Spaces:
Sleeping
Sleeping
File size: 7,630 Bytes
db17eb5 849fb14 db17eb5 ffa80b4 849fb14 db17eb5 849fb14 ffa80b4 849fb14 db17eb5 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 |
"""Gradio web interface for synthetic data generation."""
import logging
import gradio as gr
from src.pipeline import DatasetPipeline
from src.constants import PROJECT_NAME, VERSION
# Set up logger
logger = logging.getLogger(__name__)
logging.basicConfig(
level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
)
pipeline = DatasetPipeline()
PROJECT_NAME_CAP = PROJECT_NAME.capitalize()
REPO_URL = f"https://github.com/lisekarimi/{PROJECT_NAME}"
def update_output_format(dataset_type):
"""Update output format choices based on selected dataset type."""
if dataset_type in ["Tabular", "Time-series"]:
return gr.update(choices=["JSON", "csv", "Parquet"], value="JSON")
elif dataset_type == "Text":
return gr.update(choices=["JSON", "Markdown"], value="JSON")
def build_ui(css_path="assets/styles.css"):
"""Build and return the complete Gradio user interface with error handling."""
# Try to load CSS file with error handling
try:
with open(css_path, encoding="utf-8") as f:
css = f.read()
except Exception as e:
css = ""
logger.warning("⚠️ Failed to load CSS: %s", e)
# Building the UI with error handling
try:
with gr.Blocks(css=css, title=f"🧬{PROJECT_NAME_CAP}") as ui:
with gr.Column(elem_id="app-container"):
gr.Markdown(f"<h1 id='app-title'>🏷️ {PROJECT_NAME_CAP} </h1>")
gr.Markdown(
"<h2 id='app-subtitle'>AI-Powered Synthetic Dataset Generator</h2>"
)
# Fix the f-string in HTML
intro_html = f"""
<div id="intro-text">
<p>With {PROJECT_NAME_CAP}, easily generate
<strong>diverse datasets</strong>
for testing, development, and AI training.</p>
<h4>🎯 How It Works:</h4>
<p>1️⃣ Define your business problem.</p>
<p>2️⃣ Select dataset type, format, model, and samples.</p>
<p>3️⃣ Download your synthetic dataset!</p>
</div>
"""
gr.HTML(intro_html)
learn_more_html = """
<div id="learn-more-button">
<a href="https://datagen.lisekarimi.com/docs"
class="button-link">Documentation</a>
</div>
"""
gr.HTML(learn_more_html)
examples_md = """
<p><strong>🧠 Need inspiration?</strong> Try these examples:</p>
<ul>
<li>Movie summaries for genre classification.</li>
<li>Customer chats with dialogue and sentiment labels.</li>
<li>Stock prices with date, ticker, open, close, volume.</li>
</ul>
"""
gr.Markdown(examples_md)
gr.Markdown("<p><strong>Start generating now!</strong> 🗂️✨</p>")
with gr.Group(elem_id="input-container"):
business_problem = gr.Textbox(
placeholder=(
"Describe the dataset you want "
"(e.g., Job postings, Customer reviews)"
),
lines=2,
label="📌 Business Problem",
elem_classes=["label-box"],
elem_id="business-problem-box",
)
with gr.Row(elem_classes="column-gap"):
with gr.Column(scale=1):
dataset_type = gr.Dropdown(
["Tabular", "Time-series", "Text"],
value="Tabular",
label="📊 Dataset Type",
elem_classes=["label-box"],
elem_id="custom-dropdown",
)
with gr.Column(scale=1):
output_format = gr.Dropdown(
choices=["JSON", "csv", "Parquet"],
value="JSON",
label="📁 Output Format",
elem_classes=["label-box"],
elem_id="custom-dropdown",
)
# Bind the update function to the dataset type dropdown
dataset_type.change(
update_output_format,
inputs=[dataset_type],
outputs=[output_format],
)
with gr.Row(elem_classes="row-spacer column-gap"):
with gr.Column(scale=1):
model = gr.Dropdown(
["GPT", "Claude"],
value="GPT",
label="🤖 Model",
elem_classes=["label-box"],
elem_id="custom-dropdown",
)
with gr.Column(scale=1):
num_samples = gr.Slider(
minimum=10,
maximum=1000,
value=10,
step=1,
interactive=True,
label="🔢 Number of Samples",
elem_classes=["label-box"],
)
# Hidden file component for dataset download
file_download = gr.File(
visible=False, elem_id="download-box", label=None
)
# Component to display status messages
status_message = gr.Markdown("", label="Status")
# Button to trigger dataset generation
run_btn = gr.Button("Create a dataset", elem_id="run-btn")
run_btn.click(
pipeline.generate,
inputs=[
business_problem,
dataset_type,
output_format,
num_samples,
model,
],
outputs=[file_download, run_btn, status_message],
)
# Bottom: version info
gr.Markdown(
f"""
<p class="version-banner">
🔖 <strong>
<a href="{REPO_URL}/blob/main/CHANGELOG.md"
target="_blank">Version {VERSION}</a>
</strong>
</p>
"""
)
# Floating chat button
gr.HTML(
"""
<a href="https://datagen.lisekarimi.com/docs" class="floating-chat-btn"
target="_blank">
💬 Chat with AI Assistant
</a>
"""
)
return ui
except Exception as e:
logger.error("❌ Error building UI: %s", e)
# Return a minimal error UI
with gr.Blocks() as error_ui:
gr.Markdown("# Error Loading Application")
gr.Markdown(f"An error occurred: {str(e)}")
return error_ui
|