File size: 9,587 Bytes
397f6ad
 
c7dae24
 
 
a2d1710
397f6ad
c7dae24
397f6ad
 
c7dae24
f41d654
397f6ad
 
 
a2d1710
f41d654
 
 
397f6ad
f41d654
397f6ad
 
c7dae24
f41d654
a2d1710
f41d654
397f6ad
 
c7dae24
f41d654
 
 
 
b0e56f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
397f6ad
a2d1710
b0e56f1
f41d654
 
 
 
 
 
 
397f6ad
 
 
 
a2d1710
 
 
f41d654
a2d1710
 
f41d654
 
 
a2d1710
 
f41d654
397f6ad
c7dae24
f41d654
 
 
397f6ad
c7dae24
397f6ad
 
f41d654
 
 
 
 
 
397f6ad
c7dae24
 
 
 
 
 
 
 
 
 
f41d654
21ebaa7
c7dae24
 
 
f41d654
 
 
b0e56f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f41d654
 
b0e56f1
f41d654
 
 
 
c7dae24
 
 
 
f41d654
 
 
 
 
 
 
 
 
 
c7dae24
f41d654
 
 
c7dae24
 
397f6ad
c7dae24
397f6ad
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
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 πŸ“": "Based on the image, craft a concise and compelling product description that highlights key features and benefits in a formal tone.",
        "Bullet Points πŸ“‹": "From the image, provide a detailed list of bullet points describing the product's features, benefits, and unique selling points.",
        "Amazon Optimized πŸ›’": "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 πŸ‘—": "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 πŸ€": "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 βš™οΈ": "Extract and present the product's technical specifications from the image in a clear and concise manner, suitable for tech-savvy customers.",
        "SEO Optimized πŸ”": "Write an SEO-friendly product description based on the image, incorporating relevant keywords and phrases to enhance search engine visibility.",
        "Social Media Style πŸ“±": "Create a catchy and engaging product description suitable for social media platforms, using the image as inspiration.",
        "Luxury πŸ’Ž": "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 πŸ’„": "Develop a compelling product description for a health or beauty item shown in the image, highlighting its benefits, ingredients, and usage tips.",
        "Electronic Gadgets πŸ“±": "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 πŸŽ‰": "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 πŸ”—": "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 πŸ“˜": "Write a product description that includes usage instructions or assembly steps for the item shown in the image.",
        "Bundle Offer πŸ“¦": "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 πŸš€": "Create an exclusive product description for the limited-edition item shown in the image, highlighting its uniqueness and scarcity.",
        "Subscription Model πŸ”„": "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"]


css = """
  #output {
    height: 500px;
    overflow: auto;
    border: 1px solid #ccc;
  }
"""

with gr.Blocks(css=css) as demo:
    gr.Markdown("WordLift Product Description Generation - [FREE]")
    with gr.Tab(label="WordLift Product Description Generation"):
        with gr.Row():
            with gr.Column():
                input_img = gr.Image(label="Input Picture")
                description_type = gr.Dropdown(
                    label="Select Description Type",
                    choices=[
                        "Short Formal πŸ“",
                        "Bullet Points πŸ“‹",
                        "Amazon Optimized πŸ›’",
                        "Fashion πŸ‘—",
                        "Sport πŸ€",
                        "Technical Specifications βš™οΈ",
                        "SEO Optimized πŸ”",
                        "Social Media Style πŸ“±",
                        "Luxury πŸ’Ž",
                        "Kid-Friendly 🧸",
                        "Health and Beauty πŸ’„",
                        "Electronic Gadgets πŸ“±",
                        "Eco-Friendly 🌱",
                        "Personalized Gifts 🎁",
                        "Seasonal Promotion πŸŽ‰",
                        "Clearance Sale 🏷️",
                        "Cross-Selling πŸ”—",
                        "Up-Selling ⬆️",
                        "Multi-Language Support 🌍",
                        "User Testimonials ⭐",
                        "Instructional πŸ“˜",
                        "Bundle Offer πŸ“¦",
                        "Gift Guide Entry 🎁",
                        "Limited Edition πŸš€",
                        "Subscription Model πŸ”„",
                        "B2B Focused 🏒",
                        "Other",
                    ],
                    value="Short Formal πŸ“",
                )
                custom_instruction = gr.Textbox(
                    label="Custom Instruction (Only for 'Other')", visible=False
                )
                submit_btn = gr.Button(value="Submit")
            with gr.Column():
                output_text = gr.Textbox(label="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)