christofy 0.0.3

A lightweight and modular PyTorch-based image classification package

Christofy 🧠📦

Christofy is a lightweight and modular PyTorch-based image classification package designed for both training and prediction. Built on top of ResNet18, it supports both binary and multi-class classification with clean abstractions and an easy-to-use API. Now featuring a powerful RAG (Retrieval-Augmented Generation) system with Ollama integration!

---

🚀 Features

• ✅ Train image classifiers using CNN (ResNet18)
• ✅ Binary and multi-class classification support
• ✅ Predict the class of a single image using saved model
• ✅ Modular structure: clean separation between training and prediction
• ✅ RAG pipeline with Ollama integration for text analysis
• ✅ Support for multiple file formats (PDF, DOCX, CSV, Excel, TXT, JSON)
• ✅ Ready to be installed as a Python package

---

📚 Usage

Image Classification

import christofy

# Train a model
christofy.train_model(
    data_dir="path/to/dataset",
    learning_rate=0.001,
    epochs=10,
    batch_size=32,
    output_dir="output"
)

# Make predictions
predicted_class = christofy.predict_image(
    model_path="output/model.pth",
    image_path="path/to/image.jpg"
)

RAG Pipeline

from christofy import run_rag_pipeline

# Example usage
response = run_rag_pipeline(
    data="path/to/documents",  # Can be file, directory, or text
    query="Your question here?",
    model="llama2",              # Your local Ollama model
    embedding_model="nomic-embed-text",  # For embeddings
    temperature=0.7
)

print(response)

Supported File Formats for RAG

• PDF files (requires PyPDF2 or pdfplumber)
• Word documents (DOCX) (requires python-docx)
• CSV and Excel files (requires pandas)
• Text files (TXT)
• JSON files

Requirements

• Python 3.9+
• PyTorch
• Ollama (for RAG functionality)
• Additional dependencies based on file formats

Installation

pip install christofy

For PDF support:

pip install PyPDF2  # or pdfplumber

For DOCX support:

pip install python-docx

For CSV/Excel support:

pip install pandas openpyxl

---

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.