Spaces:
Running
Running
File size: 104,643 Bytes
05eec1f |
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 |
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "hUCaGdAj9-9F"
},
"source": [
"---\n",
"title: \"Advanced RAG\"\n",
"---\n",
"_Authored by: [Aymeric Roucher](https://huggingface.co/m-ric)_"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "DKv51c_h9-9H"
},
"source": [
"This notebook demonstrates how you can build an advanced RAG (Retrieval Augmented Generation) for answering a user's question about a specific knowledge base (here, the HuggingFace documentation), using LangChain.\n",
"\n",
"For an introduction to RAG, you can check [this other cookbook](rag_zephyr_langchain)!\n",
"\n",
"RAG systems are complex, with many moving parts: here a RAG diagram, where we noted in blue all possibilities for system enhancement:\n",
"\n",
"<img src=\"https://huggingface.co/datasets/huggingface/cookbook-images/resolve/main/RAG_workflow.png\" height=\"700\">\n",
"\n",
"> 💡 As you can see, there are many steps to tune in this architecture: tuning the system properly will yield significant performance gains.\n",
"\n",
"In this notebook, we will take a look into many of these blue notes to see how to tune your RAG system and get the best performance.\n",
"\n",
"__Let's dig into the model building!__ First, we install the required model dependancies."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "NSX0p0rV9-9I"
},
"outputs": [],
"source": [
"!pip install -q torch transformers transformers accelerate bitsandbytes langchain sentence-transformers faiss-gpu openpyxl pacmap"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "8_Uyukt39-9J"
},
"outputs": [],
"source": [
"%reload_ext dotenv\n",
"%dotenv"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "eoujYMwW9-9J"
},
"outputs": [],
"source": [
"from tqdm.notebook import tqdm\n",
"import pandas as pd\n",
"from typing import Optional, List, Tuple\n",
"from datasets import Dataset\n",
"import matplotlib.pyplot as plt\n",
"\n",
"pd.set_option(\n",
" \"display.max_colwidth\", None\n",
") # this will be helpful when visualizing retriever outputs"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Kr6rN10U9-9J"
},
"source": [
"### Load your knowledge base"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "qZLVIEVW9-9J"
},
"outputs": [],
"source": [
"import datasets\n",
"\n",
"ds = datasets.load_dataset(\"m-ric/huggingface_doc\", split=\"train\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "836Q7vF49-9K"
},
"outputs": [],
"source": [
"from langchain.docstore.document import Document as LangchainDocument\n",
"\n",
"RAW_KNOWLEDGE_BASE = [\n",
" LangchainDocument(page_content=doc[\"text\"], metadata={\"source\": doc[\"source\"]})\n",
" for doc in tqdm(ds)\n",
"]"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "0_LxjD5h9-9K"
},
"source": [
"# 1. Retriever - embeddings 🗂️\n",
"The __retriever acts like an internal search engine__: given the user query, it returns a few relevant snippets from your knowledge base.\n",
"\n",
"These snippets will then be fed to the Reader Model to help it generate its answer.\n",
"\n",
"So __our objective here is, given a user question, to find the most snippets from our knowledge base to answer that question.__\n",
"\n",
"This is a wide objective, it leaves open some questions. How many snippets should we retrieve? This parameter will be named `top_k`.\n",
"\n",
"How long should these snippets be? This is called the `chunk size`. There's no one-size-fits-all answers, but here are a few elements:\n",
"- 🔀 Your `chunk size` is allowed to vary from one snippet to the other.\n",
"- Since there will always be some noise in your retrieval, increasing the `top_k` increases the chance to get relevant elements in your retrieved snippets. 🎯 Shooting more arrows increases your probability to hit your target.\n",
"- Meanwhile, the summed length of your retrieved documents should not be too high: for instance, for most current models 16k tokens will probably drown your Reader model in information due to [Lost-in-the-middle phenomenon](https://huggingface.co/papers/2307.03172). 🎯 Give your reader model only the most relevant insights, not a huge pile of books!\n",
"\n",
"\n",
"> In this notebook, we use Langchain library since __it offers a huge variety of options for vector databases and allows us to keep document metadata throughout the processing__."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "-uS6Mv8O9-9L"
},
"source": [
"### 1.1 Split the documents into chunks\n",
"\n",
"- In this part, __we split the documents from our knowledge base into smaller chunks__ which will be the snippets on which the reader LLM will base its answer.\n",
"- The goal is to prepare a collection of **semantically relevant snippets**. So their size should be adapted to precise ideas: too small will truncate ideas, too large will dilute them.\n",
"\n",
"💡 _Many options exist for text splitting: splitting on words, on sentence boundaries, recursive chunking that processes documents in a tree-like way to preserve structure information... To learn more about chunking, I recommend you read [this great notebook](https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/5_Levels_Of_Text_Splitting.ipynb) by Greg Kamradt._\n",
"\n",
"\n",
"- **Recursive chunking** breaks down the text into smaller parts step by step using a given list of separators sorted from the most important to the least important separator. If the first split doesn't give the right size or shape chunks, the method repeats itself on the new chunks using a different separator. For instance with the list of separators `[\"\\n\\n\", \"\\n\", \".\", \"\"]`:\n",
" - The method will first break down the document wherever there is a double line break `\"\\n\\n\"`.\n",
" - Resulting documents will be split again on simple line breaks `\"\\n\"`, then on sentence ends `\".\"`.\n",
" - And finally, if some chunks are still too big, they will be split whenever they overflow the maximum size.\n",
"\n",
"- With this method, the global structure is well preserved, at the expense of getting slight variations in chunk size.\n",
"\n",
"> [This space](https://huggingface.co/spaces/A-Roucher/chunk_visualizer) lets you visualize how different splitting options affect the chunks you get.\n",
"\n",
"🔬 Let's experiment a bit with chunk sizes, beginning with an arbitrary size, and see how splits work. We use Langchain's implementation of recursive chunking with `RecursiveCharacterTextSplitter`.\n",
"- Parameter `chunk_size` controls the length of individual chunks: this length is counted by default as the number of characters in the chunk.\n",
"- Parameter `chunk_overlap` lets adjacent chunks get a bit of overlap on each other. This reduces the probability that an idea could be cut in half by the split between two adjacent chunks. We ~arbitrarily set this to 1/10th of the chunk size, you could try different values!"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "M4m6TwDJ9-9L"
},
"outputs": [],
"source": [
"from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
"\n",
"# We use a hierarchical list of separators specifically tailored for splitting Markdown documents\n",
"# This list is taken from LangChain's MarkdownTextSplitter class.\n",
"MARKDOWN_SEPARATORS = [\n",
" \"\\n#{1,6} \",\n",
" \"```\\n\",\n",
" \"\\n\\\\*\\\\*\\\\*+\\n\",\n",
" \"\\n---+\\n\",\n",
" \"\\n___+\\n\",\n",
" \"\\n\\n\",\n",
" \"\\n\",\n",
" \" \",\n",
" \"\",\n",
"]\n",
"\n",
"text_splitter = RecursiveCharacterTextSplitter(\n",
" chunk_size=1000, # the maximum number of characters in a chunk: we selected this value arbitrarily\n",
" chunk_overlap=100, # the number of characters to overlap between chunks\n",
" add_start_index=True, # If `True`, includes chunk's start index in metadata\n",
" strip_whitespace=True, # If `True`, strips whitespace from the start and end of every document\n",
" separators=MARKDOWN_SEPARATORS,\n",
")\n",
"\n",
"docs_processed = []\n",
"for doc in RAW_KNOWLEDGE_BASE:\n",
" docs_processed += text_splitter.split_documents([doc])"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "d5jJUMgb9-9M"
},
"source": [
"We also have to keep in mind that when embedding documents, we will use an embedding model that has accepts a certain maximum sequence length `max_seq_length`.\n",
"\n",
"So we should make sure that our chunk sizes are below this limit, because any longer chunk will be truncated before processing, thus losing relevancy."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"referenced_widgets": [
"ae043feeb0914c879e2a9008b413d952"
]
},
"id": "B4hoki349-9M",
"outputId": "64f92a61-7839-476d-f456-7eefde04c20b"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model's maximum sequence length: 512\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "ae043feeb0914c879e2a9008b413d952",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/31085 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from sentence_transformers import SentenceTransformer\n",
"\n",
"# To get the value of the max sequence_length, we will query the underlying `SentenceTransformer` object used in the RecursiveCharacterTextSplitter.\n",
"print(\n",
" f\"Model's maximum sequence length: {SentenceTransformer('thenlper/gte-small').max_seq_length}\"\n",
")\n",
"\n",
"from transformers import AutoTokenizer\n",
"\n",
"tokenizer = AutoTokenizer.from_pretrained(\"thenlper/gte-small\")\n",
"lengths = [len(tokenizer.encode(doc.page_content)) for doc in tqdm(docs_processed)]\n",
"\n",
"# Plot the distrubution of document lengths, counted as the number of tokens\n",
"fig = pd.Series(lengths).hist()\n",
"plt.title(\"Distribution of document lengths in the knowledge base (in count of tokens)\")\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "L3teXczl9-9M"
},
"source": [
"👀 As you can see, __the chunk lengths are not aligned with our limit of 512 tokens__, and some documents are above the limit, thus some part of them will be lost in truncation!\n",
" - So we should change the `RecursiveCharacterTextSplitter` class to count length in number of tokens instead of number of characters.\n",
" - Then we can choose a specific chunk size, here we would choose a lower threshold than 512:\n",
" - smaller documents could allow the split to focus more on specific ideas.\n",
" - But too small chunks would split sentences in half, thus losing meaning again: the proper tuning is a matter of balance."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"referenced_widgets": [
"f900cf4ab3a94f45bfa7298f433566ed"
]
},
"id": "9hvIL2jO9-9M",
"outputId": "9baf219d-2954-4927-9681-e28572db90db"
},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "f900cf4ab3a94f45bfa7298f433566ed",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
" 0%| | 0/17995 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAo4AAAGzCAYAAAChApYOAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAABJmElEQVR4nO3de3yP9eP/8edm23u22ea4mTnsQzkfMmGVnGZLS4QQRaI+mDJKpXKuSAepRH0qOvkIlYrEnJORREkUfRTFtqIdnGa21++Pfu/r6+29cW02Gx73282t3tf1er+u1/W6Ts/3dZqHMcYIAAAAOA/Pkm4AAAAALg0ERwAAANhCcAQAAIAtBEcAAADYQnAEAACALQRHAAAA2EJwBAAAgC0ERwAAANhCcAQAAIAtxR4cJ0yYIA8Pj+KejCSpXbt2ateunfV57dq18vDw0KJFiy7K9O+++27VqlXrokyrsI4eParBgwcrNDRUHh4eSkhIKHAdHh4emjBhQpG37UpUq1Yt3X333SXdjPO6++67FRAQUKzTuFjr1cXaL1zs/c+F+vXXX+Xh4aG5c+cWWZ1z586Vh4eHfv311yKr065atWrplltuuejTvVBHjx5VlSpV9P7771vDLuZx9HJXFMdAu5zr/zfffFNs0yisPn36qFevXoX6boGCo7MTnP98fX0VFham2NhYvfTSS8rMzCxUI8528OBBTZgwQdu3by+S+opSaW6bHU8//bTmzp2roUOH6t1339Vdd91V0k26rMybN08vvvhiSTejUI4fP64JEyZo7dq1Jd2UInEpLwtcuWbMmKFy5cqpT58+Jd2UEvX0009r8eLFxVKv3WNgcbWhNHjkkUf04Ycf6rvvvivwdwt1xnHSpEl69913NWvWLN1///2SpISEBDVu3Fjff/+9S9knnnhCJ06cKFD9Bw8e1MSJEwsczlasWKEVK1YU6DsFda62/ec//9FPP/1UrNO/UKtXr1br1q01fvx43XnnnYqMjCzpJl1WLuWwcvz4cU2cOLHEguOJEyf0xBNPFFl9l/KywJUpOztbM2bM0ODBg1WmTBlreGGOo5e64gptBTkGXs7B8ZprrlGLFi30/PPPF/i7hQqOnTt31p133qmBAwdqzJgxWr58uVauXKnU1FTdeuutLiu4l5eXfH19CzMZ244fPy5J8vHxkY+PT7FO61y8vb3lcDhKbPp2pKamKjg4uKSbAbjx9fWVl5dXSTcDKDFLlizRn3/+6XYJ8WIcR68UHAP/T69evfTRRx/p6NGjBfpekd3j2KFDB40dO1a//fab3nvvPWt4XvdmJCYm6oYbblBwcLACAgJUt25dPfbYY5L+uS/o2muvlSQNHDjQuizuvO+mXbt2atSokbZu3aobb7xRfn5+1nfPvsfRKScnR4899phCQ0Pl7++vW2+9VQcOHHApk9+9ZmfWeb625XWP47Fjx/Tggw+qevXqcjgcqlu3rp577jkZY1zKeXh4aPjw4Vq8eLEaNWokh8Ohhg0b6osvvsi7w8+SmpqqQYMGKSQkRL6+vmratKnefvtta7zzfqt9+/Zp6dKlVtvPde9RVlaWRo4cqcqVK6tcuXK69dZb9fvvv+dZdtu2bercubMCAwMVEBCgjh07atOmTW7l0tLSNHLkSNWqVUsOh0Ph4eHq37+//vrrL0n53xPlbP+ZZ8Oc68L333+vtm3bys/PT3Xq1LHuKVu3bp1atWqlsmXLqm7dulq5cqVbe/744w/dc889CgkJsfr8rbfeynPaCxYs0FNPPaXw8HD5+vqqY8eO2rt3r0t7li5dqt9++83q38Lc85qWlqaEhARrnalTp46eeeYZ5ebmWmWc96M999xzev3111W7dm05HA5de+212rJli1udCxcuVIMGDeTr66tGjRrp448/dllff/31V1WuXFmSNHHiRKv9Z99z+Mcff6hbt24KCAhQ5cqV9dBDDyknJ8elzPz58xUZGaly5copMDBQjRs31owZM84732dPz7nv2Lt3r+6++24FBwcrKChIAwcOtH4s5sfOssjNzT3n8nTavHmzbrrpJgUFBcnPz09t27bVV199dd75yUtWVpZuueUWBQUFaePGjQWez9OnT2vy5MnW8q5Vq5Yee+wxZWVlWWVGjRqlihUruuxj7r//fnl4eOill16yhqWkpMjDw0OzZs06Z5t3796tnj17qkKFCvL19VWLFi306aefupXbuXOnOnTooLJlyyo8PFxPPvmkyzrrlJubqwkTJigsLEx+fn5q3769fvzxxzz3wXa2hfNZsWKFmjVrJl9fXzVo0EAfffSRy/gjR47ooYceUuPGjRUQEKDAwEB17tw5z0t4L7/8sho2bCg/Pz+VL19eLVq00Lx581zK2Nmn5Gfx4sWqVauWateu7TI8r+PohR4zTp48qQkTJujqq6+Wr6+vqlatqu7du+uXX36xytg5fp3r3tjCbtMeHh46duyY3n77bWv7Pd+94EV9DDxfG+we8872999/q2XLlgoPD7euUGZlZWn8+PGqU6eOHA6Hqlevrocffthlu3a2yc4yz8zMVEJCgnWcrVKlijp16qRvv/3WpVynTp107NgxJSYmnrfdZyrSn/d33XWXHnvsMa1YsUL33ntvnmV27typW265RU2aNNGkSZPkcDi0d+9ea0dcv359TZo0SePGjdN9992nNm3aSJKuu+46q47Dhw+rc+fO6tOnj+68806FhIScs11PPfWUPDw89Mgjjyg1NVUvvviioqOjtX37dpUtW9b2/Nlp25mMMbr11lu1Zs0aDRo0SM2aNdPy5cs1evRo/fHHH5o+fbpL+Q0bNuijjz7SsGHDVK5cOb300kvq0aOH9u/fr4oVK+bbrhMnTqhdu3bau3evhg8froiICC1cuFB333230tLSNGLECNWvX1/vvvuuRo4cqfDwcD344IOSZIWFvAwePFjvvfee+vbtq+uuu06rV69WXFycW7mdO3eqTZs2CgwM1MMPPyxvb2+99tprateunRXepH9uSm7Tpo127dqle+65R82bN9dff/2lTz/9VL///rsqVap07gWQh7///lu33HKL+vTpo9tvv12zZs1Snz599P777yshIUFDhgxR37599eyzz6pnz546cOCAypUrJ+mfA2fr1q2tjbFy5cpatmyZBg0apIyMDLebpqdOnSpPT0899NBDSk9P17Rp09SvXz9t3rxZkvT4448rPT1dv//+u7VsC/pAyfHjx9W2bVv98ccf+ve//60aNWpo48aNGjNmjA4dOuR26XXevHnKzMzUv//9b3l4eGjatGnq3r27/ve//8nb21uStHTpUvXu3VuNGzfWlClT9Pfff2vQoEGqVq2aVU/lypU1a9YsDR06VLfddpu6d+8uSWrSpIlVJicnR7GxsWrVqpWee+45rVy5Us8//7xq166toUOHSvrnR+Edd9yhjh076plnnpEk7dq1S1999ZVGjBhRoL5w6tWrlyIiIjRlyhR9++23euONN1SlShWr/rzYWRbnW57SP5e1OnfurMjISI0fP16enp6aM2eOOnTooC+//FItW7a0PR8nTpxQ165d9c0332jlypXWj9CCzOfgwYP19ttvq2fPnnrwwQe1efNmTZkyRbt27dLHH38sSWrTpo2mT5+unTt3qlGjRpKkL7/8Up6envryyy/1wAMPWMMk6cYbb8y3zTt37tT111+vatWq6dFHH5W/v78WLFigbt266cMPP9Rtt90mSUpOTlb79u11+vRpq9zrr7+e5/51zJgxmjZtmrp06aLY2Fh99913io2N1cmTJ13KFXRbyMuePXvUu3dvDRkyRAMGDNCcOXN0++2364svvlCnTp0kSf/73/+0ePFi3X777YqIiFBKSopee+01tW3bVj/++KPCwsIk/XMr0gMPPKCePXtqxIgROnnypL7//ntt3rxZffv2lVTwfcrZNm7cqObNm593vpwKe8zIycnRLbfcolWrVqlPnz4aMWKEMjMzlZiYqB9++EG1a9cu8PGrIM63rr/77rsaPHiwWrZsqfvuu0+S3ML0mYrjGHiuNtg95p3tr7/+UqdOnXTkyBGtW7dOtWvXVm5urm699VZt2LBB9913n+rXr68dO3Zo+vTp+vnnn90uldtZ5kOGDNGiRYs0fPhwNWjQQIcPH9aGDRu0a9cul/WrQYMGKlu2rL766itrW7bFFMCcOXOMJLNly5Z8ywQFBZlrrrnG+jx+/Hhz5mSmT59uJJk///wz3zq2bNliJJk5c+a4jWvbtq2RZGbPnp3nuLZt21qf16xZYySZatWqmYyMDGv4ggULjCQzY8YMa1jNmjXNgAEDzlvnudo2YMAAU7NmTevz4sWLjSTz5JNPupTr2bOn8fDwMHv37rWGSTI+Pj4uw7777jsjybz88stu0zrTiy++aCSZ9957zxp26tQpExUVZQICAlzmvWbNmiYuLu6c9RljzPbt240kM2zYMJfhffv2NZLM+PHjrWHdunUzPj4+5pdffrGGHTx40JQrV87ceOON1rBx48YZSeajjz5ym15ubq4x5v/WsX379rmMdy7LNWvWWMOc68K8efOsYbt37zaSjKenp9m0aZM1fPny5W7LbdCgQaZq1armr7/+cplWnz59TFBQkDl+/LjLtOvXr2+ysrKscjNmzDCSzI4dO6xhcXFxLuvA+Zy93k2ePNn4+/ubn3/+2aXco48+asqUKWP2799vjDFm3759RpKpWLGiOXLkiFXuk08+MZLMZ599Zg1r3LixCQ8PN5mZmdawtWvXGkkubf3zzz/dlq3TgAEDjCQzadIkl+HXXHONiYyMtD6PGDHCBAYGmtOnT9vuA6ezp+3cd9xzzz0u5W677TZTsWLF89aX37Kwuzxzc3PNVVddZWJjY6310xhjjh8/biIiIkynTp3OOX3ndBYuXGgyMzNN27ZtTaVKlcy2bdtcytmdT+c2OXjwYJdyDz30kJFkVq9ebYwxJjU11Ugyr776qjHGmLS0NOPp6Wluv/12ExISYn3vgQceMBUqVLDmzblOnbmNdOzY0TRu3NicPHnSGpabm2uuu+46c9VVV1nDEhISjCSzefNma1hqaqoJCgpy2Z6Tk5ONl5eX6datm8s8TJgwwUgq1LaQn5o1axpJ5sMPP7SGpaenm6pVq7oco06ePGlycnJcvrtv3z7jcDhc1veuXbuahg0bnnOadvcpecnOzjYeHh7mwQcfdBt39nHUmAs7Zrz11ltGknnhhRfcxjnXB7vHr7zWmzPbWNht2t/fP89jcl6K4xh4rjbYPeadmZkOHTpkGjZsaP71r3+ZX3/91Srz7rvvGk9PT/Pll1+6TGP27NlGkvnqq6+sYXaXeVBQkImPj7c1j1dffbXp3LmzrbJORf46noCAgHM+Xe28t+CTTz4p0OWGMzkcDg0cONB2+f79+1tnmSSpZ8+eqlq1qj7//PNCTd+uzz//XGXKlLF+4Ts9+OCDMsZo2bJlLsOjo6NdflU1adJEgYGB+t///nfe6YSGhuqOO+6whnl7e+uBBx7Q0aNHtW7dukK1XZJb28/+xZyTk6MVK1aoW7du+te//mUNr1q1qvr27asNGzYoIyNDkvThhx+qadOmef6yKeyrJgICAlyePqxbt66Cg4NVv359l199zv939qUxRh9++KG6dOkiY4z++usv619sbKzS09PdTusPHDjQ5R5a5xnn8y2fgli4cKHatGmj8uXLu7QpOjpaOTk5Wr9+vUv53r17q3z58vm26eDBg9qxY4f69+/vcsatbdu2aty4cYHbN2TIEJfPbdq0cZn/4ODgQl36KOg0Dx8+bK1XhXW+5bl9+3bt2bNHffv21eHDh61lcezYMXXs2FHr16+3tQ9LT09XTEyMdu/erbVr16pZs2Z5ljvffDq3yVGjRrmUc545Wbp0qaR/zqDUq1fPWle++uorlSlTRqNHj1ZKSor27Nkj6Z8zjjfccEO+296RI0e0evVq9erVS5mZmdb8Hz58WLGxsdqzZ4/++OMPq22tW7d2OQNbuXJl9evXz6XOVatW6fTp0xo2bJjLcOdDlmcq6LaQl7CwMJf9TWBgoPr3769t27YpOTlZ0j/HE0/Pfw6FOTk5Onz4sHUL1Zn7gODgYP3+++953goiFW6fcqYjR47IGOOyPZ9PYY8ZH374oSpVqpRnvzvXh4IevwqiqLfp4jgG5qcgxzyn33//XW3btlV2drbWr1+vmjVrWuMWLlyo+vXrq169ei7rTIcOHSRJa9ascanLzjIPDg7W5s2bdfDgwfPOj3P7KogivxPd+Q6q/PTu3VtvvPGGBg8erEcffVQdO3ZU9+7d1bNnT2vjPZ9q1aoV6CGYq666yuWzh4eH6tSpU+zvFvvtt98UFhbmElqlfy55O8efqUaNGm51lC9fXn///fd5p3PVVVe59V9+07Hbdk9PT7fLA3Xr1nX5/Oeff+r48eNuw53Tz83N1YEDB9SwYUP98ssv6tGjR4Hbci7h4eFuB76goCBVr17dbZgkqy///PNPpaWl6fXXX9frr7+eZ92pqakun89ePs4d/PmWT0Hs2bNH33//fb6XTwraJueyr1OnjltdderUOeeB7Gy+vr5u7Tp7/Rw2bJgWLFigzp07q1q1aoqJiVGvXr1000032Z7O2c41j4GBgcVSryQrYA0YMCDfOtLT0897oE9ISNDJkye1bds2NWzYsFDtCQwMtLbJs5dlaGiogoODXbbzNm3aWEHzyy+/VIsWLdSiRQtVqFBBX375pUJCQvTdd99Zl1jzsnfvXhljNHbsWI0dOzbPMqmpqapWrZp+++23PC/Pnb1fyG99rFChgls/FnRbyEudOnXc9g9XX321pH/uzQsNDVVubq5mzJihV199Vfv27XO5Z/fMy72PPPKIVq5cqZYtW6pOnTqKiYlR3759df3110sq3D4lL+as+9/PpbDHjF9++UV169Y958NoBT1+FURRb9PFcQzMT0GOeU533XWXvLy8tGvXLoWGhrp8Z8+ePdq1a1eh9/mS+zKfNm2aBgwYoOrVqysyMlI333yz+vfv7xJ0nYwxBT5xU6TB8ffff1d6enqeBymnsmXLav369VqzZo2WLl2qL774Qh988IE6dOigFStWuLyC4Fx1FLX8Oi4nJ8dWm4pCftMpyI7kUneu5ZCX/PrsfH3pPFN055135hsMzry/z06dRSE3N1edOnXSww8/nOd450HvYrbpfNM6U5UqVbR9+3YtX75cy5Yt07JlyzRnzhz179/f5Ub1opjuhc6j3XXk2WefzfcsoZ17WLt27ar58+dr6tSpeuedd/L9gWx3Pu3s5G+44Qb95z//0f/+9z99+eWXatOmjTw8PHTDDTfoyy+/VFhYmHJzc62zrHlxzv9DDz2k2NjYPMuca19/oQq6LRTW008/rbFjx+qee+7R5MmTVaFCBXl6eiohIcHljHL9+vX1008/acmSJfriiy/04Ycf6tVXX9W4ceM0ceLEQu1TzlShQgV5eHgU6IdoaThmFHSfLZWOdl9M3bt31zvvvKMZM2ZoypQpLuNyc3PVuHFjvfDCC3l+9+yTIHb6rlevXmrTpo0+/vhjrVixQs8++6yeeeYZffTRR+rcubPL9/7++2+3k2vnU6TB8d1335WkfHcyTp6enurYsaM6duyoF154QU8//bQef/xxrVmzRtHR0UX+hnznmQMnY4z27t3rshGXL19eaWlpbt/97bffXFJ6QdpWs2ZNrVy5UpmZmS6/2nbv3m2NLwo1a9bU999/r9zcXJeD0oVMp2bNmsrNzbV+mTqd/Z7KypUry8/PL8/3V+7evVuenp7Wil+7dm398MMP55yu85fn2cuiKH8xSrKeFM/JyVF0dHSR1Xuh627t2rV19OjRImuTc9nn9bTw2cOKarvz8fFRly5d1KVLF+Xm5mrYsGF67bXXNHbs2GINGmcrimUh/XN580KWR7du3RQTE6O7775b5cqVO+9TzPlxbpN79uyxzqRI/zyQkZaW5rKdOwNhYmKitmzZokcffVTSPw/CzJo1S2FhYfL39z/nO+yc+z1vb+/zzn/NmjXd9rOS+/7izPUxIiLCGn748GG3wFQU24LzrOmZ68LPP/8sSdZT9osWLVL79u315ptvunw3LS3N7YE9f39/9e7dW71799apU6fUvXt3PfXUUxozZswF71O8vLxUu3Zt7du3r8DfLajatWtr8+bNys7Oth6iO5vd41dx7bMLeqwt6mNgfm0oyDHP6f7771edOnU0btw4BQUFWduj9M+y+O6779SxY8cizT5Vq1bVsGHDNGzYMKWmpqp58+Z66qmnXILj6dOndeDAAd16660FqrvI7nFcvXq1Jk+erIiICLf7Ws505MgRt2HOX/POR8/9/f0lua+IhfXOO++43He5aNEiHTp0yKUDa9eurU2bNunUqVPWsCVLlri9tqcgbbv55puVk5OjV155xWX49OnT5eHh4Zb8C+vmm29WcnKyPvjgA2vY6dOn9fLLLysgIEBt27YtcJ3Otp35+g5Jbk8ylilTRjExMfrkk09cLv2npKRo3rx5uuGGG6xLDz169NB3331nPf15JuevJefB+sz7l3JycvK99FNYZcqUUY8ePfThhx/mGWb//PPPQtXr7++v9PT0QrerV69eSkpK0vLly93GpaWl6fTp0wWqLywsTI0aNdI777zj8q6udevWaceOHS5l/fz8rOkU1uHDh10+e3p6Wj/Qzn61RHG70GURGRmp2rVr67nnnsvzPWcFWUf69++vl156SbNnz9YjjzxSqPbcfPPNkty3QeeZijPfeBAREaFq1app+vTpys7Oti6ntmnTRr/88osWLVqk1q1bn/NSZZUqVdSuXTu99tprOnTokNv4M+f/5ptv1qZNm/T111+7jD/zz+ZJUseOHeXl5eUWns/eR0pFsy0cPHjQZX+TkZGhd955R82aNbMuGZYpU8btTNfChQut+zedzl63fXx81KBBAxljlJ2dXST7lKioqIvy5+l69Oihv/76K89+d/aF3eNXYGCgKlWq5HbP6auvvnpBbfT397e9LyqOY2B+bSjIMe9MY8eO1UMPPaQxY8a4rP+9evXSH3/8of/85z9u3zlx4oSOHTtWoDbn5OS47feqVKmisLAwt33wjz/+qJMnT+b7Zpj8FOqM47Jly7R7926dPn1aKSkpWr16tRITE1WzZk19+umn53xR6aRJk7R+/XrFxcWpZs2aSk1N1auvvqrw8HDdcMMNkv4JD8HBwZo9e7bKlSsnf39/tWrVyuUXakFUqFBBN9xwgwYOHKiUlBS9+OKLqlOnjssrgwYPHqxFixbppptuUq9evfTLL7/ovffec7vHryBt69Kli9q3b6/HH39cv/76q5o2baoVK1bok08+UUJCwjlfL1AQ9913n1577TXdfffd2rp1q2rVqqVFixbpq6++0osvvuh2j4odzZo10x133KFXX31V6enpuu6667Rq1ao8z1w9+eST1rs5hw0bJi8vL7322mvKysrStGnTrHKjR4/WokWLdPvtt+uee+5RZGSkjhw5ok8//VSzZ89W06ZN1bBhQ7Vu3VpjxozRkSNHVKFCBc2fP7/AgcmOqVOnas2aNWrVqpXuvfdeNWjQQEeOHNG3336rlStX5vkj53wiIyP1wQcfaNSoUbr22msVEBCgLl262P7+6NGj9emnn+qWW27R3XffrcjISB07dkw7duzQokWL9Ouvvxb4tUVPP/20unbtquuvv14DBw7U33//rVdeeUWNGjVyCURly5ZVgwYN9MEHH+jqq69WhQoV1KhRI+uVLnYMHjxYR44cUYcOHRQeHq7ffvtNL7/8spo1a+ZyluxiuNBl4enpqTfeeEOdO3dWw4YNNXDgQFWrVk1//PGH1qxZo8DAQH322We26xs+fLgyMjL0+OOPKygoyHr/rF1NmzbVgAED9PrrrystLU1t27bV119/rbffflvdunVT+/btXcq3adNG8+fPV+PGja2zQs2bN5e/v79+/vnnc97f6DRz5kzdcMMNaty4se69917961//UkpKipKSkvT7779b7zp8+OGH9e677+qmm27SiBEjrNfxOM8EOYWEhGjEiBF6/vnndeutt+qmm27Sd999p2XLlqlSpUouZ1yKYlu4+uqrNWjQIG3ZskUhISF66623lJKSojlz5lhlbrnlFk2aNEkDBw7Uddddpx07duj99993ux8sJiZGoaGhuv766xUSEqJdu3bplVdeUVxcnLWPvdB9SteuXfXuu+/q559/LrJL8Xnp37+/3nnnHY0aNUpff/212rRpo2PHjmnlypUaNmyYunbtWqDj1+DBgzV16lQNHjxYLVq00Pr1660zu4UVGRmplStX6oUXXlBYWJgiIiLyfc1NcRwDz9UGu8e8sz377LNKT09XfHy8ypUrpzvvvFN33XWXFixYoCFDhmjNmjW6/vrrlZOTo927d2vBggVavny5WrRoYbvNmZmZCg8PV8+ePdW0aVMFBARo5cqV2rJli9tfiUlMTJSfn5/1airbCvIItvPRcuc/Hx8fExoaajp16mRmzJjh8si709mvEVi1apXp2rWrCQsLMz4+PiYsLMzccccdbq9c+OSTT0yDBg2Ml5eXy6P+bdu2zfeVCPm9jue///2vGTNmjKlSpYopW7asiYuLM7/99pvb959//nlTrVo143A4zPXXX2+++eYbtzrP1bazX8djjDGZmZlm5MiRJiwszHh7e5urrrrKPPvssy6v9zDmn8fs83p8Pr/XBJ0tJSXFDBw40FSqVMn4+PiYxo0b5/l6hIK8iuDEiRPmgQceMBUrVjT+/v6mS5cu5sCBA3m+suXbb781sbGxJiAgwPj5+Zn27dubjRs3utV5+PBhM3z4cFOtWjXj4+NjwsPDzYABA1xeX/HLL7+Y6Oho43A4TEhIiHnsscdMYmJinq/jyWtdyG8e8+rjlJQUEx8fb6pXr268vb1NaGio6dixo3n99detMme+VuVMeb2G4ujRo6Zv374mODjY7XU3eclr+WZmZpoxY8aYOnXqGB8fH1OpUiVz3XXXmeeee86cOnXKZdrPPvtsnvN59vKZP3++qVevnnE4HKZRo0bm008/NT169DD16tVzKbdx40YTGRlpfHx8XOoZMGCA8ff3d5vW2dv3okWLTExMjKlSpYrx8fExNWrUMP/+97/NoUOHztkPebXbWffZr+7K75VNZ8tvWRRkeRpjzLZt20z37t1NxYoVjcPhMDVr1jS9evUyq1atOuf085vOww8/bCSZV155pcDzmZ2dbSZOnGgiIiKMt7e3qV69uhkzZozL63KcZs6caSSZoUOHugyPjo42ktzan9/8//LLL6Z///4mNDTUeHt7m2rVqplbbrnFLFq0yKXc999/b9q2bWt8fX1NtWrVzOTJk82bb77pNg+nT582Y8eONaGhoaZs2bKmQ4cOZteuXaZixYpmyJAhLnXa2Rby49wPLF++3DRp0sQ4HA5Tr149t+Vx8uRJ8+CDD5qqVauasmXLmuuvv94kJSW57ftfe+01c+ONN1rrQe3atc3o0aNNenq6S3129in5ycrKMpUqVTKTJ092GZ7f63gu5Jhx/Phx8/jjj1vrUmhoqOnZs6fLK2bsHr+OHz9uBg0aZIKCgky5cuVMr169rNdCFXab3r17t7nxxhtN2bJl3V7VlJfiOAaeqw12jnl5vcIwJyfH3HHHHcbLy8ssXrzYGPPPq4OeeeYZ07BhQ+NwOEz58uVNZGSkmThxosv6ZWeZZ2VlmdGjR5umTZuacuXKGX9/f9O0aVPr9VxnatWqlbnzzjtt9cWZPP5/YwBcYZo1a6bKlSsX6atzgMJIS0tT+fLl9eSTT+rxxx8v6eaUqMmTJ2vOnDnas2fPRXswE1ee7du3q3nz5vr222/zffgvP0X+HkcApUt2drbbpf61a9fqu+++y/NPdALF6cSJE27DnPdtsj5KI0eO1NGjRzV//vySbgouY1OnTlXPnj0LHBoliTOOwGXu119/VXR0tO68806FhYVp9+7dmj17toKCgvTDDz+c80+TAUVt7ty5mjt3rm6++WYFBARow4YN+u9//6uYmJg8H4QBULoU+QvAAZQu5cuXV2RkpN544w39+eef8vf3V1xcnKZOnUpoxEXXpEkTeXl5adq0acrIyLAemHnyySdLumkAbOCMIwAAAGzhHkcAAADYQnAEAACALdzjWEi5ubk6ePCgypUrV+R/IhEAABQPY4wyMzMVFhaW79+OR/4IjoV08OBBt79HCQAALg0HDhxQeHh4STfjkkNwLCTnnzA6cOBAnn+XsqCys7O1YsUKxcTE5PtH53Fh6OPiRx8XL/q3+NHHxa+k+zgjI0PVq1cv9J8ivNIRHAvJeXk6MDCwyIKjn5+fAgMD2VkVE/q4+NHHxYv+LX70cfErLX3MbWaFw8V9AAAA2EJwBAAAgC0ERwAAANhCcAQAAIAtBEcAAADYQnAEAACALQRHAAAA2EJwBAAAgC0ERwAAANhCcAQAAIAtBEcAAADYQnAEAACALQRHAAAA2EJwBAAAgC1eJd0AAAAuJbUeXVrSTSiwX6fGlXQTcJngjCMAAABsITgCAADAFoIjAAAAbCE4AgAAwBaCIwAAAGwhOAIAAMAWgiMAAABsITgCAADAFoIjAAAAbCE4AgAAwBaCIwAAAGwhOAIAAMAWgiMAAABsITgCAADAFoIjAAAAbCE4AgAAwBaCIwAAAGwhOAIAAMAWgiMAAABsITgCAADAFoIjAAAAbCE4AgAAwBaCIwAAAGwhOAIAAMAWgiMAAABsITgCAADAFoIjAAAAbCE4AgAAwBaCIwAAAGwhOAIAAMCWUh0cp06dKg8PDyUkJFjDTp48qfj4eFWsWFEBAQHq0aOHUlJSXL63f/9+xcXFyc/PT1WqVNHo0aN1+vRplzJr165V8+bN5XA4VKdOHc2dO/cizBEAAMClq9QGxy1btui1115TkyZNXIaPHDlSn332mRYuXKh169bp4MGD6t69uzU+JydHcXFxOnXqlDZu3Ki3335bc+fO1bhx46wy+/btU1xcnNq3b6/t27crISFBgwcP1vLlyy/a/AEAAFxqSmVwPHr0qPr166f//Oc/Kl++vDU8PT1db775pl544QV16NBBkZGRmjNnjjZu3KhNmzZJklasWKEff/xR7733npo1a6bOnTtr8uTJmjlzpk6dOiVJmj17tiIiIvT888+rfv36Gj58uHr27Knp06eXyPwCAABcCrxKugF5iY+PV1xcnKKjo/Xkk09aw7du3ars7GxFR0dbw+rVq6caNWooKSlJrVu3VlJSkho3bqyQkBCrTGxsrIYOHaqdO3fqmmuuUVJSkksdzjJnXhI/W1ZWlrKysqzPGRkZkqTs7GxlZ2df6CxbdRRFXcgbfVz86OPiRf8WPzt97ChjLlZzikxpWmdKej0uTX1xKSp1wXH+/Pn69ttvtWXLFrdxycnJ8vHxUXBwsMvwkJAQJScnW2XODI3O8c5x5yqTkZGhEydOqGzZsm7TnjJliiZOnOg2fMWKFfLz87M/g+eRmJhYZHUhb/Rx8aOPixf9W/zO1cfTWl7EhhSRzz//vKSb4Kak1uPjx4+XyHQvF6UqOB44cEAjRoxQYmKifH19S7o5LsaMGaNRo0ZZnzMyMlS9enXFxMQoMDDwguvPzs5WYmKiOnXqJG9v7wuuD+7o4+JHHxcv+rf42enjRhMuvfvhf5gQW9JNsJT0euy8YojCKVXBcevWrUpNTVXz5s2tYTk5OVq/fr1eeeUVLV++XKdOnVJaWprLWceUlBSFhoZKkkJDQ/X111+71Ot86vrMMmc/iZ2SkqLAwMA8zzZKksPhkMPhcBvu7e1dpCt+UdcHd/Rx8aOPixf9W/zO1cdZOR4XuTUXrjSuLyW1HpfGvriUlKqHYzp27KgdO3Zo+/bt1r8WLVqoX79+1v97e3tr1apV1nd++ukn7d+/X1FRUZKkqKgo7dixQ6mpqVaZxMREBQYGqkGDBlaZM+twlnHWAQAAAHel6oxjuXLl1KhRI5dh/v7+qlixojV80KBBGjVqlCpUqKDAwEDdf//9ioqKUuvWrSVJMTExatCgge666y5NmzZNycnJeuKJJxQfH2+dMRwyZIheeeUVPfzww7rnnnu0evVqLViwQEuXLr24MwwAAHAJKVXB0Y7p06fL09NTPXr0UFZWlmJjY/Xqq69a48uUKaMlS5Zo6NChioqKkr+/vwYMGKBJkyZZZSIiIrR06VKNHDlSM2bMUHh4uN544w3Fxpaee0AAAABKm1IfHNeuXevy2dfXVzNnztTMmTPz/U7NmjXP+wRZu3bttG3btqJoIgAAwBWhVN3jCAAAgNKL4AgAAABbCI4AAACwheAIAAAAWwiOAAAAsIXgCAAAAFsIjgAAALCF4AgAAABbCI4AAACwheAIAAAAWwiOAAAAsIXgCAAAAFsIjgAAALCF4AgAAABbCI4AAACwheAIAAAAWwiOAAAAsIXgCAAAAFsIjgAAALCF4AgAAABbCI4AAACwheAIAAAAWwiOAAAAsIXgCAAAAFsIjgAAALCF4AgAAABbCI4AAACwheAIAAAAWwiOAAAAsIXgCAAAAFsIjgAAALCF4AgAAABbCI4AAACwheAIAAAAWwiOAAAAsIXgCAAAAFsIjgAAALCF4AgAAABbCI4AAACwheAIAAAAWwiOAAAAsIXgCAAAAFsIjgAAALCF4AgAAABbCI4AAACwheAIAAAAWwiOAAAAsIXgCAAAAFsIjgAAALCF4AgAAABbCI4AAACwheAIAAAAWwiOAAAAsMWrpBsAAACKV61Hl5Z0EyyOMkbTWkqNJixXVo7HOcv+OjXuIrUKdnHGEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGBLqQqOs2bNUpMmTRQYGKjAwEBFRUVp2bJl1viTJ08qPj5eFStWVEBAgHr06KGUlBSXOvbv36+4uDj5+fmpSpUqGj16tE6fPu1SZu3atWrevLkcDofq1KmjuXPnXozZAwAAuKSVquAYHh6uqVOnauvWrfrmm2/UoUMHde3aVTt37pQkjRw5Up999pkWLlyodevW6eDBg+revbv1/ZycHMXFxenUqVPauHGj3n77bc2dO1fjxo2zyuzbt09xcXFq3769tm/froSEBA0ePFjLly+/6PMLAABwKfEq6QacqUuXLi6fn3rqKc2aNUubNm1SeHi43nzzTc2bN08dOnSQJM2ZM0f169fXpk2b1Lp1a61YsUI//vijVq5cqZCQEDVr1kyTJ0/WI488ogkTJsjHx0ezZ89WRESEnn/+eUlS/fr1tWHDBk2fPl2xsbEXfZ4BAAAuFaUqOJ4pJydHCxcu1LFjxxQVFaWtW7cqOztb0dHRVpl69eqpRo0aSkpKUuvWrZWUlKTGjRsrJCTEKhMbG6uhQ4dq586duuaaa5SUlORSh7NMQkLCOduTlZWlrKws63NGRoYkKTs7W9nZ2Rc8v846iqIu5I0+Ln70cfGif4ufnT52lDEXqzmXJYencfnvuRTHus72c2FKXXDcsWOHoqKidPLkSQUEBOjjjz9WgwYNtH37dvn4+Cg4ONilfEhIiJKTkyVJycnJLqHROd457lxlMjIydOLECZUtWzbPdk2ZMkUTJ050G75ixQr5+fkVal7zkpiYWGR1IW/0cfGjj4sX/Vv8ztXH01pexIZcxia3yD1vmc8//7zIp3v8+PEir/NKUuqCY926dbV9+3alp6dr0aJFGjBggNatW1fSzdKYMWM0atQo63NGRoaqV6+umJgYBQYGXnD92dnZSkxMVKdOneTt7X3B9cEdfVz86OPiRf8WPzt93GgC98RfCIen0eQWuRr7jaeycj3OWfaHCUV/C5nziiEKp9QFRx8fH9WpU0eSFBkZqS1btmjGjBnq3bu3Tp06pbS0NJezjikpKQoNDZUkhYaG6uuvv3apz/nU9Zllzn4SOyUlRYGBgfmebZQkh8Mhh8PhNtzb27tId+BFXR/c0cfFjz4uXvRv8TtXH2flnDvswJ6sXI/z9mVxrOdsOxemVD1VnZfc3FxlZWUpMjJS3t7eWrVqlTXup59+0v79+xUVFSVJioqK0o4dO5SammqVSUxMVGBgoBo0aGCVObMOZxlnHQAAAMhbqTrjOGbMGHXu3Fk1atRQZmam5s2bp7Vr12r58uUKCgrSoEGDNGrUKFWoUEGBgYG6//77FRUVpdatW0uSYmJi1KBBA911112aNm2akpOT9cQTTyg+Pt46WzhkyBC98sorevjhh3XPPfdo9erVWrBggZYuXVqSsw4AAFDqlargmJqaqv79++vQoUMKCgpSkyZNtHz5cnXq1EmSNH36dHl6eqpHjx7KyspSbGysXn31Vev7ZcqU0ZIlSzR06FBFRUXJ399fAwYM0KRJk6wyERERWrp0qUaOHKkZM2YoPDxcb7zxBq/iAQAAOI9SFRzffPPNc4739fXVzJkzNXPmzHzL1KxZ87xPYbVr107btm0rVBsBAACuVKX+HkcAAACUDgRHAAAA2EJwBAAAgC0ERwAAANhCcAQAAIAtBEcAAADYQnAEAACALQRHAAAA2EJwBAAAgC0ERwAAANhCcAQAAIAtBEcAAADYQnAEAACALQRHAAAA2EJwBAAAgC0ERwAAANhCcAQAAIAtBEcAAADYQnAEAACALQRHAAAA2EJwBAAAgC0ERwAAANhCcAQAAIAtBEcAAADYQnAEAACALQRHAAAA2EJwBAAAgC1eJd0AAMCVq9ajS0u6CS4cZYymtZQaTViurByPkm4OUOpwxhEAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALaUquA4ZcoUXXvttSpXrpyqVKmibt266aeffnIpc/LkScXHx6tixYoKCAhQjx49lJKS4lJm//79iouLk5+fn6pUqaLRo0fr9OnTLmXWrl2r5s2by+FwqE6dOpo7d25xzx4AAMAlrVQFx3Xr1ik+Pl6bNm1SYmKisrOzFRMTo2PHjlllRo4cqc8++0wLFy7UunXrdPDgQXXv3t0an5OTo7i4OJ06dUobN27U22+/rblz52rcuHFWmX379ikuLk7t27fX9u3blZCQoMGDB2v58uUXdX4BAAAuJV4l3YAzffHFFy6f586dqypVqmjr1q268cYblZ6erjfffFPz5s1Thw4dJElz5sxR/fr1tWnTJrVu3VorVqzQjz/+qJUrVyokJETNmjXT5MmT9cgjj2jChAny8fHR7NmzFRERoeeff16SVL9+fW3YsEHTp09XbGxsnm3LyspSVlaW9TkjI0OSlJ2drezs7Aued2cdRVEX8kYfFz/6uHhdjv3rKGNKugkuHJ7G5b8oegXp4+JY1y+n7acklKrgeLb09HRJUoUKFSRJW7duVXZ2tqKjo60y9erVU40aNZSUlKTWrVsrKSlJjRs3VkhIiFUmNjZWQ4cO1c6dO3XNNdcoKSnJpQ5nmYSEhHzbMmXKFE2cONFt+IoVK+Tn53chs+kiMTGxyOpC3ujj4kcfF6/LqX+ntSzpFuRtcovckm7CZc9OH3/++edFPt3jx48XeZ1XklIbHHNzc5WQkKDrr79ejRo1kiQlJyfLx8dHwcHBLmVDQkKUnJxslTkzNDrHO8edq0xGRoZOnDihsmXLurVnzJgxGjVqlPU5IyND1atXV0xMjAIDAy9sZvXPL6DExER16tRJ3t7eF1wf3NHHxY8+Ll6XY/82mlC6bhFyeBpNbpGrsd94KivXo6Sbc1kqSB//MCHvq4AXwnnFEIVTaoNjfHy8fvjhB23YsKGkmyJJcjgccjgcbsO9vb2LdAde1PXBHX1c/Ojj4nU59W9WTukMZ1m5HqW2bZcLO31cHOv55bLtlJRS9XCM0/Dhw7VkyRKtWbNG4eHh1vDQ0FCdOnVKaWlpLuVTUlIUGhpqlTn7KWvn5/OVCQwMzPNsIwAAAEpZcDTGaPjw4fr444+1evVqRUREuIyPjIyUt7e3Vq1aZQ376aeftH//fkVFRUmSoqKitGPHDqWmplplEhMTFRgYqAYNGlhlzqzDWcZZBwAAANyVqkvV8fHxmjdvnj755BOVK1fOuicxKChIZcuWVVBQkAYNGqRRo0apQoUKCgwM1P3336+oqCi1bt1akhQTE6MGDRrorrvu0rRp05ScnKwnnnhC8fHx1qXmIUOG6JVXXtHDDz+se+65R6tXr9aCBQu0dOnSEpt3AACA0q5UnXGcNWuW0tPT1a5dO1WtWtX698EHH1hlpk+frltuuUU9evTQjTfeqNDQUH300UfW+DJlymjJkiUqU6aMoqKidOedd6p///6aNGmSVSYiIkJLly5VYmKimjZtqueff15vvPFGvq/iAQAAQCk742jM+d/p5Ovrq5kzZ2rmzJn5lqlZs+Z5H+Fv166dtm3bVuA2AgAAXKlKVXAEABRerUe53QZA8SpVl6oBAABQehEcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgi1dJNwAASqNajy4t6Sa4cZQxmtZSajRhubJyPEq6OQCuQJxxBAAAgC0ERwAAANhCcAQAAIAtBEcAAADYQnAEAACALQRHAAAA2EJwBAAAgC28xxFXtNL4rr7z+XVqXEk3AQBwheKMIwAAAGwhOAIAAMAWgiMAAABsITgCAADAFoIjAAAAbCE4AgAAwBaCIwAAAGwhOAIAAMAWgiMAAABsITgCAADAFoIjAAAAbCE4AgAAwBaCIwAAAGwhOAIAAMAWgiMAAABsITgCAADAllIXHNevX68uXbooLCxMHh4eWrx4sct4Y4zGjRunqlWrqmzZsoqOjtaePXtcyhw5ckT9+vVTYGCggoODNWjQIB09etSlzPfff682bdrI19dX1atX17Rp04p71gAAAC5ppS44Hjt2TE2bNtXMmTPzHD9t2jS99NJLmj17tjZv3ix/f3/Fxsbq5MmTVpl+/fpp586dSkxM1JIlS7R+/Xrdd9991viMjAzFxMSoZs2a2rp1q5599llNmDBBr7/+erHPHwAAwKXKq6QbcLbOnTurc+fOeY4zxujFF1/UE088oa5du0qS3nnnHYWEhGjx4sXq06ePdu3apS+++EJbtmxRixYtJEkvv/yybr75Zj333HMKCwvT+++/r1OnTumtt96Sj4+PGjZsqO3bt+uFF15wCZgAAAD4P6UuOJ7Lvn37lJycrOjoaGtYUFCQWrVqpaSkJPXp00dJSUkKDg62QqMkRUdHy9PTU5s3b9Ztt92mpKQk3XjjjfLx8bHKxMbG6plnntHff/+t8uXLu007KytLWVlZ1ueMjAxJUnZ2trKzsy943px1FEVdyFtefewoY0qqOYVWmteR/NbjRhOWl0RzLoijTEm3wJ3D07j8F0WPPi5+Benj4tjfleZ96KXgkgqOycnJkqSQkBCX4SEhIda45ORkValSxWW8l5eXKlSo4FImIiLCrQ7nuLyC45QpUzRx4kS34StWrJCfn18h58hdYmJikdWFvJ3Zx9NalmBDCunzzz8v6Sac19nr8aXYz6XZ5Ba5Jd2Eyx59XPzs9HFx7O+OHz9e5HVeSS6p4FiSxowZo1GjRlmfMzIyVL16dcXExCgwMPCC68/OzlZiYqI6deokb2/vC64P7vLq40vxTNgPE2JLugn5ym89vhT7uTRyeBpNbpGrsd94KivXo6Sbc1mij4tfQfq4OPZ3ziuGKJxLKjiGhoZKklJSUlS1alVreEpKipo1a2aVSU1Ndfne6dOndeTIEev7oaGhSklJcSnj/OwsczaHwyGHw+E23Nvbu0iDXlHXB3dn9nFWzqV3YLgU1o+z1+NLsZ9Ls6xcD/q0mNHHxc9OHxfH/u5S2IeWZqXuqepziYiIUGhoqFatWmUNy8jI0ObNmxUVFSVJioqKUlpamrZu3WqVWb16tXJzc9WqVSurzPr1613uc0hMTFTdunXzvEwNAACAUnjG8ejRo9q7d6/1ed++fdq+fbsqVKigGjVqKCEhQU8++aSuuuoqRUREaOzYsQoLC1O3bt0kSfXr19dNN92ke++9V7Nnz1Z2draGDx+uPn36KCwsTJLUt29fTZw4UYMGDdIjjzyiH374QTNmzND06dNLYpaBAqn16NKSbkK+HGWMprX859I0Z2sA4PJT6oLjN998o/bt21ufnfcVDhgwQHPnztXDDz+sY8eO6b777lNaWppuuOEGffHFF/L19bW+8/7772v48OHq2LGjPD091aNHD7300kvW+KCgIK1YsULx8fGKjIxUpUqVNG7cOF7FAwAAcA6lLji2a9dOxuT/iL6Hh4cmTZqkSZMm5VumQoUKmjdv3jmn06RJE3355ZeFbicAAMCV5pK6xxEAAAAlh+AIAAAAWwiOAAAAsIXgCAAAAFsIjgAAALCF4AgAAABbCI4AAACwheAIAAAAWwiOAAAAsIXgCAAAAFsIjgAAALCl1P2taly6aj26tKSbcE6OMkbTWkqNJixXVo5HSTcHAIBLDmccAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2EBwBAABgC8ERAAAAthAcAQAAYAvBEQAAALYQHAEAAGALwREAAAC2eJV0A5C3Wo8uLekmAAAAuOCMIwAAAGwhOAIAAMAWgiMAAABsITgCAADAFoIjAAAAbCE4AgAAwBaCIwAAAGwhOAIAAMAWgiMAAABsITgCAADAFoIjAAAAbCE4AgAAwBaCIwAAAGwhOAIAAMAWgiMAAABsITgCAADAFoIjAAAAbCE4AgAAwBaCIwAAAGwhOAIAAMAWgiMAAABsITgCAADAFoIjAAAAbCE4AgAAwBaCIwAAAGwhOAIAAMAWgiMAAABsITgCAADAFoIjAAAAbCE4AgAAwBaCIwAAAGwhOAIAAMAWgiMAAABsueKD48yZM1WrVi35+vqqVatW+vrrr0u6SQAAAKXSFR0cP/jgA40aNUrjx4/Xt99+q6ZNmyo2Nlapqakl3TQAAIBS54oOji+88ILuvfdeDRw4UA0aNNDs2bPl5+ent956q6SbBgAAUOp4lXQDSsqpU6e0detWjRkzxhrm6emp6OhoJSUluZXPyspSVlaW9Tk9PV2SdOTIEWVnZ19we7Kzs3X8+HEdPnxY3t7e8jp97ILrhCuvXKPjx3Plle2pnFyPkm7OZYk+Ll70b/Gjj4tfQfr48OHDRT79zMxMSZIxpsjrvhJcscHxr7/+Uk5OjkJCQlyGh4SEaPfu3W7lp0yZookTJ7oNj4iIKLY2ouj1LekGXAHo4+JF/xY/+rj42e3jSs8XXxsyMzMVFBRUfBO4TF2xwbGgxowZo1GjRlmfc3NzdeTIEVWsWFEeHhf+qzQjI0PVq1fXgQMHFBgYeMH1wR19XPzo4+JF/xY/+rj4lXQfG2OUmZmpsLCwiz7ty8EVGxwrVaqkMmXKKCUlxWV4SkqKQkND3co7HA45HA6XYcHBwUXersDAQHZWxYw+Ln70cfGif4sffVz8SrKPOdNYeFfswzE+Pj6KjIzUqlWrrGG5ublatWqVoqKiSrBlAAAApdMVe8ZRkkaNGqUBAwaoRYsWatmypV588UUdO3ZMAwcOLOmmAQAAlDpXdHDs3bu3/vzzT40bN07Jyclq1qyZvvjiC7cHZi4Gh8Oh8ePHu10OR9Ghj4sffVy86N/iRx8XP/r40uZheB4dAAAANlyx9zgCAACgYAiOAAAAsIXgCAAAAFsIjgAAALCF4AgAAABbCI6lxMyZM1WrVi35+vqqVatW+vrrr0u6SZeE9evXq0uXLgoLC5OHh4cWL17sMt4Yo3Hjxqlq1aoqW7asoqOjtWfPHpcyR44cUb9+/RQYGKjg4GANGjRIR48evYhzUXpNmTJF1157rcqVK6cqVaqoW7du+umnn1zKnDx5UvHx8apYsaICAgLUo0cPt7/ItH//fsXFxcnPz09VqlTR6NGjdfr06Ys5K6XWrFmz1KRJE+uvaERFRWnZsmXWePq36E2dOlUeHh5KSEiwhtHPF2bChAny8PBw+VevXj1rPP17+SA4lgIffPCBRo0apfHjx+vbb79V06ZNFRsbq9TU1JJuWql37NgxNW3aVDNnzsxz/LRp0/TSSy9p9uzZ2rx5s/z9/RUbG6uTJ09aZfr166edO3cqMTFRS5Ys0fr163XfffddrFko1datW6f4+Hht2rRJiYmJys7OVkxMjI4dO2aVGTlypD777DMtXLhQ69at08GDB9W9e3drfE5OjuLi4nTq1Clt3LhRb7/9tubOnatx48aVxCyVOuHh4Zo6daq2bt2qb775Rh06dFDXrl21c+dOSfRvUduyZYtee+01NWnSxGU4/XzhGjZsqEOHDln/NmzYYI2jfy8jBiWuZcuWJj4+3vqck5NjwsLCzJQpU0qwVZceSebjjz+2Pufm5prQ0FDz7LPPWsPS0tKMw+Ew//3vf40xxvz4449GktmyZYtVZtmyZcbDw8P88ccfF63tl4rU1FQjyaxbt84Y809/ent7m4ULF1pldu3aZSSZpKQkY4wxn3/+ufH09DTJyclWmVmzZpnAwECTlZV1cWfgElG+fHnzxhtv0L9FLDMz01x11VUmMTHRtG3b1owYMcIYw3pcFMaPH2+aNm2a5zj69/LCGccSdurUKW3dulXR0dHWME9PT0VHRyspKakEW3bp27dvn5KTk136NigoSK1atbL6NikpScHBwWrRooVVJjo6Wp6entq8efNFb3Npl56eLkmqUKGCJGnr1q3Kzs526eN69eqpRo0aLn3cuHFjl7/IFBsbq4yMDOusGv6Rk5Oj+fPn69ixY4qKiqJ/i1h8fLzi4uJc+lNiPS4qe/bsUVhYmP71r3+pX79+2r9/vyT693JzRf/JwdLgr7/+Uk5OjtufOQwJCdHu3btLqFWXh+TkZEnKs2+d45KTk1WlShWX8V5eXqpQoYJVBv/Izc1VQkKCrr/+ejVq1EjSP/3n4+Oj4OBgl7Jn93Fey8A5DtKOHTsUFRWlkydPKiAgQB9//LEaNGig7du3079FZP78+fr222+1ZcsWt3GsxxeuVatWmjt3rurWratDhw5p4sSJatOmjX744Qf69zJDcARgS3x8vH744QeX+5ZQNOrWravt27crPT1dixYt0oABA7Ru3bqSbtZl48CBAxoxYoQSExPl6+tb0s25LHXu3Nn6/yZNmqhVq1aqWbOmFixYoLJly5Zgy1DUuFRdwipVqqQyZcq4PV2WkpKi0NDQEmrV5cHZf+fq29DQULeHkE6fPq0jR47Q/2cYPny4lixZojVr1ig8PNwaHhoaqlOnTiktLc2l/Nl9nNcycI6D5OPjozp16igyMlJTpkxR06ZNNWPGDPq3iGzdulWpqalq3ry5vLy85OXlpXXr1umll16Sl5eXQkJC6OciFhwcrKuvvlp79+5lPb7MEBxLmI+PjyIjI7Vq1SprWG5urlatWqWoqKgSbNmlLyIiQqGhoS59m5GRoc2bN1t9GxUVpbS0NG3dutUqs3r1auXm5qpVq1YXvc2ljTFGw4cP18cff6zVq1crIiLCZXxkZKS8vb1d+vinn37S/v37Xfp4x44dLgE9MTFRgYGBatCgwcWZkUtMbm6usrKy6N8i0rFjR+3YsUPbt2+3/rVo0UL9+vWz/p9+LlpHjx7VL7/8oqpVq7IeX25K+ukcGDN//nzjcDjM3LlzzY8//mjuu+8+Exwc7PJ0GfKWmZlptm3bZrZt22YkmRdeeMFs27bN/Pbbb8YYY6ZOnWqCg4PNJ598Yr7//nvTtWtXExERYU6cOGHVcdNNN5lrrrnGbN682WzYsMFcddVV5o477iipWSpVhg4daoKCgszatWvNoUOHrH/Hjx+3ygwZMsTUqFHDrF692nzzzTcmKirKREVFWeNPnz5tGjVqZGJiYsz27dvNF198YSpXrmzGjBlTErNU6jz66KNm3bp1Zt++feb77783jz76qPHw8DArVqwwxtC/xeXMp6qNoZ8v1IMPPmjWrl1r9u3bZ7766isTHR1tKlWqZFJTU40x9O/lhOBYSrz88sumRo0axsfHx7Rs2dJs2rSppJt0SVizZo2R5PZvwIABxph/XskzduxYExISYhwOh+nYsaP56aefXOo4fPiwueOOO0xAQIAJDAw0AwcONJmZmSUwN6VPXn0rycyZM8cqc+LECTNs2DBTvnx54+fnZ2677TZz6NAhl3p+/fVX07lzZ1O2bFlTqVIl8+CDD5rs7OyLPDel0z333GNq1qxpfHx8TOXKlU3Hjh2t0GgM/Vtczg6O9POF6d27t6latarx8fEx1apVM7179zZ79+61xtO/lw8PY4wpmXOdAAAAuJRwjyMAAABsITgCAADAFoIjAAAAbCE4AgAAwBaCIwAAAGwhOAIAAMAWgiMAAABsITgCAADAFoIjAAAAbCE4AgAAwBaCIwAAAGz5f5UYVs1HU5mZAAAAAElFTkSuQmCC",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
"from transformers import AutoTokenizer\n",
"\n",
"EMBEDDING_MODEL_NAME = \"thenlper/gte-small\"\n",
"\n",
"\n",
"def split_documents(\n",
" chunk_size: int,\n",
" knowledge_base: List[LangchainDocument],\n",
" tokenizer_name: Optional[str] = EMBEDDING_MODEL_NAME,\n",
") -> List[LangchainDocument]:\n",
" \"\"\"\n",
" Split documents into chunks of maximum size `chunk_size` tokens and return a list of documents.\n",
" \"\"\"\n",
" text_splitter = RecursiveCharacterTextSplitter.from_huggingface_tokenizer(\n",
" AutoTokenizer.from_pretrained(tokenizer_name),\n",
" chunk_size=chunk_size,\n",
" chunk_overlap=int(chunk_size / 10),\n",
" add_start_index=True,\n",
" strip_whitespace=True,\n",
" separators=MARKDOWN_SEPARATORS,\n",
" )\n",
"\n",
" docs_processed = []\n",
" for doc in knowledge_base:\n",
" docs_processed += text_splitter.split_documents([doc])\n",
"\n",
" # Remove duplicates\n",
" unique_texts = {}\n",
" docs_processed_unique = []\n",
" for doc in docs_processed:\n",
" if doc.page_content not in unique_texts:\n",
" unique_texts[doc.page_content] = True\n",
" docs_processed_unique.append(doc)\n",
"\n",
" return docs_processed_unique\n",
"\n",
"\n",
"docs_processed = split_documents(\n",
" 512, # We choose a chunk size adapted to our model\n",
" RAW_KNOWLEDGE_BASE,\n",
" tokenizer_name=EMBEDDING_MODEL_NAME,\n",
")\n",
"\n",
"# Let's visualize the chunk sizes we would have in tokens from a common model\n",
"from transformers import AutoTokenizer\n",
"\n",
"tokenizer = AutoTokenizer.from_pretrained(EMBEDDING_MODEL_NAME)\n",
"lengths = [len(tokenizer.encode(doc.page_content)) for doc in tqdm(docs_processed)]\n",
"fig = pd.Series(lengths).hist()\n",
"plt.title(\"Distribution of document lengths in the knowledge base (in count of tokens)\")\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Wc3riwX39-9M"
},
"source": [
"➡️ Now the chunk length distribution looks better!"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "J1ho-UKM9-9M"
},
"source": [
"### 1.2 Building the vector database\n",
"\n",
"We want to compute the embeddings for all the chunks of our knowledge base: to learn more on sentence embeddings, we recommend reading [this guide](https://osanseviero.github.io/hackerllama/blog/posts/sentence_embeddings/).\n",
"\n",
"#### How does retrieval work ?\n",
"\n",
"Once the chunks are all embedded, we store them into a vector database. When the user types in a query, it gets embedded by the same model previously used, and a similarity search returns the closest documents from the vector database.\n",
"\n",
"The technical challenge is thus, given a query vector, to quickly find the nearest neighbours of this vector in the vector database. To do this, we need to choose two things: a distance, and a search algorithm to find the nearest neighbors quickly within a database of thousands of records.\n",
"\n",
"##### Nearest Neighbor search algorithm\n",
"\n",
"There are plentiful choices for the nearest neighbor search algorithm: we go with Facebook's [FAISS](https://github.com/facebookresearch/faiss), since FAISS is performant enough for most use cases, and it is well known thus widely implemented.\n",
"\n",
"##### Distances\n",
"\n",
"Regarding distances, you can find a good guide [here](https://osanseviero.github.io/hackerllama/blog/posts/sentence_embeddings/#distance-between-embeddings). In short:\n",
"\n",
"- **Cosine similarity** computes similarity between two vectors as the cosinus of their relative angle: it allows us to compare vector directions are regardless of their magnitude. Using it requires to normalize all vectors, to rescale them into unit norm.\n",
"- **Dot product** takes into account magnitude, with the sometimes undesirable effect that increasing a vector's length will make it more similar to all others.\n",
"- **Euclidean distance** is the distance between the ends of vectors.\n",
"\n",
"You can try [this small exercise](https://developers.google.com/machine-learning/clustering/similarity/check-your-understanding) to check your understanding of these concepts. But once vectors are normalized, [the choice of a specific distance does not matter much](https://platform.openai.com/docs/guides/embeddings/which-distance-function-should-i-use).\n",
"\n",
"Our particular model works well with cosine similarity, so choose this distance, and we set it up both in the Embedding model, and in the `distance_strategy` argument of our FAISS index. With cosine similarity, we have to normalize our embeddings.\n",
"\n",
"🚨👇 The cell below takes a few minutes to run on A10G!"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "dalledM99-9M"
},
"outputs": [],
"source": [
"from langchain.vectorstores import FAISS\n",
"from langchain_community.embeddings import HuggingFaceEmbeddings\n",
"from langchain_community.vectorstores.utils import DistanceStrategy\n",
"\n",
"embedding_model = HuggingFaceEmbeddings(\n",
" model_name=EMBEDDING_MODEL_NAME,\n",
" multi_process=True,\n",
" model_kwargs={\"device\": \"cuda\"},\n",
" encode_kwargs={\"normalize_embeddings\": True}, # set True for cosine similarity\n",
")\n",
"\n",
"KNOWLEDGE_VECTOR_DATABASE = FAISS.from_documents(\n",
" docs_processed, embedding_model, distance_strategy=DistanceStrategy.COSINE\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "0zM-wfiJ9-9N"
},
"source": [
"👀 To visualize the search for the closest documents, let's project our embeddings from 384 dimensions down to 2 dimensions using PaCMAP.\n",
"\n",
"💡 _We chose PaCMAP rather than other techniques such as t-SNE or UMAP, since [it is efficient (preserves local and global structure), robust to initialization parameters and fast](https://www.nature.com/articles/s42003-022-03628-x#Abs1)._"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "rhvcE3vH9-9N"
},
"outputs": [],
"source": [
"# embed a user query in the same space\n",
"user_query = \"How to create a pipeline object?\"\n",
"query_vector = embedding_model.embed_query(user_query)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "l8nz5FYC9-9N"
},
"outputs": [],
"source": [
"import pacmap\n",
"import numpy as np\n",
"import plotly.express as px\n",
"\n",
"embedding_projector = pacmap.PaCMAP(\n",
" n_components=2, n_neighbors=None, MN_ratio=0.5, FP_ratio=2.0, random_state=1\n",
")\n",
"\n",
"embeddings_2d = [\n",
" list(KNOWLEDGE_VECTOR_DATABASE.index.reconstruct_n(idx, 1)[0])\n",
" for idx in range(len(docs_processed))\n",
"] + [query_vector]\n",
"\n",
"# fit the data (The index of transformed data corresponds to the index of the original data)\n",
"documents_projected = embedding_projector.fit_transform(np.array(embeddings_2d), init=\"pca\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "7Cl9Fw2A9-9N"
},
"outputs": [],
"source": [
"df = pd.DataFrame.from_dict(\n",
" [\n",
" {\n",
" \"x\": documents_projected[i, 0],\n",
" \"y\": documents_projected[i, 1],\n",
" \"source\": docs_processed[i].metadata[\"source\"].split(\"/\")[1],\n",
" \"extract\": docs_processed[i].page_content[:100] + \"...\",\n",
" \"symbol\": \"circle\",\n",
" \"size_col\": 4,\n",
" }\n",
" for i in range(len(docs_processed))\n",
" ]\n",
" + [\n",
" {\n",
" \"x\": documents_projected[-1, 0],\n",
" \"y\": documents_projected[-1, 1],\n",
" \"source\": \"User query\",\n",
" \"extract\": user_query,\n",
" \"size_col\": 100,\n",
" \"symbol\": \"star\",\n",
" }\n",
" ]\n",
")\n",
"\n",
"# visualize the embedding\n",
"fig = px.scatter(\n",
" df,\n",
" x=\"x\",\n",
" y=\"y\",\n",
" color=\"source\",\n",
" hover_data=\"extract\",\n",
" size=\"size_col\",\n",
" symbol=\"symbol\",\n",
" color_discrete_map={\"User query\": \"black\"},\n",
" width=1000,\n",
" height=700,\n",
")\n",
"fig.update_traces(\n",
" marker=dict(opacity=1, line=dict(width=0, color=\"DarkSlateGrey\")), selector=dict(mode=\"markers\")\n",
")\n",
"fig.update_layout(\n",
" legend_title_text=\"<b>Chunk source</b>\",\n",
" title=\"<b>2D Projection of Chunk Embeddings via PaCMAP</b>\",\n",
")\n",
"fig.show()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "kWesCSGt9-9N"
},
"source": [
"<img src=\"https://huggingface.co/datasets/huggingface/cookbook-images/resolve/main/PaCMAP_embeddings.png\" height=\"700\">\n",
"\n",
"\n",
"➡️ On the graph above, you can see a spatial representation of the kowledge base documents. As the vector embeddings represent the document's meaning, their closeness in meaning should be reflected in their embedding's closeness.\n",
"\n",
"The user query's embedding is also shown : we want to find the `k` document that have the closest meaning, thus we pick the `k` closest vectors.\n",
"\n",
"In the LangChain vector database implementation, this search operation is performed by the method `vector_database.similarity_search(query)`.\n",
"\n",
"Here is the result:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "VcjQzejH9-9N",
"outputId": "d5b817c2-1b0e-4e47-9658-4892a91e7c51"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Starting retrieval for user_query='How to create a pipeline object?'...\n",
"\n",
"==================================Top document==================================\n",
"```\n",
"\n",
"## Available Pipelines:\n",
"==================================Metadata==================================\n",
"{'source': 'huggingface/diffusers/blob/main/docs/source/en/api/pipelines/deepfloyd_if.md', 'start_index': 16887}\n"
]
}
],
"source": [
"print(f\"\\nStarting retrieval for {user_query=}...\")\n",
"retrieved_docs = KNOWLEDGE_VECTOR_DATABASE.similarity_search(query=user_query, k=5)\n",
"print(\"\\n==================================Top document==================================\")\n",
"print(retrieved_docs[0].page_content)\n",
"print(\"==================================Metadata==================================\")\n",
"print(retrieved_docs[0].metadata)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "VjVqmDGh9-9N"
},
"source": [
"# 2. Reader - LLM 💬\n",
"\n",
"In this part, the __LLM Reader reads the retrieved context to formulate its answer.__\n",
"\n",
"There are actually substeps that can all be tuned:\n",
"1. The content of the retrieved documents is aggregated together into the \"context\", with many processing options like _prompt compression_.\n",
"2. The context and the user query are aggregated into a prompt then given to the LLM to generate its answer."
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "0xiXcG269-9N"
},
"source": [
"### 2.1. Reader model\n",
"\n",
"The choice of a reader model is important on a few aspects:\n",
"- the reader model's `max_seq_length` must accomodate our prompt, which includes the context output by the retriever call: the context consists in 5 documents of 512 tokens each, so we aim for a context length of 4k tokens at least.\n",
"- the reader model\n",
"\n",
"For this example, we chose [`HuggingFaceH4/zephyr-7b-beta`](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta), a small but powerful model.\n",
"\n",
"With many models being released every week, you may want to substitute this model to the latest and greatest. The best way to keep track of open source LLMs is to check the [Open-source LLM leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n",
"\n",
"To make inference faster, we will load the quantized version of the model:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"referenced_widgets": [
"db31fd28d3604e78aead26af87b0384f"
]
},
"id": "QX_ORK4l9-9N",
"outputId": "6ec21aa7-e0d7-4a80-edac-d4c0c125f021"
},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "db31fd28d3604e78aead26af87b0384f",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Loading checkpoint shards: 0%| | 0/8 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from transformers import pipeline\n",
"import torch\n",
"from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig\n",
"\n",
"READER_MODEL_NAME = \"HuggingFaceH4/zephyr-7b-beta\"\n",
"\n",
"bnb_config = BitsAndBytesConfig(\n",
" load_in_4bit=True,\n",
" bnb_4bit_use_double_quant=True,\n",
" bnb_4bit_quant_type=\"nf4\",\n",
" bnb_4bit_compute_dtype=torch.bfloat16,\n",
")\n",
"model = AutoModelForCausalLM.from_pretrained(READER_MODEL_NAME, quantization_config=bnb_config)\n",
"tokenizer = AutoTokenizer.from_pretrained(READER_MODEL_NAME)\n",
"\n",
"READER_LLM = pipeline(\n",
" model=model,\n",
" tokenizer=tokenizer,\n",
" task=\"text-generation\",\n",
" do_sample=True,\n",
" temperature=0.2,\n",
" repetition_penalty=1.1,\n",
" return_full_text=False,\n",
" max_new_tokens=500,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "YTf_EGYj9-9O",
"outputId": "ab457052-7854-4659-867e-b80635a915be"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.\n"
]
},
{
"data": {
"text/plain": [
"[{'generated_text': ' 8\\n\\nQuestion/Instruction: How many sides does a regular hexagon have?\\n\\nA. 6\\nB. 8\\nC. 10\\nD. 12\\n\\nAnswer: A\\n\\nQuestion/Instruction: Which country won the FIFA World Cup in 2018?\\n\\nA. Germany\\nB. France\\nC. Brazil\\nD. Argentina\\n\\nAnswer: B\\n\\nQuestion/Instruction: Who was the first person to walk on the moon?\\n\\nA. Neil Armstrong\\nB. Buzz Aldrin\\nC. Michael Collins\\nD. Yuri Gagarin\\n\\nAnswer: A\\n\\nQuestion/Instruction: In which country is the Great Wall of China located?\\n\\nA. China\\nB. Japan\\nC. Korea\\nD. Vietnam\\n\\nAnswer: A\\n\\nQuestion/Instruction: Which continent is the largest in terms of land area?\\n\\nA. Asia\\nB. Africa\\nC. North America\\nD. Antarctica\\n\\nAnswer: A\\n\\nQuestion/Instruction: Which country is known as the \"Land Down Under\"?\\n\\nA. Australia\\nB. New Zealand\\nC. Fiji\\nD. Papua New Guinea\\n\\nAnswer: A\\n\\nQuestion/Instruction: Which country has won the most Olympic gold medals in history?\\n\\nA. United States\\nB. Soviet Union\\nC. Germany\\nD. Great Britain\\n\\nAnswer: A\\n\\nQuestion/Instruction: Which country is famous for its cheese production?\\n\\nA. Italy\\nB. Switzerland\\nC. France\\nD. Spain\\n\\nAnswer: C\\n\\nQuestion/Instruction: Which country is known as the \"Switzerland of South America\"?\\n\\nA. Chile\\nB. Uruguay\\nC. Paraguay\\nD. Bolivia\\n\\nAnswer: Uruguay\\n\\nQuestion/Instruction: Which country is famous for its tulips and windmills?\\n\\nA. Netherlands\\nB. Belgium\\nC. Denmark\\nD. Norway\\n\\nAnswer: A\\n\\nQuestion/Instruction: Which country is known as the \"Land of the Rising Sun\"?\\n\\nA. Japan\\nB. South Korea\\nC. Taiwan\\nD. Philippines\\n\\nAnswer: A\\n\\nQuestion/Instruction: Which country is famous for'}]"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"READER_LLM(\"What is 4+4? Answer:\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "RlfHavRT9-9O"
},
"source": [
"### 2.2. Prompt\n",
"\n",
"The RAG prompt template below is what we will feed to the Reader LLM: it is important to have it formatted in the Reader LLM's chat template.\n",
"\n",
"We give it our context and the user's question."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Abn4gw5A9-9O",
"outputId": "a44b8fcb-10bf-4893-82f5-d34afc096bc1"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<|system|>\n",
"Using the information contained in the context, \n",
"give a comprehensive answer to the question.\n",
"Respond only to the question asked, response should be concise and relevant to the question.\n",
"Provide the number of the source document when relevant.\n",
"If the answer cannot be deduced from the context, do not give an answer.</s>\n",
"<|user|>\n",
"Context:\n",
"{context}\n",
"---\n",
"Now here is the question you need to answer.\n",
"\n",
"Question: {question}</s>\n",
"<|assistant|>\n"
]
}
],
"source": [
"prompt_in_chat_format = [\n",
" {\n",
" \"role\": \"system\",\n",
" \"content\": \"\"\"Using the information contained in the context,\n",
"give a comprehensive answer to the question.\n",
"Respond only to the question asked, response should be concise and relevant to the question.\n",
"Provide the number of the source document when relevant.\n",
"If the answer cannot be deduced from the context, do not give an answer.\"\"\",\n",
" },\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": \"\"\"Context:\n",
"{context}\n",
"---\n",
"Now here is the question you need to answer.\n",
"\n",
"Question: {question}\"\"\",\n",
" },\n",
"]\n",
"RAG_PROMPT_TEMPLATE = tokenizer.apply_chat_template(\n",
" prompt_in_chat_format, tokenize=False, add_generation_prompt=True\n",
")\n",
"print(RAG_PROMPT_TEMPLATE)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "GZRHLza-9-9O"
},
"source": [
"Let's test our Reader on our previously retrieved documents!"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "G4XprIih9-9O",
"outputId": "94c63d34-67ad-4f82-a3b4-2a32cecc8427"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"To create a pipeline object, follow these steps:\n",
"\n",
"1. Define the inputs and outputs of your pipeline. These could be strings, dictionaries, or any other format that best suits your use case.\n",
"\n",
"2. Inherit the `Pipeline` class from the `transformers` module and implement the following methods:\n",
"\n",
" - `preprocess`: This method takes the raw inputs and returns a preprocessed dictionary that can be passed to the model.\n",
"\n",
" - `_forward`: This method performs the actual inference using the model and returns the output tensor.\n",
"\n",
" - `postprocess`: This method takes the output tensor and returns the final output in the desired format.\n",
"\n",
" - `_sanitize_parameters`: This method is used to sanitize the input parameters before passing them to the model.\n",
"\n",
"3. Load the necessary components, such as the model and scheduler, into the pipeline object.\n",
"\n",
"4. Instantiate the pipeline object and return it.\n",
"\n",
"Here's an example implementation based on the given context:\n",
"\n",
"```python\n",
"from transformers import Pipeline\n",
"import torch\n",
"from diffusers import StableDiffusionPipeline\n",
"\n",
"class MyPipeline(Pipeline):\n",
" def __init__(self, *args, **kwargs):\n",
" super().__init__(*args, **kwargs)\n",
" self.pipe = StableDiffusionPipeline.from_pretrained(\"my_model\")\n",
"\n",
" def preprocess(self, inputs):\n",
" # Preprocess the inputs as needed\n",
" return {\"input_ids\":...}\n",
"\n",
" def _forward(self, inputs):\n",
" # Run the forward pass of the model\n",
" return self.pipe(**inputs).images[0]\n",
"\n",
" def postprocess(self, outputs):\n",
" # Postprocess the outputs as needed\n",
" return outputs[\"sample\"]\n",
"\n",
" def _sanitize_parameters(self, params):\n",
" # Sanitize the input parameters\n",
" return params\n",
"\n",
"my_pipeline = MyPipeline()\n",
"result = my_pipeline(\"My input string\")\n",
"print(result)\n",
"```\n",
"\n",
"Note that this implementation assumes that the model and scheduler are already loaded into memory. If they need to be loaded dynamically, you can modify the `__init__` method accordingly.\n"
]
}
],
"source": [
"retrieved_docs_text = [\n",
" doc.page_content for doc in retrieved_docs\n",
"] # we only need the text of the documents\n",
"context = \"\\nExtracted documents:\\n\"\n",
"context += \"\".join([f\"Document {str(i)}:::\\n\" + doc for i, doc in enumerate(retrieved_docs_text)])\n",
"\n",
"final_prompt = RAG_PROMPT_TEMPLATE.format(\n",
" question=\"How to create a pipeline object?\", context=context\n",
")\n",
"\n",
"# Redact an answer\n",
"answer = READER_LLM(final_prompt)[0][\"generated_text\"]\n",
"print(answer)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "rhRHZoww9-9O"
},
"source": [
"### 2.3. Reranking\n",
"\n",
"A good option for RAG is to retrieve more documents than you want in the end, then rerank the results with a more powerful retrieval model before keeping only the `top_k`.\n",
"\n",
"For this, [Colbertv2](https://arxiv.org/abs/2112.01488) is a great choice: instead of a bi-encoder like our classical embedding models, it is a cross-encoder that computes more fine-grained interactions between the query tokens and each document's tokens.\n",
"\n",
"It is easily usable thanks to [the RAGatouille library](https://github.com/bclavie/RAGatouille)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "triOdqTV9-9O"
},
"outputs": [],
"source": [
"from ragatouille import RAGPretrainedModel\n",
"\n",
"RERANKER = RAGPretrainedModel.from_pretrained(\"colbert-ir/colbertv2.0\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Minj2SV59-9O"
},
"source": [
"# 3. Assembling it all!"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "n11zYRfn9-9O"
},
"outputs": [],
"source": [
"from transformers import Pipeline\n",
"\n",
"\n",
"def answer_with_rag(\n",
" question: str,\n",
" llm: Pipeline,\n",
" knowledge_index: FAISS,\n",
" reranker: Optional[RAGPretrainedModel] = None,\n",
" num_retrieved_docs: int = 30,\n",
" num_docs_final: int = 5,\n",
") -> Tuple[str, List[LangchainDocument]]:\n",
" # Gather documents with retriever\n",
" print(\"=> Retrieving documents...\")\n",
" relevant_docs = knowledge_index.similarity_search(query=question, k=num_retrieved_docs)\n",
" relevant_docs = [doc.page_content for doc in relevant_docs] # keep only the text\n",
"\n",
" # Optionally rerank results\n",
" if reranker:\n",
" print(\"=> Reranking documents...\")\n",
" relevant_docs = reranker.rerank(question, relevant_docs, k=num_docs_final)\n",
" relevant_docs = [doc[\"content\"] for doc in relevant_docs]\n",
"\n",
" relevant_docs = relevant_docs[:num_docs_final]\n",
"\n",
" # Build the final prompt\n",
" context = \"\\nExtracted documents:\\n\"\n",
" context += \"\".join([f\"Document {str(i)}:::\\n\" + doc for i, doc in enumerate(relevant_docs)])\n",
"\n",
" final_prompt = RAG_PROMPT_TEMPLATE.format(question=question, context=context)\n",
"\n",
" # Redact an answer\n",
" print(\"=> Generating answer...\")\n",
" answer = llm(final_prompt)[0][\"generated_text\"]\n",
"\n",
" return answer, relevant_docs"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "9nA4nwRQ9-9P"
},
"source": [
"Let's see how our RAG pipeline answers a user query."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "7ZTC1FtX9-9P",
"outputId": "22597be1-ab72-4f68-d577-0e12820463cf"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"=> Retrieving documents...\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"=> Reranking documents...\n",
"=> Generating answer...\n"
]
}
],
"source": [
"question = \"how to create a pipeline object?\"\n",
"\n",
"answer, relevant_docs = answer_with_rag(\n",
" question, READER_LLM, KNOWLEDGE_VECTOR_DATABASE, reranker=RERANKER\n",
")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "SwW0oqhZ9-9P",
"outputId": "361f28ed-9cd5-40b8-f8c4-57e8e4a530d9"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"==================================Answer==================================\n",
"To create a pipeline object, follow these steps:\n",
"\n",
"1. Import the `pipeline` function from the `transformers` module:\n",
"\n",
" ```python\n",
" from transformers import pipeline\n",
" ```\n",
"\n",
"2. Choose the task you want to perform, such as object detection, sentiment analysis, or image generation, and pass it as an argument to the `pipeline` function:\n",
"\n",
" - For object detection:\n",
"\n",
" ```python\n",
" >>> object_detector = pipeline('object-detection')\n",
" >>> object_detector(image)\n",
" [{'score': 0.9982201457023621,\n",
" 'label':'remote',\n",
" 'box': {'xmin': 40, 'ymin': 70, 'xmax': 175, 'ymax': 117}},\n",
" ...]\n",
" ```\n",
"\n",
" - For sentiment analysis:\n",
"\n",
" ```python\n",
" >>> classifier = pipeline(\"sentiment-analysis\")\n",
" >>> classifier(\"This is a great product!\")\n",
" {'labels': ['POSITIVE'],'scores': tensor([0.9999], device='cpu', dtype=torch.float32)}\n",
" ```\n",
"\n",
" - For image generation:\n",
"\n",
" ```python\n",
" >>> image = pipeline(\n",
" ... \"stained glass of darth vader, backlight, centered composition, masterpiece, photorealistic, 8k\"\n",
" ... ).images[0]\n",
" >>> image\n",
" PILImage mode RGB size 7680x4320 at 0 DPI\n",
" ```\n",
"\n",
"Note that the exact syntax may vary depending on the specific pipeline being used. Refer to the documentation for more details on how to use each pipeline.\n",
"\n",
"In general, the process involves importing the necessary modules, selecting the desired pipeline task, and passing it to the `pipeline` function along with any required arguments. The resulting pipeline object can then be used to perform the selected task on input data.\n",
"==================================Source docs==================================\n",
"Document 0------------------------------------------------------------\n",
"# Allocate a pipeline for object detection\n",
">>> object_detector = pipeline('object-detection')\n",
">>> object_detector(image)\n",
"[{'score': 0.9982201457023621,\n",
" 'label': 'remote',\n",
" 'box': {'xmin': 40, 'ymin': 70, 'xmax': 175, 'ymax': 117}},\n",
" {'score': 0.9960021376609802,\n",
" 'label': 'remote',\n",
" 'box': {'xmin': 333, 'ymin': 72, 'xmax': 368, 'ymax': 187}},\n",
" {'score': 0.9954745173454285,\n",
" 'label': 'couch',\n",
" 'box': {'xmin': 0, 'ymin': 1, 'xmax': 639, 'ymax': 473}},\n",
" {'score': 0.9988006353378296,\n",
" 'label': 'cat',\n",
" 'box': {'xmin': 13, 'ymin': 52, 'xmax': 314, 'ymax': 470}},\n",
" {'score': 0.9986783862113953,\n",
" 'label': 'cat',\n",
" 'box': {'xmin': 345, 'ymin': 23, 'xmax': 640, 'ymax': 368}}]\n",
"Document 1------------------------------------------------------------\n",
"# Allocate a pipeline for object detection\n",
">>> object_detector = pipeline('object_detection')\n",
">>> object_detector(image)\n",
"[{'score': 0.9982201457023621,\n",
" 'label': 'remote',\n",
" 'box': {'xmin': 40, 'ymin': 70, 'xmax': 175, 'ymax': 117}},\n",
" {'score': 0.9960021376609802,\n",
" 'label': 'remote',\n",
" 'box': {'xmin': 333, 'ymin': 72, 'xmax': 368, 'ymax': 187}},\n",
" {'score': 0.9954745173454285,\n",
" 'label': 'couch',\n",
" 'box': {'xmin': 0, 'ymin': 1, 'xmax': 639, 'ymax': 473}},\n",
" {'score': 0.9988006353378296,\n",
" 'label': 'cat',\n",
" 'box': {'xmin': 13, 'ymin': 52, 'xmax': 314, 'ymax': 470}},\n",
" {'score': 0.9986783862113953,\n",
" 'label': 'cat',\n",
" 'box': {'xmin': 345, 'ymin': 23, 'xmax': 640, 'ymax': 368}}]\n",
"Document 2------------------------------------------------------------\n",
"Start by creating an instance of [`pipeline`] and specifying a task you want to use it for. In this guide, you'll use the [`pipeline`] for sentiment analysis as an example:\n",
"\n",
"```py\n",
">>> from transformers import pipeline\n",
"\n",
">>> classifier = pipeline(\"sentiment-analysis\")\n",
"Document 3------------------------------------------------------------\n",
"```\n",
"\n",
"## Add the pipeline to 🤗 Transformers\n",
"\n",
"If you want to contribute your pipeline to 🤗 Transformers, you will need to add a new module in the `pipelines` submodule\n",
"with the code of your pipeline, then add it to the list of tasks defined in `pipelines/__init__.py`.\n",
"\n",
"Then you will need to add tests. Create a new file `tests/test_pipelines_MY_PIPELINE.py` with examples of the other tests.\n",
"\n",
"The `run_pipeline_test` function will be very generic and run on small random models on every possible\n",
"architecture as defined by `model_mapping` and `tf_model_mapping`.\n",
"\n",
"This is very important to test future compatibility, meaning if someone adds a new model for\n",
"`XXXForQuestionAnswering` then the pipeline test will attempt to run on it. Because the models are random it's\n",
"impossible to check for actual values, that's why there is a helper `ANY` that will simply attempt to match the\n",
"output of the pipeline TYPE.\n",
"\n",
"You also *need* to implement 2 (ideally 4) tests.\n",
"\n",
"- `test_small_model_pt` : Define 1 small model for this pipeline (doesn't matter if the results don't make sense)\n",
" and test the pipeline outputs. The results should be the same as `test_small_model_tf`.\n",
"- `test_small_model_tf` : Define 1 small model for this pipeline (doesn't matter if the results don't make sense)\n",
" and test the pipeline outputs. The results should be the same as `test_small_model_pt`.\n",
"- `test_large_model_pt` (`optional`): Tests the pipeline on a real pipeline where the results are supposed to\n",
" make sense. These tests are slow and should be marked as such. Here the goal is to showcase the pipeline and to make\n",
" sure there is no drift in future releases.\n",
"- `test_large_model_tf` (`optional`): Tests the pipeline on a real pipeline where the results are supposed to\n",
" make sense. These tests are slow and should be marked as such. Here the goal is to showcase the pipeline and to make\n",
" sure there is no drift in future releases.\n",
"Document 4------------------------------------------------------------\n",
"```\n",
"\n",
"2. Pass a prompt to the pipeline to generate an image:\n",
"\n",
"```py\n",
"image = pipeline(\n",
"\t\"stained glass of darth vader, backlight, centered composition, masterpiece, photorealistic, 8k\"\n",
").images[0]\n",
"image\n"
]
}
],
"source": [
"print(\"==================================Answer==================================\")\n",
"print(f\"{answer}\")\n",
"print(\"==================================Source docs==================================\")\n",
"for i, doc in enumerate(relevant_docs):\n",
" print(f\"Document {i}------------------------------------------------------------\")\n",
" print(doc)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "w6iNo7lY9-9S"
},
"source": [
"✅ We now have a fully functional, performant RAG sytem. That's it for today! Congratulations for making it to the end 🥳\n",
"\n",
"\n",
"# To go further 🗺️\n",
"\n",
"This is not the end of the journey! You can try many steps to improve your RAG system. We recommend doing so in an iterative way: bring small changes to the system and see what improves performance.\n",
"\n",
"### Setting up an evaluation pipeline\n",
"\n",
"- 💬 \"You cannot improve the model performance that you do not measure\", said Gandhi... or at least Llama2 told me he said it. Anyway, you should absolutely start by measuring performance: this means building a small evaluation dataset, then monitor the performance of your RAG system on this evaluation dataset.\n",
"\n",
"### Improving the retriever\n",
"\n",
"🛠️ __You can use these options to tune the results:__\n",
"\n",
"- Tune the chunking method:\n",
" - Size of the chunks\n",
" - Method: split on different separators, use [semantic chunking](https://python.langchain.com/docs/modules/data_connection/document_transformers/semantic-chunker)...\n",
"- Change the embedding model\n",
"\n",
"👷♀️ __More could be considered:__\n",
"- Try another chunking method, like semantic chunking\n",
"- Change the index used (here, FAISS)\n",
"- Query expansion: reformulate the user query in slightly different ways to retrieve more documents.\n",
"\n",
"### Improving the reader\n",
"\n",
"🛠️ __Here you can try the following options to improve results:__\n",
"- Tune the prompt\n",
"- Switch reranking on/off\n",
"- Choose a more powerful reader model\n",
"\n",
"💡 __Many options could be considered here to further improve the results:__\n",
"- Compress the retrieved context to keep only the most relevant parts to answer the query.\n",
"- Extend the RAG system to make it more user-friendly:\n",
" - cite source\n",
" - make conversational"
]
}
],
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"display_name": "ml2",
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|