Spaces:
Runtime error
Runtime error
File size: 24,682 Bytes
170fd5f c4a50c6 170fd5f c4a50c6 f289ebb c4a50c6 170fd5f c4a50c6 170fd5f c4a50c6 f289ebb c4a50c6 f289ebb c4a50c6 f289ebb c4a50c6 f289ebb c4a50c6 f289ebb c4a50c6 170fd5f c4a50c6 170fd5f c4a50c6 170fd5f c4a50c6 170fd5f c4a50c6 170fd5f c4a50c6 800b8b5 c4a50c6 800b8b5 c4a50c6 170fd5f c4a50c6 170fd5f c4a50c6 784cc00 c4a50c6 784cc00 c4a50c6 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 |
#!/usr/bin/env python3
"""
MCP Server for Hugging Face Dataset and Model Search API
"""
import asyncio
import json
import logging
import os
from typing import Any, Dict, List, Optional
from urllib.parse import urlencode
import httpx
from mcp.server import Server
from mcp.server.stdio import stdio_server
from mcp.types import (
Tool,
TextContent,
CallToolResult,
CallToolRequest,
ListToolsResult,
)
# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
class HFSearchServer:
def __init__(self, base_url: str = "https://davanstrien-huggingface-datasets-search-v2.hf.space"):
self.base_url = base_url
self.client = httpx.AsyncClient(timeout=60.0)
async def close(self):
await self.client.aclose()
async def search_datasets(
self,
query: str,
k: int = 5,
sort_by: str = "similarity",
min_likes: int = 0,
min_downloads: int = 0
) -> Dict[str, Any]:
"""Search for datasets based on a text query"""
params = {
"query": query,
"k": k,
"sort_by": sort_by,
"min_likes": min_likes,
"min_downloads": min_downloads
}
response = await self.client.get(
f"{self.base_url}/search/datasets",
params=params
)
response.raise_for_status()
return response.json()
async def find_similar_datasets(
self,
dataset_id: str,
k: int = 5,
sort_by: str = "similarity",
min_likes: int = 0,
min_downloads: int = 0
) -> Dict[str, Any]:
"""Find similar datasets to a specified dataset"""
params = {
"dataset_id": dataset_id,
"k": k,
"sort_by": sort_by,
"min_likes": min_likes,
"min_downloads": min_downloads
}
response = await self.client.get(
f"{self.base_url}/similarity/datasets",
params=params
)
response.raise_for_status()
return response.json()
async def search_models(
self,
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
) -> Dict[str, Any]:
"""Search for models based on a text query"""
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 = await self.client.get(
f"{self.base_url}/search/models",
params=params
)
response.raise_for_status()
return response.json()
async def find_similar_models(
self,
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
) -> Dict[str, Any]:
"""Find similar models to a specified model"""
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 = await self.client.get(
f"{self.base_url}/similarity/models",
params=params
)
response.raise_for_status()
return response.json()
async def get_trending_models(
self,
limit: int = 10,
min_likes: int = 0,
min_downloads: int = 0,
min_param_count: int = 0,
max_param_count: Optional[int] = None
) -> Dict[str, Any]:
"""Get trending models with their summaries"""
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 = await self.client.get(
f"{self.base_url}/trending/models",
params=params
)
response.raise_for_status()
return response.json()
async def get_trending_datasets(
self,
limit: int = 10,
min_likes: int = 0,
min_downloads: int = 0
) -> Dict[str, Any]:
"""Get trending datasets with their summaries"""
params = {
"limit": limit,
"min_likes": min_likes,
"min_downloads": min_downloads
}
response = await self.client.get(
f"{self.base_url}/trending/datasets",
params=params
)
response.raise_for_status()
return response.json()
async def download_model_card(self, model_id: str) -> str:
"""Download the README card for a HuggingFace model"""
url = f"https://huggingface.co/{model_id}/raw/main/README.md"
response = await self.client.get(url)
response.raise_for_status()
return response.text
async def download_dataset_card(self, dataset_id: str) -> str:
"""Download the README card for a HuggingFace dataset"""
url = f"https://huggingface.co/datasets/{dataset_id}/raw/main/README.md"
response = await self.client.get(url)
response.raise_for_status()
return response.text
# Initialize server and API client
server = Server("hf-search")
api_client: Optional[HFSearchServer] = None
@server.list_tools()
async def list_tools() -> ListToolsResult:
"""List available tools"""
return ListToolsResult(
tools=[
Tool(
name="search_datasets",
description="Search for datasets using semantic/similarity search based on a text query",
inputSchema={
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search query text (natural language description of what you're looking for)"
},
"k": {
"type": "integer",
"description": "Number of results to return (1-100)",
"minimum": 1,
"maximum": 100,
"default": 5
},
"sort_by": {
"type": "string",
"description": "Sort method for results",
"enum": ["similarity", "likes", "downloads", "trending"],
"default": "similarity"
},
"min_likes": {
"type": "integer",
"description": "Minimum likes filter",
"minimum": 0,
"default": 0
},
"min_downloads": {
"type": "integer",
"description": "Minimum downloads filter",
"minimum": 0,
"default": 0
}
},
"required": ["query"]
}
),
Tool(
name="find_similar_datasets",
description="Find datasets similar to a specified dataset",
inputSchema={
"type": "object",
"properties": {
"dataset_id": {
"type": "string",
"description": "Dataset ID to find similar datasets for"
},
"k": {
"type": "integer",
"description": "Number of results to return (1-100)",
"minimum": 1,
"maximum": 100,
"default": 5
},
"sort_by": {
"type": "string",
"description": "Sort method for results",
"enum": ["similarity", "likes", "downloads", "trending"],
"default": "similarity"
},
"min_likes": {
"type": "integer",
"description": "Minimum likes filter",
"minimum": 0,
"default": 0
},
"min_downloads": {
"type": "integer",
"description": "Minimum downloads filter",
"minimum": 0,
"default": 0
}
},
"required": ["dataset_id"]
}
),
Tool(
name="search_models",
description="Search for models using semantic/similarity search based on a text query with optional parameter count filtering",
inputSchema={
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Search query text (natural language description of what you're looking for)"
},
"k": {
"type": "integer",
"description": "Number of results to return (1-100)",
"minimum": 1,
"maximum": 100,
"default": 5
},
"sort_by": {
"type": "string",
"description": "Sort method for results",
"enum": ["similarity", "likes", "downloads", "trending"],
"default": "similarity"
},
"min_likes": {
"type": "integer",
"description": "Minimum likes filter",
"minimum": 0,
"default": 0
},
"min_downloads": {
"type": "integer",
"description": "Minimum downloads filter",
"minimum": 0,
"default": 0
},
"min_param_count": {
"type": "integer",
"description": "Minimum parameter count (excludes models with unknown params)",
"minimum": 0,
"default": 0
},
"max_param_count": {
"type": ["integer", "null"],
"description": "Maximum parameter count (null for no limit)",
"minimum": 0,
"default": None
}
},
"required": ["query"]
}
),
Tool(
name="find_similar_models",
description="Find models similar to a specified model",
inputSchema={
"type": "object",
"properties": {
"model_id": {
"type": "string",
"description": "Model ID to find similar models for"
},
"k": {
"type": "integer",
"description": "Number of results to return (1-100)",
"minimum": 1,
"maximum": 100,
"default": 5
},
"sort_by": {
"type": "string",
"description": "Sort method for results",
"enum": ["similarity", "likes", "downloads", "trending"],
"default": "similarity"
},
"min_likes": {
"type": "integer",
"description": "Minimum likes filter",
"minimum": 0,
"default": 0
},
"min_downloads": {
"type": "integer",
"description": "Minimum downloads filter",
"minimum": 0,
"default": 0
},
"min_param_count": {
"type": "integer",
"description": "Minimum parameter count (excludes models with unknown params)",
"minimum": 0,
"default": 0
},
"max_param_count": {
"type": ["integer", "null"],
"description": "Maximum parameter count (null for no limit)",
"minimum": 0,
"default": None
}
},
"required": ["model_id"]
}
),
Tool(
name="get_trending_models",
description="Get trending models with their summaries and optional filtering",
inputSchema={
"type": "object",
"properties": {
"limit": {
"type": "integer",
"description": "Number of results to return (1-100)",
"minimum": 1,
"maximum": 100,
"default": 10
},
"min_likes": {
"type": "integer",
"description": "Minimum likes filter",
"minimum": 0,
"default": 0
},
"min_downloads": {
"type": "integer",
"description": "Minimum downloads filter",
"minimum": 0,
"default": 0
},
"min_param_count": {
"type": "integer",
"description": "Minimum parameter count (excludes models with unknown params)",
"minimum": 0,
"default": 0
},
"max_param_count": {
"type": ["integer", "null"],
"description": "Maximum parameter count (null for no limit)",
"minimum": 0,
"default": None
}
}
}
),
Tool(
name="get_trending_datasets",
description="Get trending datasets with their summaries",
inputSchema={
"type": "object",
"properties": {
"limit": {
"type": "integer",
"description": "Number of results to return (1-100)",
"minimum": 1,
"maximum": 100,
"default": 10
},
"min_likes": {
"type": "integer",
"description": "Minimum likes filter",
"minimum": 0,
"default": 0
},
"min_downloads": {
"type": "integer",
"description": "Minimum downloads filter",
"minimum": 0,
"default": 0
}
}
}
),
Tool(
name="download_model_card",
description="Download the README card for a HuggingFace model",
inputSchema={
"type": "object",
"properties": {
"model_id": {
"type": "string",
"description": "The model ID (e.g., 'username/model-name')"
}
},
"required": ["model_id"]
}
),
Tool(
name="download_dataset_card",
description="Download the README card for a HuggingFace dataset",
inputSchema={
"type": "object",
"properties": {
"dataset_id": {
"type": "string",
"description": "The dataset ID (e.g., 'username/dataset-name')"
}
},
"required": ["dataset_id"]
}
)
]
)
@server.call_tool()
async def call_tool(request: CallToolRequest) -> CallToolResult:
"""Handle tool calls"""
global api_client
if api_client is None:
# Initialize API client with base URL from environment or default
base_url = os.getenv("HF_SEARCH_API_URL", "https://davanstrien-huggingface-datasets-search-v2.hf.space")
api_client = HFSearchServer(base_url)
try:
# Parse arguments
args = request.params.arguments if hasattr(request.params, 'arguments') else {}
# Format results helper
def format_dataset_results(data: Dict[str, Any]) -> str:
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 format_model_results(data: Dict[str, Any]) -> str:
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)
# Route to appropriate method
if request.params.name == "search_datasets":
result = await api_client.search_datasets(**args)
formatted = format_dataset_results(result)
return CallToolResult(
content=[TextContent(text=formatted)],
isError=False
)
elif request.params.name == "find_similar_datasets":
result = await api_client.find_similar_datasets(**args)
formatted = format_dataset_results(result)
return CallToolResult(
content=[TextContent(text=formatted)],
isError=False
)
elif request.params.name == "search_models":
result = await api_client.search_models(**args)
formatted = format_model_results(result)
return CallToolResult(
content=[TextContent(text=formatted)],
isError=False
)
elif request.params.name == "find_similar_models":
result = await api_client.find_similar_models(**args)
formatted = format_model_results(result)
return CallToolResult(
content=[TextContent(text=formatted)],
isError=False
)
elif request.params.name == "get_trending_models":
result = await api_client.get_trending_models(**args)
formatted = format_model_results(result)
return CallToolResult(
content=[TextContent(text=formatted)],
isError=False
)
elif request.params.name == "get_trending_datasets":
result = await api_client.get_trending_datasets(**args)
formatted = format_dataset_results(result)
return CallToolResult(
content=[TextContent(text=formatted)],
isError=False
)
elif request.params.name == "download_model_card":
result = await api_client.download_model_card(**args)
return CallToolResult(
content=[TextContent(text=result)],
isError=False
)
elif request.params.name == "download_dataset_card":
result = await api_client.download_dataset_card(**args)
return CallToolResult(
content=[TextContent(text=result)],
isError=False
)
else:
return CallToolResult(
content=[TextContent(text=f"Unknown tool: {request.params.name}")],
isError=True
)
except httpx.HTTPStatusError as e:
error_msg = f"API request failed with status {e.response.status_code}: {e.response.text}"
logger.error(error_msg)
return CallToolResult(
content=[TextContent(text=error_msg)],
isError=True
)
except Exception as e:
error_msg = f"Error calling tool {request.params.name}: {str(e)}"
logger.error(error_msg, exc_info=True)
return CallToolResult(
content=[TextContent(text=error_msg)],
isError=True
)
async def main():
"""Main entry point"""
async with stdio_server() as (read_stream, write_stream):
await server.run(
read_stream,
write_stream,
server.create_initialization_options()
)
# Cleanup
if api_client:
await api_client.close()
if __name__ == "__main__":
asyncio.run(main()) |