---

Book Analysis Chatbot (Django + AI)

Analyze any book passage with word count, predominant emotion, candidate source books, and a concise summary. Frontend is a modern chat UI; backend is Django REST-style endpoint wiring your NLP modules.

• Stack: Django, Transformers (emotion), Groq API (LLM), Vanilla JS/Tailwind UI.
• No DB required (stateless analysis), WhiteNoise for static serving, Docker-compatible.

---

Features

• Word count via Python text processing.
• Emotion detection with a pre-trained transformer.
• Book candidates and summaries via Groq LLM API.
• Responsive chat UI with typing indicator and structured result cards.
• Ready for local dev and Hugging Face Spaces (Docker).

---

File Structure

c:/Users/chskc/Desktop/no parking/assignment/
└── book_analysis_project/
    ├── .env
    ├── chat/
    │   ├── admin.py
    │   ├── apps.py
    │   ├── migrations/
    │   │   ├── __init__.py
    │   │   └── __pycache__/
    │   │       └── __init__.cpython-311.pyc
    │   ├── models.py
    │   ├── templates/
    │   │   └── chat/
    │   │       └── chat.html
    │   ├── tests.py
    │   ├── urls.py
    │   ├── views.py
    │   ├── __init__.py
    │   └── __pycache__/
    │       ├── admin.cpython-311.pyc
    │       ├── apps.cpython-311.pyc
    │       ├── models.cpython-311.pyc
    │       ├── urls.cpython-311.pyc
    │       ├── views.cpython-311.pyc
    │       └── __init__.cpython-311.pyc
    ├── chatbot_project/
    │   ├── asgi.py
    │   ├── settings.py
    │   ├── urls.py
    │   ├── wsgi.py
    │   ├── __init__.py
    │   └── __pycache__/
    │       ├── settings.cpython-311.pyc
    │       ├── urls.cpython-311.pyc
    │       ├── wsgi.cpython-311.pyc
    │       └── __init__.cpython-311.pyc
    ├── db.sqlite3
    ├── main.py
    ├── manage.py
    ├── modules/
    │   ├── emotion.py
    │   ├── groq_inference.py
    │   ├── utils.py
    │   ├── wordcount.py
    │   └── __pycache__/
    │       ├── emotion.cpython-311.pyc
    │       ├── groq_inference.cpython-311.pyc
    │       └── wordcount.cpython-311.pyc
    ├── README.md
    ├── requirements.txt
    └── staticfiles/
        └── admin/
            ├── css/...
            ├── img/...
            └── js/...

• chat/: Django app with chat UI template and API endpoints.
• chatbot_project/: Project settings, URLs, WSGI/ASGI.
• modules/: Core NLP logic (word count, emotion, Groq inference, utils).
• staticfiles/: Collected static (auto-generated by collectstatic).
• .env: Environment variables (GROQ_API_KEY, DEBUG, DJANGO_SECRET_KEY).

---

Prerequisites

• Python 3.11+
• Pip and virtualenv
• Groq API key (set GROQ_API_KEY in .env)
• Hugging Face model auto-download enabled on first run

---

Setup (Local Development)

1. Create and activate a virtual environment

python -m venv venv
venv\Scripts\activate

2. Install dependencies

pip install -r requirements.txt

3. Create a .env file at project root

DJANGO_SECRET_KEY=replace-with-a-random-string
DEBUG=True
GROQ_API_KEY=replace-with-your-groq-key

4. Run Django server

python manage.py runserver

5. Open the app

• UI: http://127.0.0.1:8000/
• API: POST http://127.0.0.1:8000/api/ with JSON body: {"passage": "Your text..."}

---

Usage

• Paste a passage in the chat box and click Send.
• Backend calls:
  • modules/wordcount.py for count
  • modules/emotion.py for emotion detection
  • modules/groq_inference.py for candidate books and a 2–3 sentence summary
• Results render as a structured card in the chat.

---

Environment Variables

• DJANGO_SECRET_KEY: any long random string.
• DEBUG: True for local, False for production.
• GROQ_API_KEY: your Groq token for LLM inference.

Store them in .env locally; set them via Space Variables on Hugging Face.

---

Run Tests

If you add tests later under chat/tests.py:

pytest
# or
python manage.py test

---

Productivity and Professional Practices

• Load the transformer model once at startup for consistent latency.
• Use truncation and no_grad for CPU efficiency in emotion.py.
• Keep modules independent and side-effect free for easy testing.
• Add pre-commit hooks (black, isort, flake8) for consistent code style.
• Use feature branches and pull requests for changes.
• Cache models in TRANSFORMERS_CACHE to speed restarts.

---

Deployment (Hugging Face Spaces via Docker)

Spaces supports Docker apps; Django runs behind Gunicorn on port 7860.

1. Add start.sh (executable)

#!/usr/bin/env bash
set -e
python manage.py collectstatic --noinput
gunicorn chatbot_project.wsgi:application --bind 0.0.0.0:7860 --workers 2 --threads 4 --timeout 120

2. Dockerfile (root)

FROM python:3.11-slim
RUN apt-get update && apt-get install -y --no-install-recommends build-essential git curl && rm -rf /var/lib/apt/lists/*
WORKDIR /app
COPY requirements.txt /app/requirements.txt
RUN pip install --no-cache-dir -r requirements.txt
COPY . /app
ENV PORT=7860 PYTHONUNBUFFERED=1 PIP_NO_CACHE_DIR=1
EXPOSE 7860
RUN chmod +x /app/start.sh
CMD ["/app/start.sh"]

3. Configure settings.py for static and hosts

• Enable WhiteNoise middleware.
• STATIC_ROOT = BASE_DIR / "staticfiles"
• ALLOWED_HOSTS = ["*"]

4. Create a Docker Space on Hugging Face

• Create Space → SDK: Docker → CPU.
• Set Space Variables: DJANGO_SECRET_KEY, DEBUG=False, GROQ_API_KEY.

5. Push code to the Space repo

git add .
git commit -m "Deploy: Dockerized Django app for HF Spaces"
git push

6. Open your Space URL

• Check the UI at root.
• If static files are missing, verify collectstatic ran in logs.

Tip: First request may be slower due to model cold-start. Warm-up by calling a tiny passage in AppConfig.ready() if desired.

---

Git Workflow

• Initial push:

git init
git add .
git commit -m "Initial commit: Django chat + modules + UI"
git branch -M main
git remote add origin https://github.com/<user>/<repo>.git
git push -u origin main

• Update cycle:

git add .
git commit -m "Update: Tailwind UI + API error handling"
git push

• If remote is ahead:

git pull --rebase origin main
# resolve conflicts
git push

---

API Contract

POST /api/

• Request:

{"passage": "Your book excerpt here..."}

• Response:

{
  "success": true,
  "data": {
    "total_words": 123,
    "emotion": "joy (0.83)",
    "possible_books": {"possible_books": ["The Alchemist", "To Kill a Mockingbird"]},
    "summary": "Two-sentence summary..."
  }
}

Errors:

{"success": false, "error": "message"}

---

Troubleshooting

• Module not found:
  • Ensure PYTHONPATH includes project root; run from repo root.
• 403 CSRF on POST:
  • Use @csrf_exempt on API or send CSRF token if you enable CSRF.
• Static files not loading in Spaces:
  • Check WhiteNoise, collectstatic logs, and STATIC_URL/STATIC_ROOT.
• Slow first inference:
  • Model download on first call; subsequent calls are faster.

---

Roadmap

• Add LangGraph for agentic orchestration.
• Add caching for repeated passages.
• Add streaming UI responses and typing delay.
• Optional DB to log requests for analytics.

---

License

MIT (suggested). Include LICENSE file if open-sourcing.