Spaces:
Running
Running
File size: 38,647 Bytes
23df63d |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# KGLLMの動作例を作成する"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting transformers\n",
" Using cached transformers-4.48.1-py3-none-any.whl.metadata (44 kB)\n",
"Collecting torch\n",
" Using cached torch-2.5.1-cp310-cp310-manylinux1_x86_64.whl.metadata (28 kB)\n",
"Collecting accelerate\n",
" Using cached accelerate-1.3.0-py3-none-any.whl.metadata (19 kB)\n",
"Collecting filelock (from transformers)\n",
" Using cached filelock-3.17.0-py3-none-any.whl.metadata (2.9 kB)\n",
"Collecting huggingface-hub<1.0,>=0.24.0 (from transformers)\n",
" Using cached huggingface_hub-0.27.1-py3-none-any.whl.metadata (13 kB)\n",
"Collecting numpy>=1.17 (from transformers)\n",
" Using cached numpy-2.2.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (62 kB)\n",
"Requirement already satisfied: packaging>=20.0 in /home/mnktsts/repo/Fujitsu-LLM-KG/README/.venv/lib/python3.10/site-packages (from transformers) (24.2)\n",
"Collecting pyyaml>=5.1 (from transformers)\n",
" Using cached PyYAML-6.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.1 kB)\n",
"Collecting regex!=2019.12.17 (from transformers)\n",
" Using cached regex-2024.11.6-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (40 kB)\n",
"Collecting requests (from transformers)\n",
" Using cached requests-2.32.3-py3-none-any.whl.metadata (4.6 kB)\n",
"Collecting tokenizers<0.22,>=0.21 (from transformers)\n",
" Using cached tokenizers-0.21.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n",
"Collecting safetensors>=0.4.1 (from transformers)\n",
" Using cached safetensors-0.5.2-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.8 kB)\n",
"Collecting tqdm>=4.27 (from transformers)\n",
" Using cached tqdm-4.67.1-py3-none-any.whl.metadata (57 kB)\n",
"Requirement already satisfied: typing-extensions>=4.8.0 in /home/mnktsts/repo/Fujitsu-LLM-KG/README/.venv/lib/python3.10/site-packages (from torch) (4.12.2)\n",
"Collecting networkx (from torch)\n",
" Using cached networkx-3.4.2-py3-none-any.whl.metadata (6.3 kB)\n",
"Collecting jinja2 (from torch)\n",
" Using cached jinja2-3.1.5-py3-none-any.whl.metadata (2.6 kB)\n",
"Collecting fsspec (from torch)\n",
" Using cached fsspec-2024.12.0-py3-none-any.whl.metadata (11 kB)\n",
"Collecting nvidia-cuda-nvrtc-cu12==12.4.127 (from torch)\n",
" Using cached nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cuda-runtime-cu12==12.4.127 (from torch)\n",
" Using cached nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cuda-cupti-cu12==12.4.127 (from torch)\n",
" Using cached nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Collecting nvidia-cudnn-cu12==9.1.0.70 (from torch)\n",
" Using cached nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Collecting nvidia-cublas-cu12==12.4.5.8 (from torch)\n",
" Using cached nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cufft-cu12==11.2.1.3 (from torch)\n",
" Using cached nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-curand-cu12==10.3.5.147 (from torch)\n",
" Using cached nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cusolver-cu12==11.6.1.9 (from torch)\n",
" Using cached nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Collecting nvidia-cusparse-cu12==12.3.1.170 (from torch)\n",
" Using cached nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Collecting nvidia-nccl-cu12==2.21.5 (from torch)\n",
" Using cached nvidia_nccl_cu12-2.21.5-py3-none-manylinux2014_x86_64.whl.metadata (1.8 kB)\n",
"Collecting nvidia-nvtx-cu12==12.4.127 (from torch)\n",
" Using cached nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.7 kB)\n",
"Collecting nvidia-nvjitlink-cu12==12.4.127 (from torch)\n",
" Using cached nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting triton==3.1.0 (from torch)\n",
" Using cached triton-3.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.3 kB)\n",
"Collecting sympy==1.13.1 (from torch)\n",
" Using cached sympy-1.13.1-py3-none-any.whl.metadata (12 kB)\n",
"Collecting mpmath<1.4,>=1.1.0 (from sympy==1.13.1->torch)\n",
" Using cached mpmath-1.3.0-py3-none-any.whl.metadata (8.6 kB)\n",
"Requirement already satisfied: psutil in /home/mnktsts/repo/Fujitsu-LLM-KG/README/.venv/lib/python3.10/site-packages (from accelerate) (6.1.1)\n",
"Collecting MarkupSafe>=2.0 (from jinja2->torch)\n",
" Using cached MarkupSafe-3.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.0 kB)\n",
"Collecting charset-normalizer<4,>=2 (from requests->transformers)\n",
" Using cached charset_normalizer-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (35 kB)\n",
"Collecting idna<4,>=2.5 (from requests->transformers)\n",
" Using cached idna-3.10-py3-none-any.whl.metadata (10 kB)\n",
"Collecting urllib3<3,>=1.21.1 (from requests->transformers)\n",
" Using cached urllib3-2.3.0-py3-none-any.whl.metadata (6.5 kB)\n",
"Collecting certifi>=2017.4.17 (from requests->transformers)\n",
" Using cached certifi-2024.12.14-py3-none-any.whl.metadata (2.3 kB)\n",
"Using cached transformers-4.48.1-py3-none-any.whl (9.7 MB)\n",
"Using cached torch-2.5.1-cp310-cp310-manylinux1_x86_64.whl (906.4 MB)\n",
"Using cached nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl (363.4 MB)\n",
"Using cached nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (13.8 MB)\n",
"Using cached nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (24.6 MB)\n",
"Using cached nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (883 kB)\n",
"Using cached nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl (664.8 MB)\n",
"Using cached nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl (211.5 MB)\n",
"Using cached nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl (56.3 MB)\n",
"Using cached nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl (127.9 MB)\n",
"Using cached nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl (207.5 MB)\n",
"Using cached nvidia_nccl_cu12-2.21.5-py3-none-manylinux2014_x86_64.whl (188.7 MB)\n",
"Using cached nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n",
"Using cached nvidia_nvtx_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (99 kB)\n",
"Using cached sympy-1.13.1-py3-none-any.whl (6.2 MB)\n",
"Using cached triton-3.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (209.5 MB)\n",
"Using cached accelerate-1.3.0-py3-none-any.whl (336 kB)\n",
"Using cached huggingface_hub-0.27.1-py3-none-any.whl (450 kB)\n",
"Using cached fsspec-2024.12.0-py3-none-any.whl (183 kB)\n",
"Using cached numpy-2.2.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (16.4 MB)\n",
"Using cached PyYAML-6.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (751 kB)\n",
"Using cached regex-2024.11.6-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (781 kB)\n",
"Using cached safetensors-0.5.2-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (461 kB)\n",
"Using cached tokenizers-0.21.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.0 MB)\n",
"Using cached tqdm-4.67.1-py3-none-any.whl (78 kB)\n",
"Using cached filelock-3.17.0-py3-none-any.whl (16 kB)\n",
"Using cached jinja2-3.1.5-py3-none-any.whl (134 kB)\n",
"Using cached networkx-3.4.2-py3-none-any.whl (1.7 MB)\n",
"Using cached requests-2.32.3-py3-none-any.whl (64 kB)\n",
"Using cached certifi-2024.12.14-py3-none-any.whl (164 kB)\n",
"Using cached charset_normalizer-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (146 kB)\n",
"Using cached idna-3.10-py3-none-any.whl (70 kB)\n",
"Using cached MarkupSafe-3.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (20 kB)\n",
"Using cached mpmath-1.3.0-py3-none-any.whl (536 kB)\n",
"Using cached urllib3-2.3.0-py3-none-any.whl (128 kB)\n",
"Installing collected packages: mpmath, urllib3, tqdm, sympy, safetensors, regex, pyyaml, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, numpy, networkx, MarkupSafe, idna, fsspec, filelock, charset-normalizer, certifi, triton, requests, nvidia-cusparse-cu12, nvidia-cudnn-cu12, jinja2, nvidia-cusolver-cu12, huggingface-hub, torch, tokenizers, transformers, accelerate\n",
"Successfully installed MarkupSafe-3.0.2 accelerate-1.3.0 certifi-2024.12.14 charset-normalizer-3.4.1 filelock-3.17.0 fsspec-2024.12.0 huggingface-hub-0.27.1 idna-3.10 jinja2-3.1.5 mpmath-1.3.0 networkx-3.4.2 numpy-2.2.2 nvidia-cublas-cu12-12.4.5.8 nvidia-cuda-cupti-cu12-12.4.127 nvidia-cuda-nvrtc-cu12-12.4.127 nvidia-cuda-runtime-cu12-12.4.127 nvidia-cudnn-cu12-9.1.0.70 nvidia-cufft-cu12-11.2.1.3 nvidia-curand-cu12-10.3.5.147 nvidia-cusolver-cu12-11.6.1.9 nvidia-cusparse-cu12-12.3.1.170 nvidia-nccl-cu12-2.21.5 nvidia-nvjitlink-cu12-12.4.127 nvidia-nvtx-cu12-12.4.127 pyyaml-6.0.2 regex-2024.11.6 requests-2.32.3 safetensors-0.5.2 sympy-1.13.1 tokenizers-0.21.0 torch-2.5.1 tqdm-4.67.1 transformers-4.48.1 triton-3.1.0 urllib3-2.3.0\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"pip install transformers torch accelerate"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/mnktsts/repo/Fujitsu-LLM-KG/README/.venv/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"source": [
"from kgllm_utils import Fujitsu_LLM_KG, extract_turtle, extract_answer"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 共通事前学習済みLLM"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading checkpoint shards: 100%|██████████| 39/39 [00:35<00:00, 1.11it/s]\n"
]
}
],
"source": [
"kgllm = Fujitsu_LLM_KG(\"../../Fujitsu-LLM-KG-8x7B_cpt\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"## Knowledge Graph\n",
"```turtle\n",
"#@rationale: 宗像聡は富士通に2010年から勤めています。\n",
"<#宗像聡>\n",
" rel:employer [\n",
" rdf:object <#富士通>;\n",
" rel:start_time <#2010>\n",
" ].\n",
"\n",
"#@rationale: 彼はFujitsu-LLM-KG-8x7B_cptを開発しました。\n",
"<#宗像聡>\n",
" rel:notable_work <#Fujitsu-LLM-KG-8x7B_cpt>.\n",
"```\n"
]
}
],
"source": [
"prompt = \"\"\"\n",
"[INST]\n",
"Generate \"Knowledge Graph\" in RDF Turtle format based on the given \"Source\".\n",
"\n",
"## Source\n",
"```txt\n",
"宗像聡は富士通に2010年から勤めています。\n",
"彼はFujitsu-LLM-KG-8x7B_cptを開発しました。\n",
"```\n",
"\n",
"## Strategy\n",
"Extract all verifiable facts in \"Source\" as knowledge triples.\n",
"[/INST]\n",
"\"\"\".strip()\n",
"\n",
"generated = kgllm.generate(prompt)\n",
"print(generated)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"## Text\n",
"```txt\n",
"Satoshi Munakata, who started working for Fujitsu in 2010, is the author of the notable work Fujitsu-LLM-KG-8x7B cpt.\n",
"```\n"
]
}
],
"source": [
"prompt = \"\"\"\n",
"[INST]\n",
"Generate \"Text\" to explain the given knowledge triples in \"Source\".\n",
"\n",
"## Source\n",
"```turtle\n",
"<#Satoshi Munakata>\n",
" rel:notable_work <#Fujitsu-LLM-KG-8x7B_cpt>;\n",
" rel:employer [\n",
" rdf:object <#Fujitsu>;\n",
" rel:start_time <#2010>\n",
" ].\n",
"```\n",
"\n",
"## Strategy\n",
"Explain the knowledge triples in \"Source\" without omission, but concisely and fluently.\n",
"[/INST]\n",
"\"\"\".strip()\n",
"\n",
"generated = kgllm.generate(prompt)\n",
"print(generated)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## ナレッジグラフ生成LLM 日本語版"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading checkpoint shards: 100%|██████████| 39/39 [00:27<00:00, 1.41it/s]\n"
]
}
],
"source": [
"kgllm = Fujitsu_LLM_KG(\"../../Fujitsu-LLM-KG-8x7B_inst-gen_ja\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ## Knowledge Graph\n",
"```turtle\n",
"#@rationale: s0. <#マリー・テレーズ・ドートリッシュ:Person[0]>(<#1638 年 9 月 10 日:Date[6]>日-<#1683 年 7月 30 日:Date[7]>)は、<#フランス:Location[1]>王<#ルイ 14 世:Person[2]>の王妃。\n",
"\n",
"<#ルイ 14 世:Person[2]>\n",
" rel:CountryOfCitizenship <#フランス:Location[1]>.\n",
"\n",
"#@rationale: s1. 父は<#スペイン:Location[3]>王<#フェリペ 4 世:Person[4]>、母は<#フランス:Location[1]>王<#アンリ 4 世:Person[8]>と<#マリー・ド・メディシス:Person[9]>の娘<#イサベル・デ・ボルボン:Person[5]>。\n",
"\n",
"<#フェリペ 4 世:Person[4]>\n",
" rel:CountryOfCitizenship <#スペイン:Location[3]>.\n",
"\n",
"<#アンリ 4 世:Person[8]>\n",
" rel:CountryOfCitizenship <#フランス:Location[1]>.\n",
"\n",
"<#イサベル・デ・ボルボン:Person[5]>\n",
" rel:CountryOfCitizenship <#フランス:Location[1]>.\n",
"\n",
"#@rationale: s2. <#スペイン:Location[3]>名は<#マリア・テレサ:Person[0]>。\n",
"\n",
"#@rationale: s3. <#ルイ 14 世:Person[2]>の父<#ルイ 13 世:Person[10]>は<#イサベル:Person[5]>の兄、母<#アンヌ・ドートリッシュ:Person[11]>は<#フェリペ 4 世:Person[4]>の姉であり、<#ルイ 14世:Person[2]>と<#マリー・テレーズ:Person[0]>とは父方・母方双方で従兄妹に当たる。\n",
"\n",
"<#ルイ 13 世:Person[10]>\n",
" rel:CountryOfCitizenship <#フランス:Location[1]>.\n",
"\n",
"<#アンヌ・ドートリッシュ:Person[11]>\n",
" rel:CountryOfCitizenship <#フランス:Location[1]>.\n",
"\n",
"#@rationale: s4. <#神聖ローマ:Location[12]>皇帝<#レオポルト 1 世:Person[13]>の皇后<#マルガリータ・テレサ:Person[14]>は異母妹、<#スペイン:Location[3]>・<#ハプスブルク家:Organization[15]>最後の王<#カルロス 2世:Person[16]>は異母弟である。\n",
"\n",
"<#カルロス 2世:Person[16]>\n",
" rel:CountryOfCitizenship <#スペイン:Location[3]>.\n",
"```\n"
]
}
],
"source": [
"\n",
"prompt = \"\"\"\n",
"[INST]\n",
"Generate \"Knowledge Graph\" in RDF Turtle format based on the given \"Source\".\n",
"\n",
"## Source\n",
"```txt\n",
"s0. <#マリー・テレーズ・ドートリッシュ:Person[0]>(<#1638 年 9 月 10 日:Date[6]>日-<#1683 年 7月 30 日:Date[7]>)は、<#フランス:Location[1]>王<#ルイ 14 世:Person[2]>の王妃。\n",
"s1. 父は<#スペイン:Location[3]>王<#フェリペ 4 世:Person[4]>、母は<#フランス:Location[1]>王<#アンリ 4 世:Person[8]>と<#マリー・ド・メディシス:Person[9]>の娘<#イサベル・デ・ボルボン:Person[5]>。\n",
"s2. <#スペイン:Location[3]>名は<#マリア・テレサ:Person[0]>。\n",
"s3. <#ルイ 14 世:Person[2]>の父<#ルイ 13 世:Person[10]>は<#イサベル:Person[5]>の兄、母<#アンヌ・ドートリッシュ:Person[11]>は<#フェリペ 4 世:Person[4]>の姉であり、<#ルイ 14世:Person[2]>と<#マリー・テレーズ:Person[0]>とは父方・母方双方で従兄妹に当たる。\n",
"s4. <#神聖ローマ:Location[12]>皇帝<#レオポルト 1 世:Person[13]>の皇后<#マルガリータ・テレサ:Person[14]>は異母妹、<#スペイン:Location[3]>・<#ハプスブルク家:Organization[15]>最後の王<#カルロス 2世:Person[16]>は異母弟である。\n",
"```\n",
"## Strategy\n",
"Extract all verifiable facts about relation \"CountryOfCitizenship\" in \"Source\" as knowledge triples.\n",
"* Don't speculate, extract only the facts as stated in \"Source\" **WITHOUT OMMISION**. \n",
"The relation \"CountryOfCitizenship\" (P27) means \"the object is a country that recognizes the subject as its citizen\".\n",
"* The existence of a relation is restricted by the type of subject and object. You must select subjects and objects of triples from the bracketed eigenexpressions, such as \"<#name:type[id]>\", without modification.\n",
"[/INST]\n",
" \"\"\".strip()\n",
"\n",
"generated = kgllm.generate(prompt)\n",
"print(generated)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## ナレッジグラフ生成LLM 英語版"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading checkpoint shards: 100%|██████████| 39/39 [00:27<00:00, 1.42it/s]\n"
]
}
],
"source": [
"kgllm = Fujitsu_LLM_KG(\"../../Fujitsu-LLM-KG-8x7B_inst-gen_en\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ## Knowledge Graph\n",
"```turtle\n",
"#@rationale: s0. <#John Gregory Myre:Person[0]> is an <#American:Location[1]> journalist and <#NPR:Organization[2]>'s digital editor for international news.\n",
"\n",
"<#John Gregory Myre:Person[0]>\n",
" rel:country_of_citizenship <#American:Location[1]>.\n",
"\n",
"#@rationale: s1. Previously, he was a foreign correspondent for The <#Associated Press:Organization[3]> and The <#New York Times:Organization[4]> for <#20 years:Time[5]>.\n",
"\n",
"#@rationale: s2. He reported from <#Jerusalem:Location[6]> from <#2003:Time[7]> to <#2007:Time[8]> for The <#New York Times:Organization[4]>.\n",
"\n",
"#@rationale: s3. With the <#AP:Organization[3]>, <#Myre:Person[0]> was based in <#Jerusalem:Location[6]>, <#Moscow:Location[9]>, <#Nicosia:Location[10]>, <#Islamabad:Location[11]> and <#Johannesburg:Location[12]>.\n",
"\n",
"#@rationale: s4. He covered many major international stories, including <#Nelson Mandela:Person[13]>'s release from prison in <#1990:Time[14]>, the <#Gulf War:Miscellaneous[15]> of <#1991:Time[16]>, the rise of the <#Taliban:Organization[17]>, the early days of <#Vladimir Putin:Person[18]> as <#Russia:Location[19]>'s leader, the <#Israeli:Location[20]>-<#Palestinian:Location[21]> fighting that erupted in <#2000:Time[22]> and the <#U.S.:Location[23]> war in <#Afghanistan:Location[24]>.\n",
"\n",
"<#Vladimir Putin:Person[18]>\n",
" rel:country_of_citizenship <#Russia:Location[19]>.\n",
"\n",
"#@rationale: s5. He is also a scholar at the <#Middle East Institute:Organization[25]> in <#Washington:Location[26]>.\n",
"```\n"
]
}
],
"source": [
"prompt = \"\"\"\n",
"[INST]\n",
"Generate \"Knowledge Graph\" in RDF Turtle format based on the given \"Source\".\n",
" \n",
"## Source\n",
"```txt\n",
"s0. <#John Gregory Myre:Person[0]> is an <#American:Location[1]> journalist and <#NPR:Organization[2]>'s digital editor for international news.\n",
"s1. Previously, he was a foreign correspondent for The <#Associated Press:Organization[3]> and The <#New York Times:Organization[4]> for <#20 years:Time[5]>.\n",
"s2. He reported from <#Jerusalem:Location[6]> from <#2003:Time[7]> to <#2007:Time[8]> for The <#New York Times:Organization[4]>.\n",
"s3. With the <#AP:Organization[3]>, <#Myre:Person[0]> was based in <#Jerusalem:Location[6]>, <#Moscow:Location[9]>, <#Nicosia:Location[10]>, <#Islamabad:Location[11]> and <#Johannesburg:Location[12]>.\n",
"s4. He covered many major international stories, including <#Nelson Mandela:Person[13]>'s release from prison in <#1990:Time[14]>, the <#Gulf War:Miscellaneous[15]> of <#1991:Time[16]>, the rise of the <#Taliban:Organization[17]>, the early days of <#Vladimir Putin:Person[18]> as <#Russia:Location[19]>'s leader, the <#Israeli:Location[20]>-<#Palestinian:Location[21]> fighting that erupted in <#2000:Time[22]> and the <#U.S.:Location[23]> war in <#Afghanistan:Location[24]>.\n",
"s5. He is also a scholar at the <#Middle East Institute:Organization[25]> in <#Washington:Location[26]>.\n",
" ```\n",
" \n",
"## Strategy\n",
"Extract all verifiable facts about relation \"country_of_citizenship\" in \"Source\" as knowledge triples.\n",
"* Don't speculate, extract only the facts as stated in \"Source\" **WITHOUT OMMISION**.\n",
"The relation \"country_of_citizenship\" (P27) means \"the object is a country that recognizes the subject as its citizen\".\n",
"* The existence of a relation is restricted by the type of subject and object.\n",
"You must select subjects and objects of triples from the bracketed eigenexpressions, such as \"<#name:type[id]>\", without modification.\n",
"[/INST]\n",
"\"\"\".strip()\n",
"\n",
"generated = kgllm.generate(prompt)\n",
"print(generated)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## ナレッジグラフ推論LLM ver.2"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading checkpoint shards: 100%|██████████| 39/39 [00:50<00:00, 1.31s/it]\n"
]
}
],
"source": [
"kgllm = Fujitsu_LLM_KG(\"../../Fujitsu-LLM-KG-8x7B_inst-infer_v2\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ## Knowledge Graph\n",
"```turtle\n",
"<#お正月>\n",
" rel:has_duration <?duration_of_new_year>.\n",
"<#お盆>\n",
" rel:has_duration <?duration_of_obon>.\n",
"<#Answer>\n",
" rel:is <#お正月>;\n",
" rel:when [\n",
" <?duration_of_new_year>\n",
" rel:greater_than <?duration_of_obon>.\n",
" ];\n",
" rel:else <#お盆>.\n",
"```\n"
]
}
],
"source": [
"question = \"お正月とお盆とでは、どちらがより長期間の休日ですか?\"\n",
"\n",
"prompt_schema = f\"\"\"\n",
"[INST]\n",
"Generate \"Knowledge Graph\" in RDF Turtle format based on the given \"Source\".\n",
"\n",
"## Source\n",
"```txt\n",
"{question}\n",
"```\n",
" \n",
"## Strategy\n",
"Extract graph schema needed to answer the question in above \"Source\" as knowledge triples without omission.\n",
"[/INST]\n",
"\"\"\".strip()\n",
"\n",
"generated_schema = kgllm.generate(prompt_schema)\n",
"print(generated_schema)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ## Knowledge Graph\n",
"```turtle\n",
"<#お正月>\n",
" #@rationale: Title: 第２０条「休日」 - ③年末年始（１月１日～１月３日）\n",
" rel:has_duration <#3>;\n",
"<#お盆>\n",
" #@rationale: Title: 第２０条「休日」 - ④夏季休日（８月１３日～８月１６日）\n",
" rel:has_duration <#4>.\n",
"<#Answer>\n",
" rel:is <#お正月>;\n",
" rel:when [\n",
" <#3>\n",
" rel:greater_than <#4>.\n",
" ];\n",
" rel:else <#お盆>.\n",
"```\n"
]
}
],
"source": [
"prompt_kg = f\"\"\"\n",
"[INST]\n",
"Generate \"Knowledge Graph\" in RDF Turtle format based on the given \"Source\".\n",
"\n",
"## Source\n",
"```txt\n",
"Title: 第１９条「労働時間及び休憩時間」\n",
"\n",
"１ 労働者代表と１年単位の変形労働時間制に関する労使協定を締結した場合、当該協定の適用を受ける労働者について、１週間の所定労働時間は、対象期間を平均して１週間当たり４０時間とする。\n",
"２ １年単位の変形労働時間制を適用しない労働者について、１週間の所定労働時間は４０時間、１日の所定労働時間は８時間とする。\n",
"\n",
"----\n",
"Title: 第２０条「休日」\n",
"\n",
"１ １年単位の変形労働時間制の適用を受ける労働者の休日については、１年単位の変形労働時間制に関する労使協定の定めるところにより、対象期間の初日を起算日とする１週間ごとに１日以上、１年間に１２５日以上となるように指定する。その場合、年間休日カレンダーに定め、対象期間の初日の３０日前までに各労働者に通知する。\n",
"２ １年単位の変形労働時間制を適用しない労働者の休日については、以下のとおり指定し、月間休日カレンダーに定め、対象期間の初日の３０日前までに各労働者に通知する。\n",
" ①日曜日（前条第３号の特定期間を除く。）\n",
" ②国民の祝日（日曜日と重なったときは翌日）\n",
" ③年末年始（１月１日～１月３日）\n",
" ④夏季休日（８月１３日～８月１６日）\n",
" ⑤その他会社が指定する日\n",
"\n",
"----\n",
"Title: 第２１条「時間外及び休日労働等」\n",
"\n",
"１ 業務の都合により、第１９条の所定労働時間を超え、又は第２０条の所定休日に労働させることがある。\n",
"２ 前項の場合、法定労働時間を超える労働又は法定休日における労働については、あらかじめ会社は労働者の過半数代表者と書面による労使協定を締結するとともに、これを所轄の労働基準監督署長に届け出るものとする。\n",
"３ 妊娠中の女性、産後１年を経過しない女性労働者（以下「妊産婦」という）であって請求した者及び１８歳未満の者については、第２項による時間外労働又は休日若しくは深夜（午後１０時から午前５時まで）労働に従事させない。\n",
"４ 災害その他避けることのできない事由によって臨時の必要がある場合には、第１項から前項までの制限を超えて、所定労働時間外又は休日に労働させることがある。ただし、この場合であっても、請求のあった妊産婦については、所定労働時間外労働又は休日労働に従事させない。\n",
"\n",
"----\n",
"Title: 第２６条「育児時間」\n",
"\n",
"１ １歳に満たない子を養育する女性労働者から請求があったときは、休憩時間のほか１日について２回、１回について３０分の育児時間を与える。\n",
"```\n",
" \n",
"## Strategy\n",
"Extract all verifiable facts in above \"Source\", that match the following graph schema, as knowledge triples.\n",
"```turtle\n",
"{extract_turtle(generated_schema)}\n",
"```\n",
"The extracted facts are needed to answer the question \"{question}\".\n",
"However, if no useful facts are found in the above \"Source\", do not output any triples.\n",
"[/INST]\n",
"\"\"\".strip()\n",
"\n",
"generated_kg = kgllm.generate(prompt_kg)\n",
"print(generated_kg)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ## Explore Path\n",
"```path\n",
"お正月は3日間の休日です.\n",
"お盆は4日間の休日です.\n",
"Answer is 4 because 4 is greater than 3.\n",
"```\n",
"\n",
"## Answer\n",
"```txt\n",
"お盆\n",
"```\n"
]
}
],
"source": [
"prompt_answer = f\"\"\"\n",
"[INST]\n",
"Explore \"Knowledge Graph\" entity-to-entity then finally answer \"Question\".\n",
"\n",
"## Knowledge Graph\n",
"```turtle\n",
"{extract_turtle(generated_kg)}\n",
"```\n",
"\n",
"## Question\n",
"{question}\n",
"\n",
"## Strategy\n",
"Answer briefly in one line.\n",
"[/INST]\n",
"\"\"\".strip()\n",
"\n",
"generated_answer = kgllm.generate(prompt_answer)\n",
"print(generated_answer)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"お盆\n"
]
}
],
"source": [
"final_answer = extract_answer(generated_answer)[0]\n",
"print(final_answer)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## ナレッジグラフ推論LLM ver.1"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Loading checkpoint shards: 100%|██████████| 39/39 [00:51<00:00, 1.32s/it]\n"
]
}
],
"source": [
"kgllm = Fujitsu_LLM_KG(\"../../Fujitsu-LLM-KG-8x7B_inst-infer_v1\")"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ## Knowledge Graph\n",
"```turtle\n",
"<#長岡京>\n",
" rel:遷都される前の都 <#?>.\n",
"\n",
"<#?>\n",
" rel:現在の県 <#?>;\n",
" rel:現在の市 <#?>.\n",
"```\n"
]
}
],
"source": [
"question = \"長岡京に遷都される前の都の所在地は現在の何県の何市にあたるでしょうか？\"\n",
"\n",
"prompt_schema = f\"\"\"\n",
"[INST]\n",
"Generate \"Knowledge Graph\" in RDF Turtle format based on the given \"Source\".\n",
"\n",
"## Source\n",
"```txt\n",
"{question}\n",
"```\n",
"\n",
"## Strategy\n",
"Extract graph schema needed to answer the question in above \"Source\" as knowledge triples without omission.\n",
"[/INST]\n",
"\"\"\"\n",
"\n",
"generated_schema = kgllm.generate(prompt_schema)\n",
"print(generated_schema)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ## Knowledge Graph\n",
"```turtle\n",
"<#長岡京>\n",
" rel:遷都される前の都 <#平城京>.\n",
"\n",
"<#平城京>\n",
" rel:現在の県 <#奈良県>;\n",
" rel:現在の市 <#奈良市>.\n",
"```\n"
]
}
],
"source": [
"prompt_kg = f\"\"\"\n",
"[INST]\n",
"Generate \"Knowledge Graph\" in RDF Turtle format based on the given \"Source\".\n",
" \n",
"## Source\n",
"```txt\n",
"平安京\n",
"\n",
"平安京（へいあんきょう／たいらのみやこ）または平安城（へいあんじょう）は、日本における古代最後の宮都。794年（延暦13年）から1869年（明治2年）までの日本の首都。\n",
"桓武天皇により、長岡京に代わる都として山背国（山城国）愛宕・葛野の両郡にまたがる地が選ばれ、中国の洛陽城や長安城を模して793年（延暦12年）から建設された。翌794年（延暦13年）に遷都。北部中央に宮城・平安宮（大内裏）が建設され、以降歴代の皇居が置かれた。\n",
"遷都以来、平清盛により断行された福原遷都（1180年）の期間を除いて、東京奠都まで1100年近くに亘って都として機能し、1869年（明治2年）まで続いた。今日の京都市街が形成されるに至る。\n",
"----\n",
"平城京\n",
"\n",
"平城京（へいじょうきょう／へいぜいきょう／ならのみやこ）は、奈良時代の日本の首都。710年に藤原京から遷都するにあたり、唐の都長安城を模倣して大和国に建造された都城。現在の奈良県奈良市、大和郡山市に存在する。\n",
"中央北域に宮城・平城宮（大内裏）を置き、東西8坊 (約 4.3 km) の面積をもち、中央を南北に走る朱雀大路によって左京・右京に二分され、さらに南北・東西を大路・小路によって碁盤の目のように整然と区画され、全域が72坊に区画設定されていた。\n",
"大阪湾や淡路島（八島のひとつ）にも近い奈良盆地（奈良県奈良市の西部の一部、中心部及び大和郡山市北部）には、5世紀中頃にはすでに天皇陵である佐紀盾列古墳群が作られ、またのちには大神神社、7世紀には興福寺も建立されているが、京となった8世紀には、東大寺や巨大な仏像である東大寺盧舎那仏像、法華寺などが建立された。本州の政治・文化の中心地となるに至って外京（げきょう）に位置した門前町が、今に続く奈良の町を形成する中心となった。\n",
"----\n",
"長岡京\n",
"\n",
"長岡京（ながおかきょう）は、山城国乙訓郡にあった奈良時代末期（または平安時代初期）の都城（現在の京都府向日市、長岡京市、京都市西京区）。宮域跡は向日市鶏冠井町（かいでちょう）に位置し、「長岡宮跡」として国の史跡に指定されている。\n",
"延暦3年（784年）11月11日、第50代桓武天皇により平城京から遷都され、延暦13年（794年）10月22日に平安京に遷都されるまで機能した。\n",
"```\n",
"\n",
"## Strategy\n",
"Extract all verifiable facts in above \"Source\", that match the following graph schema, as knowledge triples without omission.\n",
"```turtle\n",
"{extract_turtle(generated_schema)}\n",
"```\n",
"The extracted facts are needed to answer the question \"{question}\".\n",
"[/INST]\n",
"\"\"\"\n",
"\n",
"generated_kg = kgllm.generate(prompt_kg)\n",
"print(generated_kg)"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ## Explore Path\n",
"```path\n",
"長岡京 → rel:遷都される前の都 → 平城京\n",
"平城京 → rel:現在の県 → 奈良県\n",
"平城京 → rel:現在の市 → 奈良市\n",
"```\n",
"\n",
"## Answer\n",
"```txt\n",
"奈良県奈良市\n",
"```\n"
]
}
],
"source": [
"prompt_answer = f\"\"\"\n",
"[INST]\n",
"Explore \"Knowledge Graph\" entity-to-entity then finally answer \"Question\".\n",
"\n",
"## Knowledge Graph\n",
"```turtle\n",
"{extract_turtle(generated_kg)}\n",
"```\n",
" \n",
"## Question\n",
"{question}\n",
" \n",
"## Strategy\n",
"Answer briefly in one line.\n",
"[/INST]\n",
"\"\"\"\n",
"\n",
"generated_answer = kgllm.generate(prompt_answer)\n",
"print(generated_answer)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|