app.py

# app.py

import os
import tensorflow as tf
from pymongo import MongoClient
from flask import Flask, request, jsonify, render_template
from huggingface_hub import login
from services.disease_detection import PoultryFarmBot
from services.llama_service import llama2_response

# Initialize Flask application
app = Flask(__name__, template_folder="templates", static_folder="static")

# Register Blueprints for API routes
from auth.auth_routes import auth_bp
from routes.health_routes import health_bp
from routes.inventory_routes import inventory_bp
from routes.usage_routes import usage_bp

app.register_blueprint(usage_bp, url_prefix='/api/usage')
app.register_blueprint(inventory_bp, url_prefix='/api/inventory')
app.register_blueprint(health_bp, url_prefix='/api/health')
app.register_blueprint(auth_bp, url_prefix='/auth')

# Ensure the Hugging Face token is set
tok = os.getenv('HF_Token')
if tok:
    login(token=tok, add_to_git_credential=True)
else:
    print("Warning: Hugging Face token not found in environment variables.")

# MongoDB Setup
MONGO_URI = os.getenv("MONGO_URI")
client = MongoClient(MONGO_URI)
db = client.poultry_farm  # Database

# Check GPU availability for TensorFlow
print("TensorFlow version:", tf.__version__)
print("Eager execution:", tf.executing_eagerly())
print("TensorFlow GPU Available:", tf.config.list_physical_devices('GPU'))

# Set TensorFlow to use mixed precision with available GPU
from tensorflow.keras import mixed_precision
if len(tf.config.list_physical_devices('GPU')) > 0:
    policy = mixed_precision.Policy('mixed_float16')
    mixed_precision.set_global_policy(policy)
    print("Using mixed precision with GPU")
else:
    print("Using CPU without mixed precision")

# Initialize PoultryFarmBot
bot = PoultryFarmBot(db=db)


# Routes
@app.route('/')
def index():
    return render_template('index.html')


# API to handle disease detection and AI assistant text response
@app.route('/api/chat', methods=['POST'])
def chat():
    data = request.json
    message = data.get('message')
    image = data.get('image')

    if image:
        # Handle disease detection with image
        diagnosis, name, status, recom = bot.predict(image)
        return jsonify({
            "response": f"Disease: {name}, Status: {status}, Recommendation: {recom}"
        })

    # Handle AI text generation with Llama model
    response = llama2_response(message)
    return jsonify({"response": response})


# Run the Flask app
if __name__ == "__main__":
    app.run(debug=True)