Spaces:
Runtime error
Runtime error
File size: 19,670 Bytes
170fd5f 800b8b5 170fd5f 800b8b5 f289ebb 800b8b5 170fd5f 800b8b5 170fd5f f289ebb 800b8b5 b24a29b 800b8b5 b24a29b 800b8b5 f289ebb 800b8b5 b24a29b 800b8b5 b24a29b 800b8b5 f289ebb 800b8b5 170fd5f 800b8b5 170fd5f 800b8b5 170fd5f 800b8b5 170fd5f 800b8b5 170fd5f 800b8b5 170fd5f 800b8b5 170fd5f 800b8b5 170fd5f 800b8b5 784cc00 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 |
#!/usr/bin/env python3
"""
MCP Server for Hugging Face Dataset and Model Search API using Gradio
"""
import os
import logging
from typing import Optional
import gradio as gr
import httpx
# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
# Initialize HTTP client with longer timeout for MCP usage
client = httpx.Client(timeout=60.0) # Increased timeout
base_url = os.getenv("HF_SEARCH_API_URL", "https://davanstrien-huggingface-datasets-search-v2.hf.space")
def search_datasets(
query: str,
k: int = 5,
sort_by: str = "similarity",
min_likes: int = 0,
min_downloads: int = 0
) -> str:
"""
Search for datasets using semantic/similarity search based on a text query.
This uses AI-powered semantic search to find datasets whose descriptions
are semantically similar to your query, not just keyword matching.
Args:
query: Search query text (natural language description of what you're looking for)
k: Number of results to return (1-100)
sort_by: Sort method for results (similarity, likes, downloads, trending)
min_likes: Minimum likes filter
min_downloads: Minimum downloads filter
Returns:
Formatted search results with dataset IDs, summaries, and metadata
"""
try:
logger.info(f"Searching datasets: query='{query}', k={k}, sort_by='{sort_by}'")
params = {
"query": query,
"k": k,
"sort_by": sort_by,
"min_likes": min_likes,
"min_downloads": min_downloads
}
logger.info(f"Making request to: {base_url}/search/datasets")
response = client.get(f"{base_url}/search/datasets", params=params)
response.raise_for_status()
data = response.json()
logger.info(f"Successfully retrieved {len(data.get('results', []))} results")
except httpx.TimeoutException:
logger.error(f"Request timed out for query: {query}")
return "Request timed out. The search service may be slow or unavailable."
except httpx.HTTPStatusError as e:
logger.error(f"HTTP error {e.response.status_code}: {e.response.text}")
return f"Search failed with HTTP error {e.response.status_code}: {e.response.text}"
except Exception as e:
logger.error(f"Unexpected error: {str(e)}")
return f"Search failed: {str(e)}"
results = data.get("results", [])
if not results:
return "No datasets found."
output = []
for i, result in enumerate(results, 1):
output.append(f"{i}. **{result['dataset_id']}**")
output.append(f" - Summary: {result['summary']}")
output.append(f" - Similarity: {result['similarity']:.3f}")
output.append(f" - Likes: {result['likes']:,} | Downloads: {result['downloads']:,}")
output.append("")
return "\n".join(output)
def find_similar_datasets(
dataset_id: str,
k: int = 5,
sort_by: str = "similarity",
min_likes: int = 0,
min_downloads: int = 0
) -> str:
"""
Find datasets similar to a specified dataset.
Args:
dataset_id: Dataset ID to find similar datasets for
k: Number of results to return (1-100)
sort_by: Sort method for results (similarity, likes, downloads, trending)
min_likes: Minimum likes filter
min_downloads: Minimum downloads filter
Returns:
Formatted list of similar datasets with metadata
"""
params = {
"dataset_id": dataset_id,
"k": k,
"sort_by": sort_by,
"min_likes": min_likes,
"min_downloads": min_downloads
}
response = client.get(f"{base_url}/similarity/datasets", params=params)
response.raise_for_status()
data = response.json()
results = data.get("results", [])
if not results:
return "No similar datasets found."
output = []
for i, result in enumerate(results, 1):
output.append(f"{i}. **{result['dataset_id']}**")
output.append(f" - Summary: {result['summary']}")
output.append(f" - Similarity: {result['similarity']:.3f}")
output.append(f" - Likes: {result['likes']:,} | Downloads: {result['downloads']:,}")
output.append("")
return "\n".join(output)
def search_models(
query: str,
k: int = 5,
sort_by: str = "similarity",
min_likes: int = 0,
min_downloads: int = 0,
min_param_count: int = 0,
max_param_count: Optional[int] = None
) -> str:
"""
Search for models using semantic/similarity search based on a text query with optional parameter count filtering.
This uses AI-powered semantic search to find models whose descriptions
are semantically similar to your query, not just keyword matching.
Args:
query: Search query text (natural language description of what you're looking for)
k: Number of results to return (1-100)
sort_by: Sort method for results (similarity, likes, downloads, trending)
min_likes: Minimum likes filter
min_downloads: Minimum downloads filter
min_param_count: Minimum parameter count (excludes models with unknown params)
max_param_count: Maximum parameter count (None for no limit)
Returns:
Formatted search results with model IDs, summaries, and metadata
"""
params = {
"query": query,
"k": k,
"sort_by": sort_by,
"min_likes": min_likes,
"min_downloads": min_downloads,
"min_param_count": min_param_count
}
if max_param_count is not None:
params["max_param_count"] = max_param_count
response = client.get(f"{base_url}/search/models", params=params)
response.raise_for_status()
data = response.json()
results = data.get("results", [])
if not results:
return "No models found."
output = []
for i, result in enumerate(results, 1):
output.append(f"{i}. **{result['model_id']}**")
output.append(f" - Summary: {result['summary']}")
output.append(f" - Similarity: {result['similarity']:.3f}")
output.append(f" - Likes: {result['likes']:,} | Downloads: {result['downloads']:,}")
if result.get('param_count') is not None and result['param_count'] > 0:
# Format parameter count nicely
param_count = result['param_count']
if param_count >= 1_000_000_000:
param_str = f"{param_count / 1_000_000_000:.1f}B"
elif param_count >= 1_000_000:
param_str = f"{param_count / 1_000_000:.1f}M"
elif param_count >= 1_000:
param_str = f"{param_count / 1_000:.1f}K"
else:
param_str = str(param_count)
output.append(f" - Parameters: {param_str}")
output.append("")
return "\n".join(output)
def find_similar_models(
model_id: str,
k: int = 5,
sort_by: str = "similarity",
min_likes: int = 0,
min_downloads: int = 0,
min_param_count: int = 0,
max_param_count: Optional[int] = None
) -> str:
"""
Find models similar to a specified model.
Args:
model_id: Model ID to find similar models for
k: Number of results to return (1-100)
sort_by: Sort method for results (similarity, likes, downloads, trending)
min_likes: Minimum likes filter
min_downloads: Minimum downloads filter
min_param_count: Minimum parameter count (excludes models with unknown params)
max_param_count: Maximum parameter count (None for no limit)
Returns:
Formatted list of similar models with metadata
"""
params = {
"model_id": model_id,
"k": k,
"sort_by": sort_by,
"min_likes": min_likes,
"min_downloads": min_downloads,
"min_param_count": min_param_count
}
if max_param_count is not None:
params["max_param_count"] = max_param_count
response = client.get(f"{base_url}/similarity/models", params=params)
response.raise_for_status()
data = response.json()
results = data.get("results", [])
if not results:
return "No similar models found."
output = []
for i, result in enumerate(results, 1):
output.append(f"{i}. **{result['model_id']}**")
output.append(f" - Summary: {result['summary']}")
output.append(f" - Similarity: {result['similarity']:.3f}")
output.append(f" - Likes: {result['likes']:,} | Downloads: {result['downloads']:,}")
if result.get('param_count') is not None and result['param_count'] > 0:
# Format parameter count nicely
param_count = result['param_count']
if param_count >= 1_000_000_000:
param_str = f"{param_count / 1_000_000_000:.1f}B"
elif param_count >= 1_000_000:
param_str = f"{param_count / 1_000_000:.1f}M"
elif param_count >= 1_000:
param_str = f"{param_count / 1_000:.1f}K"
else:
param_str = str(param_count)
output.append(f" - Parameters: {param_str}")
output.append("")
return "\n".join(output)
def get_trending_models(
limit: int = 10,
min_likes: int = 0,
min_downloads: int = 0,
min_param_count: int = 0,
max_param_count: Optional[int] = None
) -> str:
"""
Get trending models with their summaries and optional filtering.
Args:
limit: Number of results to return (1-100)
min_likes: Minimum likes filter
min_downloads: Minimum downloads filter
min_param_count: Minimum parameter count (excludes models with unknown params)
max_param_count: Maximum parameter count (None for no limit)
Returns:
Formatted list of trending models with metadata
"""
params = {
"limit": limit,
"min_likes": min_likes,
"min_downloads": min_downloads,
"min_param_count": min_param_count
}
if max_param_count is not None:
params["max_param_count"] = max_param_count
response = client.get(f"{base_url}/trending/models", params=params)
response.raise_for_status()
data = response.json()
results = data.get("results", [])
if not results:
return "No trending models found."
output = []
for i, result in enumerate(results, 1):
output.append(f"{i}. **{result['model_id']}**")
output.append(f" - Summary: {result['summary']}")
output.append(f" - Similarity: {result['similarity']:.3f}")
output.append(f" - Likes: {result['likes']:,} | Downloads: {result['downloads']:,}")
if result.get('param_count') is not None and result['param_count'] > 0:
# Format parameter count nicely
param_count = result['param_count']
if param_count >= 1_000_000_000:
param_str = f"{param_count / 1_000_000_000:.1f}B"
elif param_count >= 1_000_000:
param_str = f"{param_count / 1_000_000:.1f}M"
elif param_count >= 1_000:
param_str = f"{param_count / 1_000:.1f}K"
else:
param_str = str(param_count)
output.append(f" - Parameters: {param_str}")
output.append("")
return "\n".join(output)
def get_trending_datasets(
limit: int = 10,
min_likes: int = 0,
min_downloads: int = 0
) -> str:
"""
Get trending datasets with their summaries.
Args:
limit: Number of results to return (1-100)
min_likes: Minimum likes filter
min_downloads: Minimum downloads filter
Returns:
Formatted list of trending datasets with metadata
"""
params = {
"limit": limit,
"min_likes": min_likes,
"min_downloads": min_downloads
}
response = client.get(f"{base_url}/trending/datasets", params=params)
response.raise_for_status()
data = response.json()
results = data.get("results", [])
if not results:
return "No trending datasets found."
output = []
for i, result in enumerate(results, 1):
output.append(f"{i}. **{result['dataset_id']}**")
output.append(f" - Summary: {result['summary']}")
output.append(f" - Similarity: {result['similarity']:.3f}")
output.append(f" - Likes: {result['likes']:,} | Downloads: {result['downloads']:,}")
output.append("")
return "\n".join(output)
def download_model_card(model_id: str) -> str:
"""
Download the README card for a HuggingFace model.
Args:
model_id: The model ID (e.g., 'username/model-name')
Returns:
The content of the model card (README.md)
"""
url = f"https://huggingface.co/{model_id}/raw/main/README.md"
response = client.get(url)
response.raise_for_status()
return response.text
def download_dataset_card(dataset_id: str) -> str:
"""
Download the README card for a HuggingFace dataset.
Args:
dataset_id: The dataset ID (e.g., 'username/dataset-name')
Returns:
The content of the dataset card (README.md)
"""
url = f"https://huggingface.co/datasets/{dataset_id}/raw/main/README.md"
response = client.get(url)
response.raise_for_status()
return response.text
# Create Gradio interface
with gr.Blocks(title="HuggingFace Search MCP Server") as demo:
gr.Markdown("# HuggingFace Search MCP Server")
gr.Markdown("This server provides semantic search capabilities for HuggingFace models and datasets.")
gr.Markdown(f"**Backend API:** {base_url}")
with gr.Tab("Search Datasets"):
gr.Interface(
fn=search_datasets,
inputs=[
gr.Textbox(label="Query", placeholder="Enter search query"),
gr.Slider(1, 100, value=5, step=1, label="Number of results"),
gr.Dropdown(["similarity", "likes", "downloads", "trending"], value="similarity", label="Sort by"),
gr.Number(value=0, label="Minimum likes"),
gr.Number(value=0, label="Minimum downloads")
],
outputs=gr.Markdown(label="Results"),
title="Search Datasets",
description="Search for datasets based on a text query"
)
with gr.Tab("Find Similar Datasets"):
gr.Interface(
fn=find_similar_datasets,
inputs=[
gr.Textbox(label="Dataset ID", placeholder="username/dataset-name"),
gr.Slider(1, 100, value=5, step=1, label="Number of results"),
gr.Dropdown(["similarity", "likes", "downloads", "trending"], value="similarity", label="Sort by"),
gr.Number(value=0, label="Minimum likes"),
gr.Number(value=0, label="Minimum downloads")
],
outputs=gr.Markdown(label="Results"),
title="Find Similar Datasets",
description="Find datasets similar to a specified dataset"
)
with gr.Tab("Search Models"):
gr.Interface(
fn=search_models,
inputs=[
gr.Textbox(label="Query", placeholder="Enter search query"),
gr.Slider(1, 100, value=5, step=1, label="Number of results"),
gr.Dropdown(["similarity", "likes", "downloads", "trending"], value="similarity", label="Sort by"),
gr.Number(value=0, label="Minimum likes"),
gr.Number(value=0, label="Minimum downloads"),
gr.Number(value=0, label="Minimum parameter count"),
gr.Number(value=None, label="Maximum parameter count (leave empty for no limit)")
],
outputs=gr.Markdown(label="Results"),
title="Search Models",
description="Search for models based on a text query with optional parameter count filtering"
)
with gr.Tab("Find Similar Models"):
gr.Interface(
fn=find_similar_models,
inputs=[
gr.Textbox(label="Model ID", placeholder="username/model-name"),
gr.Slider(1, 100, value=5, step=1, label="Number of results"),
gr.Dropdown(["similarity", "likes", "downloads", "trending"], value="similarity", label="Sort by"),
gr.Number(value=0, label="Minimum likes"),
gr.Number(value=0, label="Minimum downloads"),
gr.Number(value=0, label="Minimum parameter count"),
gr.Number(value=None, label="Maximum parameter count (leave empty for no limit)")
],
outputs=gr.Markdown(label="Results"),
title="Find Similar Models",
description="Find models similar to a specified model"
)
with gr.Tab("Trending Models"):
gr.Interface(
fn=get_trending_models,
inputs=[
gr.Slider(1, 100, value=10, step=1, label="Number of results"),
gr.Number(value=0, label="Minimum likes"),
gr.Number(value=0, label="Minimum downloads"),
gr.Number(value=0, label="Minimum parameter count"),
gr.Number(value=None, label="Maximum parameter count (leave empty for no limit)")
],
outputs=gr.Markdown(label="Results"),
title="Get Trending Models",
description="Get trending models with their summaries and optional filtering"
)
with gr.Tab("Trending Datasets"):
gr.Interface(
fn=get_trending_datasets,
inputs=[
gr.Slider(1, 100, value=10, step=1, label="Number of results"),
gr.Number(value=0, label="Minimum likes"),
gr.Number(value=0, label="Minimum downloads")
],
outputs=gr.Markdown(label="Results"),
title="Get Trending Datasets",
description="Get trending datasets with their summaries"
)
with gr.Tab("Download Model Card"):
gr.Interface(
fn=download_model_card,
inputs=gr.Textbox(label="Model ID", placeholder="username/model-name"),
outputs=gr.Textbox(label="Model Card Content", lines=20),
title="Download Model Card",
description="Download the README card for a HuggingFace model"
)
with gr.Tab("Download Dataset Card"):
gr.Interface(
fn=download_dataset_card,
inputs=gr.Textbox(label="Dataset ID", placeholder="username/dataset-name"),
outputs=gr.Textbox(label="Dataset Card Content", lines=20),
title="Download Dataset Card",
description="Download the README card for a HuggingFace dataset"
)
if __name__ == "__main__":
# Launch with MCP server enabled
# Try environment variable approach as workaround for initialization race condition
import os
os.environ["GRADIO_MCP_SERVER"] = "true"
try:
# First try with environment variable only
demo.launch(
server_name="0.0.0.0",
server_port=7860,
show_error=True
)
except Exception as e:
logger.error(f"Environment variable approach failed: {e}")
# Fallback to parameter approach
demo.launch(
mcp_server=True,
server_name="0.0.0.0",
server_port=7860,
show_error=True
) |