas. Based on the benchmark data, I directed the implementation of an automated model fallback system with exponential backoff and selected gemini-3.5-flash-lite, which brought response times down to under 3 seconds while ensuring 100% uptime.
  2. SDK Retry Hangs: Underlying API retry loops caused the dashboard to freeze for minutes when free-tier quotas were exhausted. I isolated the bottleneck by running standalone Python integration tests outside of Streamlit and reconfigured the retry logic to decouple API calls, keeping the dashboard responsive.
  3. Parsing Diagrams Without Heavy OCR Libraries: Traditional OCR engines failed to parse non-text structures like weighted graphs, binary trees, and flowcharts. Instead of bloating the app with heavy local OCR dependencies, I re-architected the ingestion pipeline to leverage Gemini's native multimodal vision capabilities, passing raw image and PDF bytes directly via types.Part.from_bytes() for holistic visual understanding.
  4. Zero-Dependency Markdown Export: During report export, pandas.to_markdown() crashed due to an uninstalled optional tabulate library. Rather than introducing additional system dependencies that could complicate cloud deployment, I replaced it with a custom, pure-Python table generator to keep the application lightweight and deployment-ready.

Accomplishments that i'm proud of

  • Built a Complete End-to-End Pipeline: Seamlessly connected multimodal ingestion, structured AI extraction, Pandas statistical analysis, and an interactive Streamlit UI in a single lightweight app.
  • Multimodal Diagram Recognition: Successfully recognized and summarized visual exam questions containing graphs, trees, and charts from both PDFs and uploaded images without heavy OCR libraries.
  • Sub-3-Second AI Processing: Optimized model selection with gemini-3.5-flash-lite and strict Pydantic JSON schemas, achieving reliable structured parsing in under 3 seconds per paper.
  • Zero Hallucination Numbers: Combined deterministic Pandas math for exact frequency metrics with Gemini's qualitative reasoning, ensuring trends and predictions are grounded in real data.
  • Cloud-Ready & Privacy-Conscious: Implemented a secure key hierarchy (Streamlit Secrets $\rightarrow$ .env $\rightarrow$ UI input) with built-in sample papers so anyone can test the app with zero setup.

What I Learned

  • Structured Outputs are Essential: Enforcing Pydantic schemas eliminates prompt fragility and prevents hallucinated schemas, turning an LLM into a reliable API endpoint.
  • Multimodal AI Beats Traditional OCR: Modern vision models can understand the semantic meaning of diagrams and charts far better than traditional bounding-box OCR tools.
  • Hybrid Pipelines Work Best: Combining quantitative math (Pandas) with qualitative reasoning (Gemini) produces far more trustworthy predictions than asking an LLM to guess numbers on its own.

What's Next for ExamPulse AI

  • Syllabus Cross-Referencing: Uploading course syllabi alongside past papers to highlight untouched topics.
  • Custom Flashcard & Quiz Mode: Automatically generating interactive multiple-choice practice quizzes from predicted topics.
  • Multi-University Benchmarking: Aggregating question patterns across different universities for standardized national exams.

Built With

  • ai-study-assistant
  • computer-vision
  • data-analysis
  • data-visualization
  • document-processing
  • edtech
  • gemini-api
  • generative-ai
  • git
  • github
  • google-gemini
  • google-genai
  • large-language-models
  • multimodal-ai
  • pandas
  • pattern-recognition
  • pdf-extraction
  • plotly
  • predictive-analytics
  • pydantic
  • pypdf
  • python
  • statistical-analysis
  • streamlit
  • streamlit-cloud
Share this project:

Updates

Submission history