Image Processing Using Llama 3.2 with Hugging Face Transformers

				
					import os
import json
import requests
from PIL import Image
from flask import Flask, request, render_template, session
from transformers import MllamaForConditionalGeneration, AutoProcessor
import boto3
import torch
import mysql.connector
import re

# Initialize Flask app
app = Flask(__name__)
app.secret_key = "your_secret_key"  # Replace with a strong secret key

# Load the Llama 3.2 model and processor
model_id = "meta-llama/Llama-3.2-11B-Vision-Instruct"
model = MllamaForConditionalGeneration.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, device_map="auto"
)
processor = AutoProcessor.from_pretrained(model_id)

# object storage setup
SPACE_NAME = "your_space_name"
SPACE_REGION = "your_region"
ACCESS_KEY = "your_access_key"
SECRET_KEY = "your_secret_key"

s3 = boto3.client(
    "s3",
    region_name=SPACE_REGION,
    endpoint_url=f"images/image-processing-using-llama-huggingface-section-1.png",
    aws_access_key_id=ACCESS_KEY,
    aws_secret_access_key=SECRET_KEY
)

# the cloud provider Managed MySQL setup
DB_HOST = "your_mysql_host"
DB_PORT = 25060
DB_NAME = "your_database_name"
DB_USER = "your_username"
DB_PASSWORD = "your_password"

# Function to establish a database connection
def get_db_connection():
    try:
        conn = mysql.connector.connect(
            host=DB_HOST, port=DB_PORT, database=DB_NAME, user=DB_USER, password=DB_PASSWORD
        )
        print("✅ Database connection successful!")
        return conn
    except Exception as e:
        print(f"❌ Error connecting to the database: {e}")
        return None

# Function to extract Employee ID & Name from an image
def extract_employee_details(image_path):
    """Extracts Employee Name and ID using Llama 3.2 Vision AI."""
    try:
        image = Image.open(image_path)
        prompt = (
            "Extract the Employee ID and Name from the given image. "
            "Provide output in valid JSON format with keys: 'employee_id' and 'employee_name'."
        )
        messages = [{"role": "user", "content": [{"type": "image"}, {"type": "text", "text": prompt}]}]

        input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
        inputs = processor(image, input_text, return_tensors="pt").to(model.device)

        output = model.generate(**inputs, max_new_tokens=1024)
        raw_result = processor.decode(output[0])

        json_match = re.search(r"\{.*?\}", raw_result, re.DOTALL)
        extracted_data = json.loads(json_match.group(0)) if json_match else {}
        employee_id = extracted_data.get("employee_id", "").strip()
        employee_name = extracted_data.get("employee_name", "").strip()

        return employee_id, employee_name
    except Exception as e:
        return None, None

# Flask Routes
@app.route("/", methods=["GET", "POST"])
def index():
    """Handles image uploads, extracts Employee Name & ID, and stores it in MySQL."""
    result = None
    image_url = session.get("image_url")

    if request.method == "POST":
        image_file = request.files.get("image")
        if not image_file:
            return "Error: Please upload an image.", 400
        filename = image_file.filename
        image_path = os.path.join("/tmp", filename)
        image_file.save(image_path)

        employee_id, employee_name = extract_employee_details(image_path)
        return render_template("index.html", result=result, image_url=image_url)

if __name__ == "__main__":
    app.run(host="0.0.0.0", port=5000)