Enhance README with project details and setup instructions
Browse filesAdded detailed project description, features, tech stack, installation instructions, and example API response to README.
README.md
CHANGED
|
@@ -3,3 +3,86 @@ title: Homework Validation System
|
|
| 3 |
sdk: docker
|
| 4 |
app_port: 7860
|
| 5 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
sdk: docker
|
| 4 |
app_port: 7860
|
| 5 |
---
|
| 6 |
+
# Homework Validation System (FastAPI)
|
| 7 |
+
|
| 8 |
+
A backend API that validates student homework by extracting text from teacher and student files, comparing answers, and generating remarks using rule-based logic and optional AI.
|
| 9 |
+
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
## Features
|
| 13 |
+
|
| 14 |
+
- Upload teacher and student homework files
|
| 15 |
+
- OCR support for images and scanned PDFs
|
| 16 |
+
- Text extraction from PDF and DOCX
|
| 17 |
+
- Similarity matching using TF-IDF + cosine similarity
|
| 18 |
+
- Optional AI-generated remarks (OpenAI / Gemini)
|
| 19 |
+
- FastAPI Swagger documentation
|
| 20 |
+
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
## Tech Stack
|
| 24 |
+
|
| 25 |
+
- FastAPI
|
| 26 |
+
- Python
|
| 27 |
+
- pytesseract
|
| 28 |
+
- Pillow
|
| 29 |
+
- pypdf / pdf2image
|
| 30 |
+
- python-docx
|
| 31 |
+
- scikit-learn
|
| 32 |
+
- OpenAI / Gemini (optional)
|
| 33 |
+
|
| 34 |
+
---
|
| 35 |
+
|
| 36 |
+
## Project Structure
|
| 37 |
+
|
| 38 |
+
---
|
| 39 |
+
homework_validation_system/
|
| 40 |
+
│
|
| 41 |
+
├── app.py
|
| 42 |
+
├── requirements.txt
|
| 43 |
+
├── artifacts/
|
| 44 |
+
├── uploads/
|
| 45 |
+
├── src/
|
| 46 |
+
│ ├── extractors.py
|
| 47 |
+
│ ├── similarity.py
|
| 48 |
+
│ ├── llm_client.py
|
| 49 |
+
│ └── utils.py
|
| 50 |
+
└── README.md
|
| 51 |
+
## Installation
|
| 52 |
+
|
| 53 |
+
### 1. Create Virtual Environment
|
| 54 |
+
python -m venv myenv
|
| 55 |
+
|
| 56 |
+
### 2. Install Requirements
|
| 57 |
+
pip install -r requirements.txt
|
| 58 |
+
## OCR Setup (Required)
|
| 59 |
+
|
| 60 |
+
### Install Tesseract OCR
|
| 61 |
+
|
| 62 |
+
This project uses **Tesseract OCR** for extracting text from images and scanned PDFs.
|
| 63 |
+
|
| 64 |
+
#### Windows
|
| 65 |
+
1. Download and install Tesseract OCR.
|
| 66 |
+
2. Default installation path:
|
| 67 |
+
3. Add this path in your code:
|
| 68 |
+
|
| 69 |
+
pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
|
| 70 |
+
|
| 71 |
+
### Run API
|
| 72 |
+
uvicorn app:app --reload --host 0.0.0.0 --port 8000
|
| 73 |
+
|
| 74 |
+
### Swagger UI:
|
| 75 |
+
|
| 76 |
+
http://localhost:8000/docs
|
| 77 |
+
|
| 78 |
+
### Example API Response
|
| 79 |
+
{
|
| 80 |
+
"student_id": 1,
|
| 81 |
+
"homework_id": 10,
|
| 82 |
+
"status": "Needs Review",
|
| 83 |
+
"match_percentage": 72,
|
| 84 |
+
"teacher_extracted_text": "...",
|
| 85 |
+
"student_extracted_text": "...",
|
| 86 |
+
"ai_generated_remark": "Good attempt but missing key points.",
|
| 87 |
+
"llm_used": true
|
| 88 |
+
}
|