app.py

import base64
import requests
import gradio as gr
from PIL import Image
import numpy as np
from datetime import datetime
import os

# OpenAI API Key
api_key = os.getenv("OPENAI_API_KEY")


# Function to encode the image
def encode_image(image_array):
    # Convert numpy array to an image file and encode it in base64
    img = Image.fromarray(np.uint8(image_array))
    img_buffer = os.path.join(
        "/tmp", f"temp_image_{datetime.now().strftime('%Y%m%d_%H%M%S')}.jpg"
    )
    img.save(img_buffer, format="JPEG")

    with open(img_buffer, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")


# Function to generate product description using OpenAI API
def generate_product_description(image, description_type, custom_instruction=None):
    # Encode the uploaded image
    base64_image = encode_image(image)

    headers = {"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"}

    # Set the description type or custom instruction
    description_prompts = {
        "Short Formal 📝": "Based on the image, craft a concise and compelling product description that highlights key features and benefits in a formal tone.",
        "Bullet Points 📋": "From the image, provide a detailed list of bullet points describing the product's features, benefits, and unique selling points.",
        "Amazon Optimized 🛒": "Create an Amazon-style product description based on the image, including key features, benefits, relevant keywords for SEO, and a persuasive call to action.",
        "Fashion 👗": "Generate a stylish and trendy product description for a fashion item shown in the image, emphasizing its design, materials, and how it fits into current fashion trends.",
        "Sport 🏀": "Using the image, develop an energetic and engaging product description for a sports-related item, highlighting its performance features and benefits for athletic activities.",
        "Technical Specifications ⚙️": "Extract and present the product's technical specifications from the image in a clear and concise manner, suitable for tech-savvy customers.",
        "SEO Optimized 🔍": "Write an SEO-friendly product description based on the image, incorporating relevant keywords and phrases to enhance search engine visibility.",
        "Social Media Style 📱": "Create a catchy and engaging product description suitable for social media platforms, using the image as inspiration.",
        "Luxury 💎": "Craft an elegant and sophisticated product description for the luxury item shown in the image, emphasizing exclusivity, premium quality, and craftsmanship.",
        "Kid-Friendly 🧸": "Generate a fun and appealing product description for a children's product based on the image, using language that resonates with both kids and parents.",
        "Health and Beauty 💄": "Develop a compelling product description for a health or beauty item shown in the image, highlighting its benefits, ingredients, and usage tips.",
        "Electronic Gadgets 📱": "Write a tech-focused product description for the electronic gadget in the image, focusing on its innovative features, specifications, and user advantages.",
        "Eco-Friendly 🌱": "Create an eco-conscious product description for the environmentally friendly product shown in the image, emphasizing sustainability and green benefits.",
        "Personalized Gifts 🎁": "Generate a heartfelt product description for the personalized gift in the image, highlighting customization options and sentimental value.",
        "Seasonal Promotion 🎉": "Craft a seasonal promotional product description based on the image, incorporating festive themes and limited-time offers to encourage immediate purchase.",
        "Clearance Sale 🏷️": "Write an urgent and enticing product description for the item in the image, emphasizing discounted prices and limited stock availability.",
        "Cross-Selling 🔗": "Develop a product description that not only highlights the item in the image but also suggests complementary products, encouraging additional purchases.",
        "Up-Selling ⬆️": "Create a persuasive product description that highlights premium features of the item in the image, encouraging customers to consider higher-end versions.",
        "Multi-Language Support 🌍": "Provide a product description based on the image in multiple languages to cater to a diverse customer base.",
        "User Testimonials ⭐": "Incorporate fictional user testimonials or reviews into the product description based on the image, adding credibility and social proof.",
        "Instructional 📘": "Write a product description that includes usage instructions or assembly steps for the item shown in the image.",
        "Bundle Offer 📦": "Craft a product description that promotes the item in the image as part of a bundle deal, highlighting the added value.",
        "Gift Guide Entry 🎁": "Generate a product description suitable for inclusion in a gift guide, emphasizing why the item in the image makes a great gift.",
        "Limited Edition 🚀": "Create an exclusive product description for the limited-edition item shown in the image, highlighting its uniqueness and scarcity.",
        "Subscription Model 🔄": "Write a product description that promotes the item in the image as part of a subscription service, detailing recurring benefits.",
        "B2B Focused 🏢": "Develop a professional product description suitable for business-to-business contexts, emphasizing features relevant to corporate clients.",
    }


    if description_type == "Other" and custom_instruction:
        instruction = custom_instruction
    else:
        instruction = description_prompts.get(
            description_type, "Create a product description based on the image."
        )

    # Payload with base64 encoded image as a Data URL
    payload = {
        "model": "gpt-4o-mini",
        "messages": [
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": instruction},
                    {
                        "type": "image_url",
                        "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"},
                    },
                ],
            }
        ],
        "max_tokens": 300,
    }

    response = requests.post(
        "https://api.openai.com/v1/chat/completions", headers=headers, json=payload
    )
    response_data = response.json()

    # Handle errors
    if response.status_code != 200:
        raise ValueError(
            f"OpenAI API Error: {response_data.get('error', {}).get('message', 'Unknown Error')}"
        )

    # Extract and return only the generated message content
    return response_data["choices"][0]["message"]["content"]


# Custom CSS to match WordLift style
css = """
  body {
    font-family: 'Inter', sans-serif;
    background-color: #ffffff;
    color: #333333;
  }
  #output {
    height: 500px;
    overflow: auto;
    border: 1px solid #ccc;
    padding: 20px;
    font-size: 1em; /* Reduced font size */
    border-radius: 8px;
  }
  button, select, input[type="button"], input[type="submit"] {
    background-color: #3452db; /* Correct WordLift blue */
    color: white;
    border-radius: 5px; /* Slightly smaller radius */
    padding: 10px 20px;
    border: none;
    font-size: 1em;
    cursor: pointer;
    box-shadow: none; /* Removed heavy shadow */
  }
  button:hover, select:hover, input[type="button"]:hover, input[type="submit"]:hover {
    background-color: #2c44ba; /* Slightly darker shade for hover */
  }
  .gr-box {
    border: 1px solid #e1e1e1;
    border-radius: 5px;
    box-shadow: none; /* Removed heavy shadow */
    padding: 15px; /* Reduced padding */
  }
  .gr-block {
    margin-bottom: 15px; /* Reduced margin */
  }
  .output-text {
    font-size: 1.1em; /* Reduced font size */
    color: #000000;
    padding: 10px; /* Reduced padding */
    border-radius: 5px;
    box-shadow: none; /* Removed heavy shadow */
    border: 1px solid #e1e1e1;
  }
"""


with gr.Blocks(css=css) as demo:
    gr.Markdown("<h1>WordLift Product Description Generation - [FREE]</h1>")
    with gr.Tab(label="WordLift Product Description Generation"):
        with gr.Row():
            with gr.Column():
                input_img = gr.Image(label="Input Picture", elem_classes="gr-box")
                description_type = gr.Dropdown(
                    label="Select Description Type",
                    choices=[
                        "Short Formal 📝",
                        "Bullet Points 📋",
                        "Amazon Optimized 🛒",
                        "Fashion 👗",
                        "Sport 🏀",
                        "Technical Specifications ⚙️",
                        "SEO Optimized 🔍",
                        "Social Media Style 📱",
                        "Luxury 💎",
                        "Kid-Friendly 🧸",
                        "Health and Beauty 💄",
                        "Electronic Gadgets 📱",
                        "Eco-Friendly 🌱",
                        "Personalized Gifts 🎁",
                        "Seasonal Promotion 🎉",
                        "Clearance Sale 🏷️",
                        "Cross-Selling 🔗",
                        "Up-Selling ⬆️",
                        "Multi-Language Support 🌍",
                        "User Testimonials ⭐",
                        "Instructional 📘",
                        "Bundle Offer 📦",
                        "Gift Guide Entry 🎁",
                        "Limited Edition 🚀",
                        "Subscription Model 🔄",
                        "B2B Focused 🏢",
                        "Other",
                    ],
                    value="Short Formal 📝",
                    elem_classes="gr-box"
                )
                custom_instruction = gr.Textbox(
                    label="Custom Instruction (Only for 'Other')", visible=False, elem_classes="gr-box"
                )
                submit_btn = gr.Button(value="Submit", elem_classes="gr-box")
            with gr.Column():
                output_text = gr.Markdown(label="Output Text", show_copy_button=True, elem_classes="output-text")

        # Toggle visibility of custom instruction based on selected type
        def toggle_custom_instruction(type_selection):
            return gr.update(visible=(type_selection == "Other"))

        description_type.change(
            toggle_custom_instruction,
            inputs=[description_type],
            outputs=[custom_instruction],
        )

        submit_btn.click(
            generate_product_description,
            [input_img, description_type, custom_instruction],
            [output_text],
        )

# Launch Gradio app
demo.queue(api_open=False)
demo.launch(debug=True)