Spaces:
Sleeping
Sleeping
File size: 11,723 Bytes
1fdaf11 3721393 1fdaf11 31d8f00 1fdaf11 01c4c02 1fdaf11 7c4fb72 1fdaf11 7c4fb72 1fdaf11 7c4fb72 1fdaf11 d2d2d94 7c4fb72 1fdaf11 7c4fb72 1fdaf11 7c4fb72 01c4c02 7c4fb72 1fdaf11 d2d2d94 7c4fb72 1fdaf11 3721393 1fdaf11 b6f2734 1fdaf11 b6f2734 7c4fb72 1fdaf11 b6f2734 1fdaf11 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 |
import gradio as gr
from src import argilla_utils
from src import dataset
from src import spaces
def refresh_dataset_settings_view(
columns,
question_columns,
field_columns,
split,
settings,
dataset_name,
argilla_dataset_name,
mapping,
):
"""This is a utility function to refresh the gradio applications state variables when a new dataset is loaded."""
columns = dataset.load_columns()
field_columns = dataset.get_field_columns()
question_columns = []
metadata_columns = []
split = dataset.load_split()
settings = None
dataset_name = dataset.load_dataset_name()
argilla_dataset_name = dataset.load_argilla_dataset_name()
mapping = None
return (
columns,
field_columns,
question_columns,
metadata_columns,
split,
settings,
dataset_name,
argilla_dataset_name,
mapping,
)
with gr.Blocks() as app:
##############################################
# Define the app state
##############################################
columns = gr.State(dataset.load_columns)
question_columns = gr.State(dataset.get_question_columns)
field_columns = gr.State(dataset.get_field_columns)
split = gr.State(dataset.load_split)
settings = gr.State(None)
dataset_name = gr.State(dataset.load_dataset_name)
argilla_dataset_name = gr.State(dataset.load_argilla_dataset_name)
mapping = gr.State(None)
state_variables = [
columns,
question_columns,
field_columns,
split,
settings,
dataset_name,
argilla_dataset_name,
mapping,
]
##############################################
# Define the app dataset and argilla space
##############################################
gr.Markdown(
"""# 🚂 Argilla Direct
A direct connection from a Hub dataset to an Argilla dataset.
This app allows you to create an Argilla dataset from a Hugging Face dataset.
You will need to load a dataset from the Hugging Face Hub, create an Argilla space,
define the dataset's settings, and add records to the dataset.
"""
)
gr.LoginButton()
with gr.Group():
with gr.Row():
with gr.Column():
with gr.Row():
with gr.Column():
dataset_name_input = gr.Textbox(
label="Dataset Repo ID", value=dataset.load_dataset_name()
)
with gr.Column():
split_input = gr.Dropdown(
label="Dataset Split",
choices=dataset.load_split_choices(),
allow_custom_value=True,
value=dataset.load_split(),
)
load_dataset_btn = gr.Button(value="1️⃣ Load Dataset")
with gr.Column():
argilla_space_name = gr.Textbox(
label="Argilla Space Name", value=f"{dataset_name.value}_argilla"
)
create_argilla_space_btn = gr.Button(value="2️⃣ Create Argilla Space")
argilla_space_url = gr.Textbox(
label="Argilla Space URL",
info="Create a new Argilla space or add the URL of an existing one here",
)
##############################################
# Define the Argilla dataset configuration
##############################################
gr.Markdown(
"""## 3️⃣ Define Argilla Dataset
Define the settings for the Argilla dataset including fields, questions, metadata, and vectors.
Select the columns from the Hugging Face dataset to be used as Argilla dataset attributes.
"""
)
with gr.Row():
with gr.Group():
with gr.Column():
# DATASET SETTINGS
# Argilla dataset name
argilla_dataset_name_view = gr.Textbox(
label="Dataset Name",
info="The name of the dataset in Argilla to be created or used",
value=dataset.load_argilla_dataset_name(),
)
argilla_dataset_name_view.change(
fn=lambda value: gr.update(
value=dataset.load_argilla_dataset_name()
),
inputs=[argilla_dataset_name_view],
outputs=[argilla_dataset_name_view],
)
# Field columns
with gr.Accordion(label="Fields", open=True):
field_columns_view = gr.Dropdown(
label="Column",
info="Columns to be used as fields in the Argilla dataset",
choices=dataset.load_columns(),
multiselect=True,
value=dataset.get_field_columns(),
)
field_columns_view.change(
fn=lambda value: gr.update(value=[]),
inputs=[field_columns_view],
outputs=[field_columns_view],
)
# Question columns
with gr.Accordion(label="Questions", open=True):
question_type = gr.Dropdown(
label="Type",
info="The type of question to be added to the Argilla dataset",
choices=["Text", "Label", "Rating"],
)
question_column = gr.Dropdown(
label="Column",
info="Column in the hub dataset to be used as question suggestions in the Argilla dataset",
choices=dataset.load_columns(),
allow_custom_value=True,
)
question_name = gr.Textbox(
label="Name",
info="The name of the question to be added to the Argilla dataset",
)
question_column.select(
fn=lambda value: value,
inputs=[question_column],
outputs=[question_name],
)
add_question_btn = gr.Button(value="Add Question")
question_columns_view = gr.Dropdown(
label="Question Columns",
info="Columns to be used as question suggestions in the Argilla dataset",
multiselect=True,
allow_custom_value=True,
value=[],
)
# question_columns_view.change(
# fn=lambda value: gr.update(value=[]),
# inputs=[question_columns_view],
# outputs=[question_columns_view],
# )
add_question_btn.click(
fn=lambda type, name, column, questions: questions
+ [(type, name, column)],
inputs=[
question_type,
question_name,
question_column,
question_columns_view,
],
outputs=[question_columns_view],
)
# Metadata columns
with gr.Accordion(label="Metadata", open=True):
metadata_type = gr.Dropdown(
label="Type",
info="The type of metadata to be added to the Argilla dataset",
choices=["Integer", "Float", "Term"],
)
metadata_column = gr.Dropdown(
label="Column",
info="Column in the hub dataset to be used as metadata suggestions in the Argilla dataset",
choices=dataset.load_columns(),
allow_custom_value=True,
)
metadata_name = gr.Textbox(
label="Name",
info="The name of the metadata to be added to the Argilla dataset",
)
metadata_column.select(
fn=lambda value: value,
inputs=[metadata_column],
outputs=[metadata_name],
)
add_metadata_btn = gr.Button(value="Add Metadata")
metadata_columns_view = gr.Dropdown(
label="Metadata Columns",
info="Columns to be used as metadata suggestions in the Argilla dataset",
multiselect=True,
allow_custom_value=True,
value=[],
)
add_metadata_btn.click(
fn=lambda type, name, column, metadata: metadata
+ [(type, name, column)],
inputs=[
metadata_type,
metadata_name,
metadata_column,
metadata_columns_view,
],
outputs=[metadata_columns_view],
)
n_records = gr.Slider(1, 10000, 100, label="Number of Records")
create_argilla_dataset_btn = gr.Button(value="Create Argilla Dataset")
add_records_btn = gr.Button(value="Add Records to Argilla")
delete_dataset_btn = gr.Button(value="Delete Argilla Dataset")
with gr.Column():
dataset_view = gr.Dataframe(
label="Dataset Viewer",
column_widths="20%",
headers=columns.value,
wrap=True,
)
records_view = gr.Text(label="Status", value="")
##############################################
# Define the app logic
##############################################
load_dataset_btn.click(
fn=dataset.load_dataset_from_hub,
inputs=[dataset_name_input],
outputs=[dataset_view],
).then(
fn=refresh_dataset_settings_view,
inputs=state_variables,
outputs=[
columns,
field_columns_view,
question_columns_view,
metadata_columns_view,
split_input,
settings,
dataset_name,
argilla_dataset_name_view,
mapping,
],
)
create_argilla_space_btn.click(
fn=spaces.create_argilla_space,
inputs=[argilla_space_name],
outputs=[argilla_space_url],
)
delete_dataset_btn.click(
fn=argilla_utils.delete_dataset,
inputs=[argilla_dataset_name_view],
outputs=[records_view],
)
create_argilla_dataset_btn.click(
fn=argilla_utils.define_dataset_setting,
inputs=[
argilla_dataset_name_view,
field_columns_view,
question_columns_view,
metadata_columns_view,
argilla_space_url,
# vector_columns_view,
],
outputs=[records_view, mapping],
)
add_records_btn.click(
fn=argilla_utils.add_records,
inputs=[argilla_dataset_name_view, mapping, n_records, argilla_space_url],
outputs=[records_view],
)
if __name__ == "__main__":
app.launch()
|