README.md

metadata

title: PlantInfo
emoji: 🦀
colorFrom: green
colorTo: blue
sdk: gradio
sdk_version: 5.17.1
app_file: app.py
pinned: false
license: apache-2.0

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

🌿 AI Plant Guide - English & Arabic

Overview

AI Plant Guide is a user-friendly Gradio-based application that provides detailed plant information in both English and Arabic. By entering a plant name and selecting a language, users can access insights on scientific names, growing conditions, common uses, and care tips.

Project Objectives

• Provide an AI-powered plant guide with bilingual support.
• Ensure user-friendly interaction through a web-based interface.
• Leverage state-of-the-art NLP models for accurate and informative responses.
• Offer quick and efficient responses using GPU acceleration.

Implemented Pipelines

1. User Input Handling:
   • The user enters a plant name and selects a language.
2. Model Selection:
   • Based on the chosen language, the appropriate transformer model is loaded:
     • Microsoft Phi-3-mini-4k-instruct for English
     • ALLaM-7B-Instruct-preview for Arabic
3. Text Generation Pipeline:
   • The selected model generates plant details, including:
     • Scientific name
     • Growing conditions
     • Common uses
     • Care tips
4. Output Display:
   • The generated information is displayed in a user-friendly interface.

Instructions for Using the Interface

1. Open the Gradio UI in your browser.
2. Select a language (English/Arabic).
3. Enter a plant name (e.g., Lavender, Aloe Vera).
4. Click "🔍 Get Plant Info" to generate information.
5. View the plant details in the output box.

Justification for Model and Pipeline Choices

• Hugging Face Transformers: Offers pre-trained state-of-the-art language models optimized for text generation.
• Gradio: Provides an easy-to-use web interface without the need for extensive frontend development.
• PyTorch: Ensures efficient model inference and flexibility for future enhancements.
• GPU Acceleration: Speeds up response times, improving user experience.
• Pipeline-Based Design: Ensures modularity and scalability for future improvements.

Bilingual Implementation

• The project supports English and Arabic via two specialized transformer models.
• The UI allows users to choose their preferred language.
• The prompt structure is adapted for each language to ensure high-quality responses.

Technologies Used

• Gradio for UI development
• Transformers (Hugging Face) for text generation
• PyTorch for model inference
• Microsoft Phi-3-mini-4k-instruct (English) and ALLaM-7B-Instruct-preview (Arabic) models
• Spaces GPU Acceleration

Installation

Prerequisites

Ensure you have Python installed (>=3.8) and required dependencies.

Steps

1. Clone the repository:

   git clone https://huggingface.co/spaces/NoufSaleh46/PlantInfo1
   cd PlantInfo1
   

2. Create a virtual environment (optional but recommended):

   python -m venv venv
   source venv/bin/activate  # On Windows use `venv\Scripts\activate`
   

3. Install dependencies:

   pip install -r requirements.txt
   

4. Run the application:

   python app.py
   

Deployment

This project is deployed on Hugging Face Spaces. You can access it directly here.