File size: 82,629 Bytes
57bdca5 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 |
{
"cells": [
{
"cell_type": "markdown",
"id": "844fe3af-9cf1-4c66-aa78-b88a3429acc6",
"metadata": {
"id": "844fe3af-9cf1-4c66-aa78-b88a3429acc6"
},
"source": [
"### 0. Setup\n",
"1) Clone https://github.com/plaggy/rag-gradio-sample-project and set up an environment with gradio_app/requirements.txt.\n",
"\n",
"There you'll find the following files:\n",
"- [prep_scripts/markdown_to_text.py](https://github.com/plaggy/rag-gradio-sample-project/blob/main/prep_scripts/markdown_to_text.py) processes markdown into text; you won't need to change it.\n",
"- [prep_scripts/lancedb_setup.py](https://github.com/plaggy/rag-gradio-sample-project/blob/main/prep_scripts/lancedb_setup.py) is the file where the database is created and, in particular, an embedding model is defined.\n",
"- [gradio_app/backend/query_llm.py](https://github.com/plaggy/rag-gradio-sample-project/blob/main/gradio_app/backend/query_llm.py) defines what LLM is used.\n",
"- [gradio_app/app.py](https://github.com/plaggy/rag-gradio-sample-project/blob/main/gradio_app/app.py) creates the gradio app.\n",
"\n",
"In this task you'll try not only OpenAI models, but also open-source models from Hugging Face Hub through InferenceClient interface (see [gradio_app/backend/query_llm.py](https://github.com/plaggy/rag-gradio-sample-project/blob/main/gradio_app/backend/query_llm.py)). Please don't forget to obtain a Hugging Face token for that (see here https://huggingface.co/settings/tokens).\n",
"\n",
"\n",
"A convenient way to work through the project is to test locally and keep committing the changes to the [HF Spaces](https://huggingface.co/spaces) repo. A space gets automatically rebuilt after each commit and you get a new version of your application up and running.\n",
"\n",
"2) Create a new space with Gradio SDK. You'll get an almost empty repo, the only thing you'll need from it is README.md which has a config letting a space builder know that it's a Gradio app. Reset a remote upstream of your local rag-gradio-sample-project clone to be your freshly created Spaces repository.\n",
"\n",
"The easiest way to set your space up is to set up the gradio_app folder as a git repo, set remote origin to your space repo and checkout the remote README:\n",
"\n",
"```\n",
"cd gradio_app\n",
"git init\n",
"git remote add origin <your spaces repo url>\n",
"git fetch\n",
"git checkout origin/main README.md\n",
"```\n",
"\n",
"The space is not working yet. You'll get the first working version after the Step 3.\n",
"\n",
"- Clone https://github.com/huggingface/transformers to a local machine and run prep_scripts/markdown_to_text.py script to extract raw text from transformers/docs/source/en/. This will be your knowledge base, you don't need it to be a part of your repository\n",
"\n",
"Run the command as follows (pass arguments that work for you)\n",
"```\n",
"python prep_scripts/markdown_to_text.py --input-dir transformers/docs/source/en/ --output-dir docs\n",
"```\n"
]
},
{
"cell_type": "markdown",
"id": "762e9fde-c1f4-464c-b12b-dca602fac5ba",
"metadata": {
"id": "762e9fde-c1f4-464c-b12b-dca602fac5ba"
},
"source": [
"**By design, you'll be running your experiments in a [Gradio space](https://huggingface.co/docs/hub/en/spaces-sdks-gradio). Apart from deliverables for each step you'll need to provide a link to a functioning RAG space in it final state!**"
]
},
{
"cell_type": "code",
"source": [
"!git clone https://github.com/plaggy/rag-gradio-sample-project"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "BUHKUeqR7unC",
"outputId": "92617e28-da69-45e3-b34e-2b88876ae3dd"
},
"id": "BUHKUeqR7unC",
"execution_count": 1,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Cloning into 'rag-gradio-sample-project'...\n",
"remote: Enumerating objects: 73, done.\u001b[K\n",
"remote: Counting objects: 100% (73/73), done.\u001b[K\n",
"remote: Compressing objects: 100% (59/59), done.\u001b[K\n",
"remote: Total 73 (delta 23), reused 57 (delta 14), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (73/73), 31.10 KiB | 10.37 MiB/s, done.\n",
"Resolving deltas: 100% (23/23), done.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!pip install -r /content/rag-gradio-sample-project/gradio_app/requirements.txt"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "FFIvgBYDcVMt",
"outputId": "3c53faf0-f87e-4d19-bbac-90401cc70b71"
},
"id": "FFIvgBYDcVMt",
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Collecting lancedb==0.5.3 (from -r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1))\n",
" Downloading lancedb-0.5.3-py3-none-any.whl (106 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m107.0/107.0 kB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting openai==1.11.1 (from -r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 2))\n",
" Downloading openai-1.11.1-py3-none-any.whl (226 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m226.1/226.1 kB\u001b[0m \u001b[31m19.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting sentence-transformers==2.3.1 (from -r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 3))\n",
" Downloading sentence_transformers-2.3.1-py3-none-any.whl (132 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m132.8/132.8 kB\u001b[0m \u001b[31m15.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting tqdm==4.66.1 (from -r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 4))\n",
" Downloading tqdm-4.66.1-py3-none-any.whl (78 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m78.3/78.3 kB\u001b[0m \u001b[31m9.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting torch==2.1.1 (from -r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5))\n",
" Downloading torch-2.1.1-cp310-cp310-manylinux1_x86_64.whl (670.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m670.2/670.2 MB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting transformers==4.37.2 (from -r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 6))\n",
" Downloading transformers-4.37.2-py3-none-any.whl (8.4 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.4/8.4 MB\u001b[0m \u001b[31m89.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting deprecation (from lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1))\n",
" Downloading deprecation-2.1.0-py2.py3-none-any.whl (11 kB)\n",
"Collecting pylance==0.9.12 (from lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1))\n",
" Downloading pylance-0.9.12-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (21.4 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.4/21.4 MB\u001b[0m \u001b[31m68.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting ratelimiter~=1.0 (from lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1))\n",
" Downloading ratelimiter-1.2.0.post0-py3-none-any.whl (6.6 kB)\n",
"Collecting retry>=0.9.2 (from lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1))\n",
" Downloading retry-0.9.2-py2.py3-none-any.whl (8.0 kB)\n",
"Requirement already satisfied: pydantic>=1.10 in /usr/local/lib/python3.10/dist-packages (from lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1)) (2.6.1)\n",
"Requirement already satisfied: attrs>=21.3.0 in /usr/local/lib/python3.10/dist-packages (from lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1)) (23.2.0)\n",
"Collecting semver>=3.0 (from lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1))\n",
" Downloading semver-3.0.2-py3-none-any.whl (17 kB)\n",
"Requirement already satisfied: cachetools in /usr/local/lib/python3.10/dist-packages (from lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1)) (5.3.2)\n",
"Requirement already satisfied: pyyaml>=6.0 in /usr/local/lib/python3.10/dist-packages (from lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1)) (6.0.1)\n",
"Requirement already satisfied: click>=8.1.7 in /usr/local/lib/python3.10/dist-packages (from lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1)) (8.1.7)\n",
"Requirement already satisfied: requests>=2.31.0 in /usr/local/lib/python3.10/dist-packages (from lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1)) (2.31.0)\n",
"Collecting overrides>=0.7 (from lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1))\n",
" Downloading overrides-7.7.0-py3-none-any.whl (17 kB)\n",
"Requirement already satisfied: anyio<5,>=3.5.0 in /usr/local/lib/python3.10/dist-packages (from openai==1.11.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 2)) (3.7.1)\n",
"Requirement already satisfied: distro<2,>=1.7.0 in /usr/lib/python3/dist-packages (from openai==1.11.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 2)) (1.7.0)\n",
"Collecting httpx<1,>=0.23.0 (from openai==1.11.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 2))\n",
" Downloading httpx-0.26.0-py3-none-any.whl (75 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.9/75.9 kB\u001b[0m \u001b[31m7.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from openai==1.11.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 2)) (1.3.0)\n",
"Requirement already satisfied: typing-extensions<5,>=4.7 in /usr/local/lib/python3.10/dist-packages (from openai==1.11.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 2)) (4.9.0)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==2.3.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 3)) (1.25.2)\n",
"Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==2.3.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 3)) (1.2.2)\n",
"Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==2.3.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 3)) (1.11.4)\n",
"Requirement already satisfied: nltk in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==2.3.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 3)) (3.8.1)\n",
"Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==2.3.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 3)) (0.1.99)\n",
"Requirement already satisfied: huggingface-hub>=0.15.1 in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==2.3.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 3)) (0.20.3)\n",
"Requirement already satisfied: Pillow in /usr/local/lib/python3.10/dist-packages (from sentence-transformers==2.3.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 3)) (9.4.0)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5)) (3.13.1)\n",
"Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5)) (1.12)\n",
"Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5)) (3.2.1)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5)) (3.1.3)\n",
"Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5)) (2023.6.0)\n",
"Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5))\n",
" Downloading nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m23.7/23.7 MB\u001b[0m \u001b[31m59.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting nvidia-cuda-runtime-cu12==12.1.105 (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5))\n",
" Downloading nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m823.6/823.6 kB\u001b[0m \u001b[31m43.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting nvidia-cuda-cupti-cu12==12.1.105 (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5))\n",
" Downloading nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m14.1/14.1 MB\u001b[0m \u001b[31m80.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting nvidia-cudnn-cu12==8.9.2.26 (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5))\n",
" Downloading nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m731.7/731.7 MB\u001b[0m \u001b[31m764.7 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting nvidia-cublas-cu12==12.1.3.1 (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5))\n",
" Downloading nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m410.6/410.6 MB\u001b[0m \u001b[31m2.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting nvidia-cufft-cu12==11.0.2.54 (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5))\n",
" Downloading nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m121.6/121.6 MB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting nvidia-curand-cu12==10.3.2.106 (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5))\n",
" Downloading nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.5/56.5 MB\u001b[0m \u001b[31m10.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting nvidia-cusolver-cu12==11.4.5.107 (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5))\n",
" Downloading nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m124.2/124.2 MB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting nvidia-cusparse-cu12==12.1.0.106 (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5))\n",
" Downloading nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.0/196.0 MB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting nvidia-nccl-cu12==2.18.1 (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5))\n",
" Downloading nvidia_nccl_cu12-2.18.1-py3-none-manylinux1_x86_64.whl (209.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m209.8/209.8 MB\u001b[0m \u001b[31m5.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting nvidia-nvtx-cu12==12.1.105 (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5))\n",
" Downloading nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m99.1/99.1 kB\u001b[0m \u001b[31m13.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5)) (2.1.0)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers==4.37.2->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 6)) (23.2)\n",
"Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.37.2->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 6)) (2023.12.25)\n",
"Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers==4.37.2->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 6)) (0.15.2)\n",
"Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.37.2->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 6)) (0.4.2)\n",
"Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5))\n",
" Downloading nvidia_nvjitlink_cu12-12.3.101-py3-none-manylinux1_x86_64.whl (20.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m20.5/20.5 MB\u001b[0m \u001b[31m72.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting pyarrow>=12 (from pylance==0.9.12->lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1))\n",
" Downloading pyarrow-15.0.0-cp310-cp310-manylinux_2_28_x86_64.whl (38.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.3/38.3 MB\u001b[0m \u001b[31m14.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: idna>=2.8 in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai==1.11.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 2)) (3.6)\n",
"Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai==1.11.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 2)) (1.2.0)\n",
"Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx<1,>=0.23.0->openai==1.11.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 2)) (2024.2.2)\n",
"Collecting httpcore==1.* (from httpx<1,>=0.23.0->openai==1.11.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 2))\n",
" Downloading httpcore-1.0.3-py3-none-any.whl (77 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.0/77.0 kB\u001b[0m \u001b[31m10.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting h11<0.15,>=0.13 (from httpcore==1.*->httpx<1,>=0.23.0->openai==1.11.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 2))\n",
" Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m7.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic>=1.10->lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1)) (0.6.0)\n",
"Requirement already satisfied: pydantic-core==2.16.2 in /usr/local/lib/python3.10/dist-packages (from pydantic>=1.10->lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1)) (2.16.2)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.31.0->lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1)) (3.3.2)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.31.0->lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1)) (2.0.7)\n",
"Requirement already satisfied: decorator>=3.4.2 in /usr/local/lib/python3.10/dist-packages (from retry>=0.9.2->lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1)) (4.4.2)\n",
"Collecting py<2.0.0,>=1.4.26 (from retry>=0.9.2->lancedb==0.5.3->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 1))\n",
" Downloading py-1.11.0-py2.py3-none-any.whl (98 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m98.7/98.7 kB\u001b[0m \u001b[31m12.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5)) (2.1.5)\n",
"Requirement already satisfied: joblib in /usr/local/lib/python3.10/dist-packages (from nltk->sentence-transformers==2.3.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 3)) (1.3.2)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->sentence-transformers==2.3.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 3)) (3.2.0)\n",
"Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch==2.1.1->-r /content/rag-gradio-sample-project/gradio_app/requirements.txt (line 5)) (1.3.0)\n",
"Installing collected packages: ratelimiter, tqdm, semver, pyarrow, py, overrides, 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, h11, deprecation, retry, pylance, nvidia-cusparse-cu12, nvidia-cudnn-cu12, httpcore, nvidia-cusolver-cu12, lancedb, httpx, transformers, torch, openai, sentence-transformers\n",
" Attempting uninstall: tqdm\n",
" Found existing installation: tqdm 4.66.2\n",
" Uninstalling tqdm-4.66.2:\n",
" Successfully uninstalled tqdm-4.66.2\n",
" Attempting uninstall: pyarrow\n",
" Found existing installation: pyarrow 10.0.1\n",
" Uninstalling pyarrow-10.0.1:\n",
" Successfully uninstalled pyarrow-10.0.1\n",
" Attempting uninstall: transformers\n",
" Found existing installation: transformers 4.35.2\n",
" Uninstalling transformers-4.35.2:\n",
" Successfully uninstalled transformers-4.35.2\n",
" Attempting uninstall: torch\n",
" Found existing installation: torch 2.1.0+cu121\n",
" Uninstalling torch-2.1.0+cu121:\n",
" Successfully uninstalled torch-2.1.0+cu121\n",
"\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
"llmx 0.0.15a0 requires cohere, which is not installed.\n",
"llmx 0.0.15a0 requires tiktoken, which is not installed.\n",
"ibis-framework 7.1.0 requires pyarrow<15,>=2, but you have pyarrow 15.0.0 which is incompatible.\n",
"torchaudio 2.1.0+cu121 requires torch==2.1.0, but you have torch 2.1.1 which is incompatible.\n",
"torchdata 0.7.0 requires torch==2.1.0, but you have torch 2.1.1 which is incompatible.\n",
"torchtext 0.16.0 requires torch==2.1.0, but you have torch 2.1.1 which is incompatible.\n",
"torchvision 0.16.0+cu121 requires torch==2.1.0, but you have torch 2.1.1 which is incompatible.\u001b[0m\u001b[31m\n",
"\u001b[0mSuccessfully installed deprecation-2.1.0 h11-0.14.0 httpcore-1.0.3 httpx-0.26.0 lancedb-0.5.3 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.18.1 nvidia-nvjitlink-cu12-12.3.101 nvidia-nvtx-cu12-12.1.105 openai-1.11.1 overrides-7.7.0 py-1.11.0 pyarrow-15.0.0 pylance-0.9.12 ratelimiter-1.2.0.post0 retry-0.9.2 semver-3.0.2 sentence-transformers-2.3.1 torch-2.1.1 tqdm-4.66.1 transformers-4.37.2\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!pip install huggingface_hub"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "uVHHnyoedIPy",
"outputId": "527c17ae-a7db-45db-cf12-46cb07f90342"
},
"id": "uVHHnyoedIPy",
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.10/dist-packages (0.20.3)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (3.13.1)\n",
"Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2023.6.0)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2.31.0)\n",
"Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.66.1)\n",
"Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (6.0.1)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.9.0)\n",
"Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (23.2)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.3.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.6)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2.0.7)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2024.2.2)\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!huggingface-cli login"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "8-M0jyfGdKYe",
"outputId": "c7f7d369-c51b-43e6-8aa4-182af93a7f4a"
},
"id": "8-M0jyfGdKYe",
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" _| _| _| _| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _|_|_|_| _|_| _|_|_| _|_|_|_|\n",
" _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|\n",
" _|_|_|_| _| _| _| _|_| _| _|_| _| _| _| _| _| _|_| _|_|_| _|_|_|_| _| _|_|_|\n",
" _| _| _| _| _| _| _| _| _| _| _|_| _| _| _| _| _| _| _|\n",
" _| _| _|_| _|_|_| _|_|_| _|_|_| _| _| _|_|_| _| _| _| _|_|_| _|_|_|_|\n",
"\n",
" To login, `huggingface_hub` requires a token generated from https://huggingface.co/settings/tokens .\n",
"Token: \n",
"Add token as git credential? (Y/n) \n",
"Token is valid (permission: read).\n",
"\u001b[1m\u001b[31mCannot authenticate through git-credential as no helper is defined on your machine.\n",
"You might have to re-authenticate when pushing to the Hugging Face Hub.\n",
"Run the following command in your terminal in case you want to set the 'store' credential helper as default.\n",
"\n",
"git config --global credential.helper store\n",
"\n",
"Read https://git-scm.com/book/en/v2/Git-Tools-Credential-Storage for more details.\u001b[0m\n",
"Token has not been saved to git credential helper.\n",
"Your token has been saved to /root/.cache/huggingface/token\n",
"Login successful\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"%cd rag-gradio-sample-project/gradio_app/\n",
"%ls"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "HjXOD1nH1fx5",
"outputId": "874e8e62-8730-47e2-b185-c7c1e9cc6cfe"
},
"id": "HjXOD1nH1fx5",
"execution_count": 5,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"/content/rag-gradio-sample-project/gradio_app\n",
"app.py \u001b[0m\u001b[01;34mbackend\u001b[0m/ requirements.txt \u001b[01;34mtemplates\u001b[0m/\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"%pwd"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 36
},
"id": "55IyOwgr1kNR",
"outputId": "6235574d-e278-40eb-f389-bdae96090556"
},
"id": "55IyOwgr1kNR",
"execution_count": 6,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"'/content/rag-gradio-sample-project/gradio_app'"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "string"
}
},
"metadata": {},
"execution_count": 6
}
]
},
{
"cell_type": "code",
"source": [
"!git init\n",
"!git remote add origin https://huggingface.co/spaces/Ahmadzei/RAG\n",
"!git config --global init.defaultBranch main\n",
"!git fetch\n",
"!git checkout origin/main README.md"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "1wY0VaL-9c14",
"outputId": "27d6b540-2d9a-4dee-d397-25601878c187"
},
"id": "1wY0VaL-9c14",
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[33mhint: Using 'master' as the name for the initial branch. This default branch name\u001b[m\n",
"\u001b[33mhint: is subject to change. To configure the initial branch name to use in all\u001b[m\n",
"\u001b[33mhint: of your new repositories, which will suppress this warning, call:\u001b[m\n",
"\u001b[33mhint: \u001b[m\n",
"\u001b[33mhint: \tgit config --global init.defaultBranch <name>\u001b[m\n",
"\u001b[33mhint: \u001b[m\n",
"\u001b[33mhint: Names commonly chosen instead of 'master' are 'main', 'trunk' and\u001b[m\n",
"\u001b[33mhint: 'development'. The just-created branch can be renamed via this command:\u001b[m\n",
"\u001b[33mhint: \u001b[m\n",
"\u001b[33mhint: \tgit branch -m <name>\u001b[m\n",
"Initialized empty Git repository in /content/rag-gradio-sample-project/gradio_app/.git/\n",
"remote: Enumerating objects: 4, done.\u001b[K\n",
"remote: Total 4 (delta 0), reused 0 (delta 0), pack-reused 4\u001b[K\n",
"Unpacking objects: 100% (4/4), 1.27 KiB | 1.27 MiB/s, done.\n",
"From https://huggingface.co/spaces/Ahmadzei/RAG\n",
" * [new branch] main -> origin/main\n",
"Updated 1 path from b4805fb\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!git clone https://github.com/huggingface/transformers"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "cgX7Aqujk37U",
"outputId": "6294a191-642f-41f2-bb07-0ce528fae8c2"
},
"id": "cgX7Aqujk37U",
"execution_count": 7,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Cloning into 'transformers'...\n",
"remote: Enumerating objects: 185037, done.\u001b[K\n",
"remote: Counting objects: 100% (1681/1681), done.\u001b[K\n",
"remote: Compressing objects: 100% (1231/1231), done.\u001b[K\n",
"remote: Total 185037 (delta 824), reused 742 (delta 374), pack-reused 183356\u001b[K\n",
"Receiving objects: 100% (185037/185037), 205.20 MiB | 19.65 MiB/s, done.\n",
"Resolving deltas: 100% (130045/130045), done.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# !python transformers/prep_scripts/markdown_to_text.py --input_dir transformers/docs/source/en/ --output_dir /content/knowledge_base/\n",
"!python /content/rag-gradio-sample-project/prep_scripts/markdown_to_text.py --input-dir /content/rag-gradio-sample-project/gradio_app/transformers/docs/source/en/ --output-dir /content/docs/"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "2NYMq3KIlMAz",
"outputId": "d24cd17b-2f77-4f3a-b8c0-449acd9b0f80"
},
"id": "2NYMq3KIlMAz",
"execution_count": 8,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\r0it [00:00, ?it/s]/content/rag-gradio-sample-project/prep_scripts/markdown_to_text.py:22: DeprecationWarning: The 'text' argument to find()-type methods is deprecated. Use 'string' instead.\n",
" text = ''.join(soup.findAll(text=True))\n",
"385it [00:06, 60.38it/s]\n"
]
}
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6c813d03-33a7-4ce1-836f-11afc541f291",
"metadata": {
"id": "6c813d03-33a7-4ce1-836f-11afc541f291"
},
"outputs": [],
"source": [
"# Add the link to the space you've just created here:\n",
"# https://huggingface.co/spaces/Ahmadzei/RAG"
]
},
{
"cell_type": "markdown",
"id": "c970d0a4-fee8-48ac-9377-4a6def7712b2",
"metadata": {
"id": "c970d0a4-fee8-48ac-9377-4a6def7712b2"
},
"source": [
"### Step 1: Chunk Your Data\n",
"\n",
"To efficiently pull up documents relevant to a query from a knowledge base documents are embedded and stored as vectors. Documents in your knowledge base are not expected to fit into the context length of an embedding model (most have 512 token limit). Hence chunking your documents into smaller pieces is required. Take a deeper dive into why chunking is important and what are the options [here](https://www.pinecone.io/learn/chunking-strategies/).\n",
"\n",
"Your task is to implement and compare two chunking strategies: fixed-sized chunking and content-aware chunking. For content-aware you could split by sentences, paragraphs or in some other way that makes sense.\n",
"\n",
"The deliverables are:\n",
"- The code for chunk splitting"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f7bad8c8",
"metadata": {
"id": "f7bad8c8"
},
"outputs": [],
"source": [
"# Chunk splitting deliverables"
]
},
{
"cell_type": "code",
"source": [
"def fixed_size_chunking(text, chunk_size=512):\n",
" \"\"\"\n",
" Splits the text into fixed-sized chunks.\n",
"\n",
" :param text: The input text to be chunked.\n",
" :param chunk_size: The size of each chunk in number of characters.\n",
" :return: A list of chunks.\n",
" \"\"\"\n",
" return [text[i:i+chunk_size] for i in range(0, len(text), chunk_size)]\n"
],
"metadata": {
"id": "n9qEj8jfvlPj"
},
"id": "n9qEj8jfvlPj",
"execution_count": 9,
"outputs": []
},
{
"cell_type": "code",
"source": [
"def content_aware_chunking(text, max_chunk_size=512):\n",
" \"\"\"\n",
" Splits the text into content-aware chunks by sentences.\n",
"\n",
" :param text: The input text to be chunked.\n",
" :param max_chunk_size: The maximum size of each chunk in number of characters.\n",
" :return: A list of chunks.\n",
" \"\"\"\n",
" sentences = text.split('. ') # Simple sentence splitting, can be improved with NLP libraries\n",
" chunks = []\n",
" current_chunk = \"\"\n",
"\n",
" for sentence in sentences:\n",
" if len(current_chunk) + len(sentence) < max_chunk_size:\n",
" current_chunk += sentence + \". \"\n",
" else:\n",
" chunks.append(current_chunk.strip())\n",
" current_chunk = sentence + \". \"\n",
" if current_chunk:\n",
" chunks.append(current_chunk.strip())\n",
"\n",
" return chunks"
],
"metadata": {
"id": "DB5IlJAdL6Bq"
},
"id": "DB5IlJAdL6Bq",
"execution_count": 10,
"outputs": []
},
{
"cell_type": "code",
"source": [
"import nltk\n",
"nltk.download('punkt')\n",
"from nltk.tokenize import sent_tokenize\n",
"\n",
"def nltk_chunking(text):\n",
" \"\"\"\n",
" Divide text into chunks based on sentences.\n",
"\n",
" Args:\n",
" text (str): The text to be chunked.\n",
"\n",
" Returns:\n",
" list of str: A list containing the text chunks (sentences).\n",
" \"\"\"\n",
" return sent_tokenize(text)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "8eYOiabGvl00",
"outputId": "abf76bf5-09cb-43f6-b40e-0fffcbf37b3a"
},
"id": "8eYOiabGvl00",
"execution_count": 11,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"[nltk_data] Downloading package punkt to /root/nltk_data...\n",
"[nltk_data] Unzipping tokenizers/punkt.zip.\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"def paragraph_chunking(text):\n",
" \"\"\"\n",
" Divide text into chunks based on paragraphs.\n",
"\n",
" Args:\n",
" text (str): The text to be chunked.\n",
"\n",
" Returns:\n",
" list of str: A list containing the text chunks (paragraphs).\n",
" \"\"\"\n",
" return text.split('\\n\\n')"
],
"metadata": {
"id": "Sk2M6tYmvosj"
},
"id": "Sk2M6tYmvosj",
"execution_count": 12,
"outputs": []
},
{
"cell_type": "code",
"source": [
"import os\n",
"import glob\n",
"\n",
"def chunk_and_write_docs(input_dir, output_dir_fixed, output_dir_content_aware):\n",
" # Ensure output directories exist\n",
" os.makedirs(output_dir_fixed, exist_ok=True)\n",
" os.makedirs(output_dir_content_aware, exist_ok=True)\n",
"\n",
" # List all text files in the input directory\n",
" file_paths = glob.glob(os.path.join(input_dir, '*.txt'))\n",
"\n",
" for file_path in file_paths:\n",
" # Read the content of the file\n",
" with open(file_path, 'r', encoding='utf-8') as file:\n",
" text_content = file.read()\n",
"\n",
" # Generate chunks using both methods\n",
" fixed_chunks = fixed_size_chunking(text_content)\n",
" content_aware_chunks = content_aware_chunking(text_content)\n",
"\n",
" # Extract base name without extension for use in chunk file names\n",
" base_name = os.path.splitext(os.path.basename(file_path))[0]\n",
"\n",
" # Fixed-size chunking\n",
" fixed_chunk_dir = os.path.join(output_dir_fixed, base_name.replace('.txt', ''))\n",
" os.makedirs(fixed_chunk_dir, exist_ok=True)\n",
" for i, chunk in enumerate(fixed_chunks):\n",
" with open(os.path.join(fixed_chunk_dir, f'chunk_{i}.txt'), 'w', encoding='utf-8') as chunk_file:\n",
" chunk_file.write(chunk)\n",
"\n",
" # Content-aware chunking\n",
" content_aware_chunk_dir = os.path.join(output_dir_content_aware, base_name.replace('.txt', ''))\n",
" os.makedirs(content_aware_chunk_dir, exist_ok=True)\n",
" for i, chunk in enumerate(content_aware_chunks):\n",
" with open(os.path.join(content_aware_chunk_dir, f'chunk_{i}.txt'), 'w', encoding='utf-8') as chunk_file:\n",
" chunk_file.write(chunk)\n",
"\n",
"# Define input and output directories\n",
"input_dir = '/content/docs'\n",
"output_dir_fixed = '/content/chunked/fixed_size_chunking'\n",
"output_dir_content_aware = '/content/chunked/content_aware_chunking'\n",
"\n",
"# Process the documents\n",
"chunk_and_write_docs(input_dir, output_dir_fixed, output_dir_content_aware)\n",
"\n",
"# To indicate completion and the count of processed files\n",
"processed_files_count = len(glob.glob(os.path.join(input_dir, '*.txt')))\n",
"processed_files_count\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "FGDf40tqSK2C",
"outputId": "39033395-444e-4579-a387-1128ec73bc41"
},
"id": "FGDf40tqSK2C",
"execution_count": 13,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"381"
]
},
"metadata": {},
"execution_count": 13
}
]
},
{
"cell_type": "markdown",
"id": "5e5ebaad-8d42-430c-b00b-18198cdb9ce8",
"metadata": {
"id": "5e5ebaad-8d42-430c-b00b-18198cdb9ce8"
},
"source": [
"### Step 2: Ingest chunks into a database and create an index\n",
"\n",
"Chunks need to be vectorized and made accessible to an LLM to enable semantic search with embedding models. A current industry standard is to use a vector database to store and retrieve texts both conveniently and efficiently. There are many products out there, we'll be using [LanceDB](https://lancedb.github.io/lancedb/). LanceDB is a young product, one way it stands out is that it's embedded - it's designed not to be a standalone service but rather a part of an application, more on this [here](https://lancedb.github.io/lancedb/basic/).\n",
"\n",
"Find more details on how different databases compare in [this](https://thedataquarry.com/tags/vector-db/) series of posts.\n",
"\n",
"Your task is to vectorize and ingest chunked documents into the database.\n",
"**For each chunking strategy from the previous step create a separate table with one of the embedding models. Compare the chunking strategies and choose one. Perform vectorization+ingestion with the second model only with one chunking strategy of your choice**.\n",
"Use prep_scrips/lancedb_setup.py to vectorize chunks and store vector representations along with raw text in a Lancedb instance. The script also creates an index for fast ANN retrieval (not really needed for this exercise but necessary at scale). Try different embedding models and see how results differ. The options are:\n",
"\n",
"- `sentence-transformers/all-MiniLM-L6-v2`: a light model, produces vectors of length 384\n",
"- `BAAI/bge-large-en-v1.5`: a much heavier model, embedding vector length is 1024\n",
"\n",
"Feel free to explore other embedding models and justify your choice.\n",
"For different embedding models and different chunking strategies create different tables in the database so you can easily switch between them and compare.\n",
"\n",
"Run the embedding+ingestion script as follows, make sure to look into the script and go over the arguments. Note that the number of sub-vectors for indexing must be a divisor of the model embedding size.\n",
"\n",
"```\n",
"python prep_scrips/lancedb_setup.py --emb-model <model name> --table <db table name> --input-dir <folder with chunked docs> --num-sub-vectors <a number which is a divisor of the embedding dim>\n",
"```\n",
"\n",
"Before committing to your space set up environment variables on the settings tab of your space, use `.env` as a ference list of all the things you can customize. Make sure to add HF_TOKEN and OPENAI_API_KEY as secrets.\n",
"Not all the parameters are required to set via environment variables, most have default values.\n",
"\n",
"*The database is expected to be in the `gradio_app` folder under `.lancedb`, make sure to move it there if was initialized elsewhere.* It can be parametrized but it's unnecessary here.\n",
"\n",
"To commit large files to Github use `git lfs`:\n",
"```\n",
"git lfs install\n",
"git lfs track \"*.lance\"\n",
"git lfs track \"*.idx\"\n",
"git add .gitattributes\n",
"```\n",
"Then proceed as usual.\n",
"\n",
"For experimenting you can easily switch between embedding models/tables by changing the values of the corresponding env variables in your space (`EMB_MODEL`, `TABLE_NAME`). Overall, every time you change the value of an environment variable a space gets automatically rebuilt.\n",
"\n",
"The deliverables are:\n",
"1. The illustration of how retrieved documents differ depending on the embedding model and the chunking strategy. You should create at least 3 tables: model_1 + chunking_strategy_1, model_1 + chunking_strategy_2, model_2 + chunking_strategy_<1 or 2>\n",
"2. The analysis of pros and cons of chunking strategies\n",
"3. The analysis of how retrieved document differ between embedding models (is one better than the other?)\n",
"4. The analysis of how the embedding time differs between models"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f7db282e-e03c-41de-9c03-54abf455481f",
"metadata": {
"id": "f7db282e-e03c-41de-9c03-54abf455481f"
},
"outputs": [],
"source": [
"# Embed documents with different chunking strategies and ingest into the database"
]
},
{
"cell_type": "code",
"source": [
"!pip install lancedb openai pyarrow pandas numpy sentence-transformers"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "vrrCjCs3-lNy",
"outputId": "c1a20049-d733-4390-ef65-cd9df1c0109f"
},
"id": "vrrCjCs3-lNy",
"execution_count": 14,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Requirement already satisfied: lancedb in /usr/local/lib/python3.10/dist-packages (0.5.3)\n",
"Requirement already satisfied: openai in /usr/local/lib/python3.10/dist-packages (1.11.1)\n",
"Requirement already satisfied: pyarrow in /usr/local/lib/python3.10/dist-packages (15.0.0)\n",
"Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (1.5.3)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (1.25.2)\n",
"Requirement already satisfied: sentence-transformers in /usr/local/lib/python3.10/dist-packages (2.3.1)\n",
"Requirement already satisfied: deprecation in /usr/local/lib/python3.10/dist-packages (from lancedb) (2.1.0)\n",
"Requirement already satisfied: pylance==0.9.12 in /usr/local/lib/python3.10/dist-packages (from lancedb) (0.9.12)\n",
"Requirement already satisfied: ratelimiter~=1.0 in /usr/local/lib/python3.10/dist-packages (from lancedb) (1.2.0.post0)\n",
"Requirement already satisfied: retry>=0.9.2 in /usr/local/lib/python3.10/dist-packages (from lancedb) (0.9.2)\n",
"Requirement already satisfied: tqdm>=4.27.0 in /usr/local/lib/python3.10/dist-packages (from lancedb) (4.66.1)\n",
"Requirement already satisfied: pydantic>=1.10 in /usr/local/lib/python3.10/dist-packages (from lancedb) (2.6.1)\n",
"Requirement already satisfied: attrs>=21.3.0 in /usr/local/lib/python3.10/dist-packages (from lancedb) (23.2.0)\n",
"Requirement already satisfied: semver>=3.0 in /usr/local/lib/python3.10/dist-packages (from lancedb) (3.0.2)\n",
"Requirement already satisfied: cachetools in /usr/local/lib/python3.10/dist-packages (from lancedb) (5.3.2)\n",
"Requirement already satisfied: pyyaml>=6.0 in /usr/local/lib/python3.10/dist-packages (from lancedb) (6.0.1)\n",
"Requirement already satisfied: click>=8.1.7 in /usr/local/lib/python3.10/dist-packages (from lancedb) (8.1.7)\n",
"Requirement already satisfied: requests>=2.31.0 in /usr/local/lib/python3.10/dist-packages (from lancedb) (2.31.0)\n",
"Requirement already satisfied: overrides>=0.7 in /usr/local/lib/python3.10/dist-packages (from lancedb) (7.7.0)\n",
"Requirement already satisfied: anyio<5,>=3.5.0 in /usr/local/lib/python3.10/dist-packages (from openai) (3.7.1)\n",
"Requirement already satisfied: distro<2,>=1.7.0 in /usr/lib/python3/dist-packages (from openai) (1.7.0)\n",
"Requirement already satisfied: httpx<1,>=0.23.0 in /usr/local/lib/python3.10/dist-packages (from openai) (0.26.0)\n",
"Requirement already satisfied: sniffio in /usr/local/lib/python3.10/dist-packages (from openai) (1.3.0)\n",
"Requirement already satisfied: typing-extensions<5,>=4.7 in /usr/local/lib/python3.10/dist-packages (from openai) (4.9.0)\n",
"Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2023.4)\n",
"Requirement already satisfied: transformers<5.0.0,>=4.32.0 in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (4.37.2)\n",
"Requirement already satisfied: torch>=1.11.0 in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (2.1.1)\n",
"Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (1.2.2)\n",
"Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (1.11.4)\n",
"Requirement already satisfied: nltk in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (3.8.1)\n",
"Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (0.1.99)\n",
"Requirement already satisfied: huggingface-hub>=0.15.1 in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (0.20.3)\n",
"Requirement already satisfied: Pillow in /usr/local/lib/python3.10/dist-packages (from sentence-transformers) (9.4.0)\n",
"Requirement already satisfied: idna>=2.8 in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai) (3.6)\n",
"Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.5.0->openai) (1.2.0)\n",
"Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx<1,>=0.23.0->openai) (2024.2.2)\n",
"Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.10/dist-packages (from httpx<1,>=0.23.0->openai) (1.0.3)\n",
"Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.10/dist-packages (from httpcore==1.*->httpx<1,>=0.23.0->openai) (0.14.0)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.15.1->sentence-transformers) (3.13.1)\n",
"Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.15.1->sentence-transformers) (2023.6.0)\n",
"Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.15.1->sentence-transformers) (23.2)\n",
"Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic>=1.10->lancedb) (0.6.0)\n",
"Requirement already satisfied: pydantic-core==2.16.2 in /usr/local/lib/python3.10/dist-packages (from pydantic>=1.10->lancedb) (2.16.2)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas) (1.16.0)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.31.0->lancedb) (3.3.2)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.31.0->lancedb) (2.0.7)\n",
"Requirement already satisfied: decorator>=3.4.2 in /usr/local/lib/python3.10/dist-packages (from retry>=0.9.2->lancedb) (4.4.2)\n",
"Requirement already satisfied: py<2.0.0,>=1.4.26 in /usr/local/lib/python3.10/dist-packages (from retry>=0.9.2->lancedb) (1.11.0)\n",
"Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (1.12)\n",
"Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (3.2.1)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (3.1.3)\n",
"Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (12.1.105)\n",
"Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (12.1.105)\n",
"Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (12.1.105)\n",
"Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (8.9.2.26)\n",
"Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (12.1.3.1)\n",
"Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (11.0.2.54)\n",
"Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (10.3.2.106)\n",
"Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (11.4.5.107)\n",
"Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (12.1.0.106)\n",
"Requirement already satisfied: nvidia-nccl-cu12==2.18.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (2.18.1)\n",
"Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (12.1.105)\n",
"Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.11.0->sentence-transformers) (2.1.0)\n",
"Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.11.0->sentence-transformers) (12.3.101)\n",
"Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.32.0->sentence-transformers) (2023.12.25)\n",
"Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.32.0->sentence-transformers) (0.15.2)\n",
"Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers<5.0.0,>=4.32.0->sentence-transformers) (0.4.2)\n",
"Requirement already satisfied: joblib in /usr/local/lib/python3.10/dist-packages (from nltk->sentence-transformers) (1.3.2)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->sentence-transformers) (3.2.0)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.11.0->sentence-transformers) (2.1.5)\n",
"Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.11.0->sentence-transformers) (1.3.0)\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Setting environment variables\n",
"os.environ['EMB_MODEL'] = 'sentence-transformers/all-MiniLM-L6-v2' #sentence-transformers/all-MiniLM-L6-v2: a light model, produces vectors of length 384 / BAAI/bge-large-en-v1.5: a much heavier model, embedding vector length is 1024\n",
"os.environ['TABLE_NAME'] = 'fixed_size_chunking' # fixed_size_chunking / content_aware_chunking\n",
"os.environ['INPUT_DIR'] = '/content/chunked/docs/fixed_size_chunking/' # fixed_size_chunking / content_aware_chunking\n",
"os.environ['NUM_SUB_VECTORS'] = '12'"
],
"metadata": {
"id": "o3TCdDIEYwk6"
},
"id": "o3TCdDIEYwk6",
"execution_count": 15,
"outputs": []
},
{
"cell_type": "code",
"source": [
"EMB_MODEL = os.getenv('EMB_MODEL')\n",
"TABLE_NAME = os.getenv('TABLE_NAME')\n",
"INPUT_DIR = os.getenv('INPUT_DIR')\n",
"NUM_SUB_VECTORS = os.getenv('NUM_SUB_VECTORS')"
],
"metadata": {
"id": "1tVGE7JYZc3i"
},
"id": "1tVGE7JYZc3i",
"execution_count": 16,
"outputs": []
},
{
"cell_type": "code",
"source": [
"print(INPUT_DIR)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "uL8Gzk6TgLtK",
"outputId": "68c608cf-e685-45c6-fc5f-e51ba204c074"
},
"id": "uL8Gzk6TgLtK",
"execution_count": 17,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"/content/chunked/docs/fixed_size_chunking/\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!python /content/rag-gradio-sample-project/prep_scripts/lancedb_setup.py --emb-model {EMB_MODEL} --table {TABLE_NAME} --input-dir {INPUT_DIR} --num-sub-vectors {NUM_SUB_VECTORS}"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Xy1cyu7_zFgO",
"outputId": "89ade558-d3bf-4aab-9b29-35f72950a07d"
},
"id": "Xy1cyu7_zFgO",
"execution_count": 19,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"INFO:sentence_transformers.SentenceTransformer:Load pretrained SentenceTransformer: sentence-transformers/all-MiniLM-L6-v2\n",
"/usr/local/lib/python3.10/dist-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()\n",
" return self.fget.__get__(instance, owner)()\n",
"INFO:sentence_transformers.SentenceTransformer:Use pytorch device_name: cpu\n",
"INFO:__main__:using cpu device\n",
"0it [00:00, ?it/s]\n",
"Traceback (most recent call last):\n",
" File \"/content/rag-gradio-sample-project/prep_scripts/lancedb_setup.py\", line 96, in <module>\n",
" main()\n",
" File \"/content/rag-gradio-sample-project/prep_scripts/lancedb_setup.py\", line 88, in main\n",
" tbl.create_index(\n",
" File \"/usr/local/lib/python3.10/dist-packages/lancedb/table.py\", line 858, in create_index\n",
" self._dataset.create_index(\n",
" File \"/usr/local/lib/python3.10/dist-packages/lance/dataset.py\", line 1269, in create_index\n",
" self._ds.create_index(column, index_type, name, replace, kwargs)\n",
"OSError: LanceError(Index): KMeans: can not train 256 centroids with 0 vectors, choose a smaller K (< 0) instead, /home/runner/work/lance/lance/rust/lance-index/src/vector/kmeans.rs:45:21\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Setting environment variables\n",
"os.environ['EMB_MODEL'] = 'sentence-transformers/all-MiniLM-L6-v2' #sentence-transformers/all-MiniLM-L6-v2: a light model, produces vectors of length 384 / BAAI/bge-large-en-v1.5: a much heavier model, embedding vector length is 1024\n",
"os.environ['TABLE_NAME'] = 'content_aware_chunking' # fixed_size_chunking / content_aware_chunking\n",
"os.environ['INPUT_DIR'] = '/content/chunked/docs/content_aware_chunking/' # fixed_size_chunking / content_aware_chunking\n",
"os.environ['NUM_SUB_VECTORS'] = '12'"
],
"metadata": {
"id": "t7aqMOI3bh2s"
},
"id": "t7aqMOI3bh2s",
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"EMB_MODEL2 = os.getenv('EMB_MODEL')\n",
"TABLE_NAME2 = os.getenv('TABLE_NAME')\n",
"INPUT_DIR2 = os.getenv('INPUT_DIR')\n",
"NUM_SUB_VECTORS2 = os.getenv('NUM_SUB_VECTORS')"
],
"metadata": {
"id": "Gk9ynF4Bbslu"
},
"id": "Gk9ynF4Bbslu",
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"!python /content/rag-gradio-sample-project/prep_scripts/lancedb_setup.py --emb-model {EMB_MODEL2} --table {TABLE_NAME2} --input-dir {INPUT_DIR2} --num-sub-vectors {NUM_SUB_VECTORS2}"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "rc0n7a9zbwh2",
"outputId": "50251872-bad0-473b-9ac3-36ed6d7a2e5f"
},
"id": "rc0n7a9zbwh2",
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"INFO:sentence_transformers.SentenceTransformer:Load pretrained SentenceTransformer: sentence-transformers/all-MiniLM-L6-v2\n",
"/usr/local/lib/python3.10/dist-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()\n",
" return self.fget.__get__(instance, owner)()\n",
"INFO:sentence_transformers.SentenceTransformer:Use pytorch device_name: cpu\n",
"INFO:__main__:using cpu device\n",
"0it [00:00, ?it/s]\n",
"Traceback (most recent call last):\n",
" File \"/content/rag-gradio-sample-project/prep_scripts/lancedb_setup.py\", line 100, in <module>\n",
" main()\n",
" File \"/content/rag-gradio-sample-project/prep_scripts/lancedb_setup.py\", line 92, in main\n",
" tbl.create_index(\n",
" File \"/usr/local/lib/python3.10/dist-packages/lancedb/table.py\", line 858, in create_index\n",
" self._dataset.create_index(\n",
" File \"/usr/local/lib/python3.10/dist-packages/lance/dataset.py\", line 1269, in create_index\n",
" self._ds.create_index(column, index_type, name, replace, kwargs)\n",
"OSError: LanceError(Index): KMeans: can not train 256 centroids with 0 vectors, choose a smaller K (< 0) instead, /home/runner/work/lance/lance/rust/lance-index/src/vector/kmeans.rs:45:21\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!git lfs install\n",
"!git lfs track \"*.lance\"\n",
"!git lfs track \"*.idx\"\n",
"!git add .gitattributes\n",
"# Then commit and push as usual\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "3Mlmy4j7x9Ln",
"outputId": "c4940d06-37a5-4861-a101-d6cbf753b5d2"
},
"id": "3Mlmy4j7x9Ln",
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Updated git hooks.\n",
"Git LFS initialized.\n",
"Tracking \"*.lance\"\n",
"Tracking \"*.idx\"\n"
]
}
]
},
{
"cell_type": "markdown",
"id": "7d818b4f-ba5a-4c81-b6d7-f3474c398d9c",
"metadata": {
"id": "7d818b4f-ba5a-4c81-b6d7-f3474c398d9c"
},
"source": [
"### Step 3: Add a reranker\n",
"\n",
"A reranker is a second-level model which produces similarity scores for pairs of (input query + retrieved document). Cross-encoders are conventionally used for reranking, their architecture is slightly different from retrieval models (more on it [here] and [here](https://www.sbert.net/examples/applications/retrieve_rerank/README.html)). Cross-encoders are much more costly to run, therefore a retrieval model is used to get a few (dozens) highest-scoring items, and a reranker picks the best among these. The overall pipeline is similar to the recommender system industry standard: a light model retrieves top-n, a precise and heavy model reranks n to get top k, n is orders of magnitude larger than k.\n",
"\n",
"Cross-encoders are optional because of the overhead their usage implies. Your task is to implement a reranker using a cross-encoder and assess pros and cons of having it. Do not forget that the process of pulling the most relevant documents becomes two-staged: retrieve a larger number of items first, than rerank and keep the best top-k for context.\n",
"\n",
"The models fit for the task:\n",
"1. BAAI/bge-reranker-large\n",
"2. cross-encoder/ms-marco-MiniLM-L-6-v2\n",
"\n",
"As usual, feel free to pick another model and provide some description to it.\n",
"\n",
"The deliverables are:\n",
"\n",
"1. The code that enables a reranker.\n",
"3. A comparison of how the prompt and the model output change after adding a reranker\n",
"4. The analysis of pros and cons. The evaluation aspects should include the relevance of the top-k documents, the response time.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ee1b0160-0ba0-4b5f-81c4-ef3ea76850e5",
"metadata": {
"id": "ee1b0160-0ba0-4b5f-81c4-ef3ea76850e5"
},
"outputs": [],
"source": [
"# Implement code for selecting the final documents using a cross-encoder and compare with and without"
]
},
{
"cell_type": "code",
"source": [
"from sentence_transformers import SentenceTransformer\n",
"\n",
"# Load the model\n",
"model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2') # BAAI/bge-reranker-large\n",
"\n",
"# Vectorize the query\n",
"query = \"Your search query here\"\n",
"query_vector = model.encode(query)"
],
"metadata": {
"id": "peSWSL0lXOK5"
},
"id": "peSWSL0lXOK5",
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"import lancedb\n",
"import numpy as np\n",
"\n",
"# Connect to LanceDB and open your table\n",
"db = lancedb.connect(\"/content/rag-gradio-sample-project/gradio_app/.lancedb/\")\n",
"tbl = db.open_table({TABLE_NAME2})\n",
"\n",
"# Perform a vector search for the top-N documents\n",
"df = tbl.search(query_vector) \\\n",
" .metric(\"cosine\") \\\n",
" .limit(10) \\\n",
" .to_list() # Or use .to_pandas(), .to_arrow(), etc., based on your preference\n",
"\n",
"# `df` now contains the top-N documents and their similarity scores"
],
"metadata": {
"id": "xd10rndiUCIW"
},
"id": "xd10rndiUCIW",
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Assuming `df` contains document IDs or keys to fetch the actual documents\n",
"documents = [db.fetch_document(table_name, doc_id) for doc_id in df]"
],
"metadata": {
"id": "8KWuDzhxTLTX"
},
"id": "8KWuDzhxTLTX",
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"from transformers import AutoTokenizer, AutoModelForSequenceClassification\n",
"from torch.utils.data import DataLoader\n",
"import torch\n",
"\n",
"# Initialize the tokenizer and model\n",
"tokenizer = AutoTokenizer.from_pretrained(\"cross-encoder/ms-marco-MiniLM-L-6-v2\")\n",
"model = AutoModelForSequenceClassification.from_pretrained(\"cross-encoder/ms-marco-MiniLM-L-6-v2\")\n",
"\n",
"def rerank(query, documents):\n",
" # Assuming `documents` is a list of texts\n",
" pairs = [[query, doc['text']] for doc in documents] # Adjust based on your `results` structure\n",
" inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors=\"pt\")\n",
" with torch.no_grad():\n",
" scores = rerank_model(**inputs).logits[:,1] # Scores for each pair\n",
" # Sort documents by scores in descending order and return\n",
" documents = [doc for _, doc in sorted(zip(scores, documents), key=lambda x: x[0], reverse=True)]\n",
" return documents"
],
"metadata": {
"id": "O6xMyqFjRp_m"
},
"id": "O6xMyqFjRp_m",
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"top_k_documents = rerank(query, documents)[:K] # Keep top K after reranking"
],
"metadata": {
"id": "dZtiwhPBRtnS"
},
"id": "dZtiwhPBRtnS",
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"id": "f5816c54-a290-4cb0-b7db-3b8901998cb0",
"metadata": {
"id": "f5816c54-a290-4cb0-b7db-3b8901998cb0"
},
"source": [
"### Step 4: Try a different LLM\n",
"\n",
"The suggested `Mistral-7b-instruct` is a great but small model for an LLM. A larger model can be applied to a wider range of problems and do more complex reasoning. Within the scope of this project a larger model may not be beneficial but for more complex cases the difference would become apparent. Another dimension to explore is a base model which was not instruction fine-tuned - it won't respond to your queries the way you'd expect. It may be a great exercise to see the value of fine-tuning.\n",
"\n",
"The task here is to try out an alternative LLM to explore the differences.\n",
"\n",
"The options are:\n",
"1. mistralai/Mistral-7B-v0.1\n",
"2. mistralai/Mixtral-8x7B-Instruct-v0.1\n",
"\n",
"Of course, feel free to choose another one and give some details on how different it is from the initial model.\n",
"\n",
"The deliverables are:\n",
"\n",
"1. The comparison between outputs of the Mistral-7b-instuct and a different model of your choice.\n",
"2. The difference in response times if a larger model was chosen. Make sure to make multiple queries to make the comparison meaningful.\n",
"3. Analyse the differences between outputs and share the conclusions.\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "942f39d4-eb27-4f2d-ae47-a5d65f102faa",
"metadata": {
"id": "942f39d4-eb27-4f2d-ae47-a5d65f102faa"
},
"outputs": [],
"source": [
"# Analysis of the difference between LLMs"
]
},
{
"cell_type": "markdown",
"id": "70c16440",
"metadata": {
"id": "70c16440"
},
"source": [
"### Step 5 (Bonus): Use an LLM to quantitatively compare outputs of different variants of the system (LLM as a Judge)\n",
"\n",
"Use a powerful LLM (e.g. GPT-4) to quantitatively evaluate outputs of two alternative setups (different embedding models, different LLMs, both etc.). For inspiration and for prompts refer to [1](https://arxiv.org/pdf/2306.05685.pdf), [2](https://arxiv.org/pdf/2401.10020.pdf), [3](https://www.airtrain.ai/blog/the-comprehensive-guide-to-llm-evaluation#high-level-approach)\n",
"\n",
"The deliverables:\n",
"\n",
"1. The code you put together\n",
"2. The high-level description of the setup\n",
"3. The results of the qualitative comparison\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "39c18ba0-e54a-478f-9e60-0ea65c29238a",
"metadata": {
"id": "39c18ba0-e54a-478f-9e60-0ea65c29238a"
},
"outputs": [],
"source": [
"# The code implementing LLM-as-a-Judge and the evaluation results"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2ce78700-2578-4719-8b6b-d59fc669d1c1",
"metadata": {
"id": "2ce78700-2578-4719-8b6b-d59fc669d1c1"
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.10.11"
},
"colab": {
"provenance": []
}
},
"nbformat": 4,
"nbformat_minor": 5
} |