Spaces:
Running
Running
File size: 135,007 Bytes
cf7a8a2 |
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 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 |
<!DOCTYPE html>
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
<meta charset="utf-8">
<meta name="generator" content="quarto-1.6.40">
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
<title>RAG Evaluation – Open-Source AI Cookbook</title>
<style>
code{white-space: pre-wrap;}
span.smallcaps{font-variant: small-caps;}
div.columns{display: flex; gap: min(4vw, 1.5em);}
div.column{flex: auto; overflow-x: auto;}
div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;}
ul.task-list{list-style: none;}
ul.task-list li input[type="checkbox"] {
width: 0.8em;
margin: 0 0.8em 0.2em -1em; /* quarto-specific, see https://github.com/quarto-dev/quarto-cli/issues/4556 */
vertical-align: middle;
}
/* CSS for syntax highlighting */
pre > code.sourceCode { white-space: pre; position: relative; }
pre > code.sourceCode > span { line-height: 1.25; }
pre > code.sourceCode > span:empty { height: 1.2em; }
.sourceCode { overflow: visible; }
code.sourceCode > span { color: inherit; text-decoration: inherit; }
div.sourceCode { margin: 1em 0; }
pre.sourceCode { margin: 0; }
@media screen {
div.sourceCode { overflow: auto; }
}
@media print {
pre > code.sourceCode { white-space: pre-wrap; }
pre > code.sourceCode > span { display: inline-block; text-indent: -5em; padding-left: 5em; }
}
pre.numberSource code
{ counter-reset: source-line 0; }
pre.numberSource code > span
{ position: relative; left: -4em; counter-increment: source-line; }
pre.numberSource code > span > a:first-child::before
{ content: counter(source-line);
position: relative; left: -1em; text-align: right; vertical-align: baseline;
border: none; display: inline-block;
-webkit-touch-callout: none; -webkit-user-select: none;
-khtml-user-select: none; -moz-user-select: none;
-ms-user-select: none; user-select: none;
padding: 0 4px; width: 4em;
}
pre.numberSource { margin-left: 3em; padding-left: 4px; }
div.sourceCode
{ }
@media screen {
pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; }
}
</style>
<script src="../site_libs/quarto-nav/quarto-nav.js"></script>
<script src="../site_libs/quarto-nav/headroom.min.js"></script>
<script src="../site_libs/clipboard/clipboard.min.js"></script>
<script src="../site_libs/quarto-search/autocomplete.umd.js"></script>
<script src="../site_libs/quarto-search/fuse.min.js"></script>
<script src="../site_libs/quarto-search/quarto-search.js"></script>
<meta name="quarto:offset" content="../">
<script src="../site_libs/quarto-html/quarto.js"></script>
<script src="../site_libs/quarto-html/popper.min.js"></script>
<script src="../site_libs/quarto-html/tippy.umd.min.js"></script>
<script src="../site_libs/quarto-html/anchor.min.js"></script>
<link href="../site_libs/quarto-html/tippy.css" rel="stylesheet">
<link href="../site_libs/quarto-html/quarto-syntax-highlighting-549806ee2085284f45b00abea8c6df48.css" rel="stylesheet" id="quarto-text-highlighting-styles">
<script src="../site_libs/bootstrap/bootstrap.min.js"></script>
<link href="../site_libs/bootstrap/bootstrap-icons.css" rel="stylesheet">
<link href="../site_libs/bootstrap/bootstrap-2be10d9e998f81ff6e49e26833438aa5.min.css" rel="stylesheet" append-hash="true" id="quarto-bootstrap" data-mode="light">
<script id="quarto-search-options" type="application/json">{
"location": "sidebar",
"copy-button": false,
"collapse-after": 3,
"panel-placement": "start",
"type": "textbox",
"limit": 50,
"keyboard-shortcut": [
"f",
"/",
"s"
],
"show-item-context": false,
"language": {
"search-no-results-text": "No results",
"search-matching-documents-text": "matching documents",
"search-copy-link-title": "Copy link to search",
"search-hide-matches-text": "Hide additional matches",
"search-more-match-text": "more match in this document",
"search-more-matches-text": "more matches in this document",
"search-clear-button-title": "Clear",
"search-text-placeholder": "",
"search-detached-cancel-button-title": "Cancel",
"search-submit-button-title": "Submit",
"search-label": "Search"
}
}</script>
<link rel="stylesheet" href="../styles.css">
</head>
<body class="nav-sidebar docked">
<div id="quarto-search-results"></div>
<header id="quarto-header" class="headroom fixed-top">
<nav class="quarto-secondary-nav">
<div class="container-fluid d-flex">
<button type="button" class="quarto-btn-toggle btn" data-bs-toggle="collapse" role="button" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
<i class="bi bi-layout-text-sidebar-reverse"></i>
</button>
<nav class="quarto-page-breadcrumbs" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item">Open-Source AI Cookbook</li><li class="breadcrumb-item"><a href="../notebooks/rag_zephyr_langchain.html">RAG Techniques</a></li><li class="breadcrumb-item"><a href="../notebooks/rag_evaluation.html">RAG Evaluation</a></li></ol></nav>
<a class="flex-grow-1" role="navigation" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
</a>
<button type="button" class="btn quarto-search-button" aria-label="Search" onclick="window.quartoOpenSearch();">
<i class="bi bi-search"></i>
</button>
</div>
</nav>
</header>
<!-- content -->
<div id="quarto-content" class="quarto-container page-columns page-rows-contents page-layout-article">
<!-- sidebar -->
<nav id="quarto-sidebar" class="sidebar collapse collapse-horizontal quarto-sidebar-collapse-item sidebar-navigation docked overflow-auto">
<div class="pt-lg-2 mt-2 text-left sidebar-header">
<div class="sidebar-title mb-0 py-0">
<a href="../">Open-Source AI Cookbook</a>
</div>
</div>
<div class="mt-2 flex-shrink-0 align-items-center">
<div class="sidebar-search">
<div id="quarto-search" class="" title="Search"></div>
</div>
</div>
<div class="sidebar-menu-container">
<ul class="list-unstyled mt-1">
<li class="sidebar-item sidebar-item-section">
<div class="sidebar-item-container">
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" aria-expanded="true">
<span class="menu-text">About</span></a>
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-1" role="navigation" aria-expanded="true" aria-label="Toggle section">
<i class="bi bi-chevron-right ms-2"></i>
</a>
</div>
<ul id="quarto-sidebar-section-1" class="collapse list-unstyled sidebar-section depth1 show">
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../index.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">About Quarto</span></a>
</div>
</li>
</ul>
</li>
<li class="sidebar-item sidebar-item-section">
<div class="sidebar-item-container">
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" role="navigation" aria-expanded="true">
<span class="menu-text">Open-Source AI Cookbook</span></a>
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-2" role="navigation" aria-expanded="true" aria-label="Toggle section">
<i class="bi bi-chevron-right ms-2"></i>
</a>
</div>
<ul id="quarto-sidebar-section-2" class="collapse list-unstyled sidebar-section depth1 show">
<li class="sidebar-item sidebar-item-section">
<div class="sidebar-item-container">
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true">
<span class="menu-text">RAG Techniques</span></a>
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-3" role="navigation" aria-expanded="true" aria-label="Toggle section">
<i class="bi bi-chevron-right ms-2"></i>
</a>
</div>
<ul id="quarto-sidebar-section-3" class="collapse list-unstyled sidebar-section depth2 show">
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../notebooks/rag_zephyr_langchain.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">RAG Zephyr & LangChain</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../notebooks/advanced_rag.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Advanced RAG</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../notebooks/rag_evaluation.html" class="sidebar-item-text sidebar-link active">
<span class="menu-text">RAG Evaluation</span></a>
</div>
</li>
</ul>
</li>
<li class="sidebar-item sidebar-item-section">
<div class="sidebar-item-container">
<a class="sidebar-item-text sidebar-link text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-4" role="navigation" aria-expanded="true">
<span class="menu-text">Additional Techniques</span></a>
<a class="sidebar-item-toggle text-start" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar-section-4" role="navigation" aria-expanded="true" aria-label="Toggle section">
<i class="bi bi-chevron-right ms-2"></i>
</a>
</div>
<ul id="quarto-sidebar-section-4" class="collapse list-unstyled sidebar-section depth2 show">
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../notebooks/automatic_embedding.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Automatic Embedding</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../notebooks/faiss.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">FAISS for Efficient Search</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="../notebooks/single_gpu.html" class="sidebar-item-text sidebar-link">
<span class="menu-text">Single GPU Optimization</span></a>
</div>
</li>
</ul>
</li>
</ul>
</li>
</ul>
</div>
</nav>
<div id="quarto-sidebar-glass" class="quarto-sidebar-collapse-item" data-bs-toggle="collapse" data-bs-target=".quarto-sidebar-collapse-item"></div>
<!-- margin-sidebar -->
<div id="quarto-margin-sidebar" class="sidebar margin-sidebar">
<nav id="TOC" role="doc-toc" class="toc-active">
<h2 id="toc-title">On this page</h2>
<ul>
<li><a href="#load-your-knowledge-base" id="toc-load-your-knowledge-base" class="nav-link active" data-scroll-target="#load-your-knowledge-base">Load your knowledge base</a></li>
<li><a href="#build-a-synthetic-dataset-for-evaluation" id="toc-build-a-synthetic-dataset-for-evaluation" class="nav-link" data-scroll-target="#build-a-synthetic-dataset-for-evaluation">1. Build a synthetic dataset for evaluation</a>
<ul class="collapse">
<li><a href="#prepare-source-documents" id="toc-prepare-source-documents" class="nav-link" data-scroll-target="#prepare-source-documents">1.1. Prepare source documents</a></li>
<li><a href="#setup-agents-for-question-generation" id="toc-setup-agents-for-question-generation" class="nav-link" data-scroll-target="#setup-agents-for-question-generation">1.2. Setup agents for question generation</a></li>
<li><a href="#setup-critique-agents" id="toc-setup-critique-agents" class="nav-link" data-scroll-target="#setup-critique-agents">1.3. Setup critique agents</a></li>
</ul></li>
<li><a href="#build-our-rag-system" id="toc-build-our-rag-system" class="nav-link" data-scroll-target="#build-our-rag-system">2. Build our RAG System</a>
<ul class="collapse">
<li><a href="#preprocessing-documents-to-build-our-vector-database" id="toc-preprocessing-documents-to-build-our-vector-database" class="nav-link" data-scroll-target="#preprocessing-documents-to-build-our-vector-database">2.1. Preprocessing documents to build our vector database</a></li>
<li><a href="#retriever---embeddings" id="toc-retriever---embeddings" class="nav-link" data-scroll-target="#retriever---embeddings">2.2. Retriever - embeddings 🗂️</a></li>
<li><a href="#reader---llm" id="toc-reader---llm" class="nav-link" data-scroll-target="#reader---llm">2.3. Reader - LLM 💬</a></li>
</ul></li>
<li><a href="#benchmarking-the-rag-system" id="toc-benchmarking-the-rag-system" class="nav-link" data-scroll-target="#benchmarking-the-rag-system">3. Benchmarking the RAG system</a>
<ul class="collapse">
<li><a href="#inspect-results" id="toc-inspect-results" class="nav-link" data-scroll-target="#inspect-results">Inspect results</a></li>
<li><a href="#example-results" id="toc-example-results" class="nav-link" data-scroll-target="#example-results">Example results</a></li>
</ul></li>
</ul>
</nav>
</div>
<!-- main -->
<main class="content" id="quarto-document-content">
<header id="title-block-header" class="quarto-title-block default"><nav class="quarto-page-breadcrumbs quarto-title-breadcrumbs d-none d-lg-block" aria-label="breadcrumb"><ol class="breadcrumb"><li class="breadcrumb-item">Open-Source AI Cookbook</li><li class="breadcrumb-item"><a href="../notebooks/rag_zephyr_langchain.html">RAG Techniques</a></li><li class="breadcrumb-item"><a href="../notebooks/rag_evaluation.html">RAG Evaluation</a></li></ol></nav>
<div class="quarto-title">
<h1 class="title">RAG Evaluation</h1>
</div>
<div class="quarto-title-meta">
</div>
</header>
<div id="22784221" class="cell" data-execution_count="1">
<div class="sourceCode cell-code" id="cb1"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="op">!</span>pip install <span class="op">-</span>q torch transformers transformers langchain sentence<span class="op">-</span>transformers faiss<span class="op">-</span>gpu openpyxl openai</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div id="01b9dea1" class="cell" data-execution_count="2">
<div class="sourceCode cell-code" id="cb2"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a><span class="op">%</span>reload_ext autoreload</span>
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a><span class="op">%</span>autoreload <span class="dv">2</span></span>
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a><span class="op">%</span>reload_ext dotenv</span>
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a><span class="op">%</span>dotenv</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div id="b2fdd362" class="cell" data-execution_count="3">
<div class="sourceCode cell-code" id="cb3"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> tqdm.notebook <span class="im">import</span> tqdm</span>
<span id="cb3-2"><a href="#cb3-2" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> pandas <span class="im">as</span> pd</span>
<span id="cb3-3"><a href="#cb3-3" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> typing <span class="im">import</span> Optional, List, Tuple</span>
<span id="cb3-4"><a href="#cb3-4" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain_core.language_models <span class="im">import</span> BaseChatModel</span>
<span id="cb3-5"><a href="#cb3-5" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> json</span>
<span id="cb3-6"><a href="#cb3-6" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> datasets</span>
<span id="cb3-7"><a href="#cb3-7" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb3-8"><a href="#cb3-8" aria-hidden="true" tabindex="-1"></a>pd.set_option(<span class="st">"display.max_colwidth"</span>, <span class="va">None</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<section id="load-your-knowledge-base" class="level3">
<h3 class="anchored" data-anchor-id="load-your-knowledge-base">Load your knowledge base</h3>
<div id="359836ac" class="cell" data-execution_count="4">
<div class="sourceCode cell-code" id="cb4"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a>ds <span class="op">=</span> datasets.load_dataset(<span class="st">"m-ric/huggingface_doc"</span>, split<span class="op">=</span><span class="st">"train"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
</section>
<section id="build-a-synthetic-dataset-for-evaluation" class="level1">
<h1>1. Build a synthetic dataset for evaluation</h1>
<p>We first build a synthetic dataset of questions and associated contexts. The method is to get elements from our knowledge base, and ask an LLM to generate questions based on these documents.</p>
<p>Then we setup other LLM agents to act as quality filters for the generated QA couples: each of them will act as the filter for a specific flaw.</p>
<section id="prepare-source-documents" class="level3">
<h3 class="anchored" data-anchor-id="prepare-source-documents">1.1. Prepare source documents</h3>
<div id="36f649ad" class="cell" data-execution_count="5">
<div class="sourceCode cell-code" id="cb5"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb5-1"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.text_splitter <span class="im">import</span> RecursiveCharacterTextSplitter</span>
<span id="cb5-2"><a href="#cb5-2" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.docstore.document <span class="im">import</span> Document <span class="im">as</span> LangchainDocument</span>
<span id="cb5-3"><a href="#cb5-3" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb5-4"><a href="#cb5-4" aria-hidden="true" tabindex="-1"></a>langchain_docs <span class="op">=</span> [</span>
<span id="cb5-5"><a href="#cb5-5" aria-hidden="true" tabindex="-1"></a> LangchainDocument(page_content<span class="op">=</span>doc[<span class="st">"text"</span>], metadata<span class="op">=</span>{<span class="st">"source"</span>: doc[<span class="st">"source"</span>]})</span>
<span id="cb5-6"><a href="#cb5-6" aria-hidden="true" tabindex="-1"></a> <span class="cf">for</span> doc <span class="kw">in</span> tqdm(ds)</span>
<span id="cb5-7"><a href="#cb5-7" aria-hidden="true" tabindex="-1"></a>]</span>
<span id="cb5-8"><a href="#cb5-8" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb5-9"><a href="#cb5-9" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb5-10"><a href="#cb5-10" aria-hidden="true" tabindex="-1"></a>text_splitter <span class="op">=</span> RecursiveCharacterTextSplitter(</span>
<span id="cb5-11"><a href="#cb5-11" aria-hidden="true" tabindex="-1"></a> chunk_size<span class="op">=</span><span class="dv">2000</span>,</span>
<span id="cb5-12"><a href="#cb5-12" aria-hidden="true" tabindex="-1"></a> chunk_overlap<span class="op">=</span><span class="dv">200</span>,</span>
<span id="cb5-13"><a href="#cb5-13" aria-hidden="true" tabindex="-1"></a> add_start_index<span class="op">=</span><span class="va">True</span>,</span>
<span id="cb5-14"><a href="#cb5-14" aria-hidden="true" tabindex="-1"></a> separators<span class="op">=</span>[<span class="st">"</span><span class="ch">\n\n</span><span class="st">"</span>, <span class="st">"</span><span class="ch">\n</span><span class="st">"</span>, <span class="st">"."</span>, <span class="st">" "</span>, <span class="st">""</span>],</span>
<span id="cb5-15"><a href="#cb5-15" aria-hidden="true" tabindex="-1"></a>)</span>
<span id="cb5-16"><a href="#cb5-16" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb5-17"><a href="#cb5-17" aria-hidden="true" tabindex="-1"></a>docs_processed <span class="op">=</span> []</span>
<span id="cb5-18"><a href="#cb5-18" aria-hidden="true" tabindex="-1"></a><span class="cf">for</span> doc <span class="kw">in</span> langchain_docs:</span>
<span id="cb5-19"><a href="#cb5-19" aria-hidden="true" tabindex="-1"></a> docs_processed <span class="op">+=</span> text_splitter.split_documents([doc])</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
</section>
<section id="setup-agents-for-question-generation" class="level3">
<h3 class="anchored" data-anchor-id="setup-agents-for-question-generation">1.2. Setup agents for question generation</h3>
<p>We use <a href="https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1">Mixtral</a> for QA couple generation because it it has excellent performance in leaderboards such as <a href="https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard">Chatbot Arena</a>.</p>
<div id="03878328" class="cell" data-execution_count="6">
<div class="sourceCode cell-code" id="cb6"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain_community.llms <span class="im">import</span> HuggingFaceHub</span>
<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb6-3"><a href="#cb6-3" aria-hidden="true" tabindex="-1"></a>repo_id <span class="op">=</span> <span class="st">"mistralai/Mixtral-8x7B-Instruct-v0.1"</span></span>
<span id="cb6-4"><a href="#cb6-4" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb6-5"><a href="#cb6-5" aria-hidden="true" tabindex="-1"></a>llm <span class="op">=</span> HuggingFaceHub(</span>
<span id="cb6-6"><a href="#cb6-6" aria-hidden="true" tabindex="-1"></a> repo_id<span class="op">=</span>repo_id,</span>
<span id="cb6-7"><a href="#cb6-7" aria-hidden="true" tabindex="-1"></a> task<span class="op">=</span><span class="st">"text-generation"</span>,</span>
<span id="cb6-8"><a href="#cb6-8" aria-hidden="true" tabindex="-1"></a> model_kwargs<span class="op">=</span>{</span>
<span id="cb6-9"><a href="#cb6-9" aria-hidden="true" tabindex="-1"></a> <span class="st">"max_new_tokens"</span>: <span class="dv">512</span>,</span>
<span id="cb6-10"><a href="#cb6-10" aria-hidden="true" tabindex="-1"></a> <span class="st">"top_k"</span>: <span class="dv">30</span>,</span>
<span id="cb6-11"><a href="#cb6-11" aria-hidden="true" tabindex="-1"></a> <span class="st">"temperature"</span>: <span class="fl">0.1</span>,</span>
<span id="cb6-12"><a href="#cb6-12" aria-hidden="true" tabindex="-1"></a> <span class="st">"repetition_penalty"</span>: <span class="fl">1.03</span>,</span>
<span id="cb6-13"><a href="#cb6-13" aria-hidden="true" tabindex="-1"></a> },</span>
<span id="cb6-14"><a href="#cb6-14" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div id="67115f45" class="cell" data-execution_count="7">
<div class="sourceCode cell-code" id="cb7"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb7-1"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain_community.chat_models <span class="im">import</span> ChatHuggingFace</span>
<span id="cb7-2"><a href="#cb7-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb7-3"><a href="#cb7-3" aria-hidden="true" tabindex="-1"></a>chat_model <span class="op">=</span> ChatHuggingFace(llm<span class="op">=</span>llm)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div id="8a75ff72" class="cell" data-execution_count="8">
<div class="sourceCode cell-code" id="cb8"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.prompts <span class="im">import</span> ChatPromptTemplate</span>
<span id="cb8-2"><a href="#cb8-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb8-3"><a href="#cb8-3" aria-hidden="true" tabindex="-1"></a>QA_generation_prompt <span class="op">=</span> <span class="st">"""</span></span>
<span id="cb8-4"><a href="#cb8-4" aria-hidden="true" tabindex="-1"></a><span class="st">Your task is to write a factoid question and an answer given a context.</span></span>
<span id="cb8-5"><a href="#cb8-5" aria-hidden="true" tabindex="-1"></a><span class="st">Your factoid question should be answerable with a specific, concise piece of factual information from the context.</span></span>
<span id="cb8-6"><a href="#cb8-6" aria-hidden="true" tabindex="-1"></a><span class="st">Your factoid question should be formulated in the same style as questions users could ask in a search engine.</span></span>
<span id="cb8-7"><a href="#cb8-7" aria-hidden="true" tabindex="-1"></a><span class="st">This means that your factoid question MUST NOT mention something like "according to the passage" or "context".</span></span>
<span id="cb8-8"><a href="#cb8-8" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb8-9"><a href="#cb8-9" aria-hidden="true" tabindex="-1"></a><span class="st">Provide your answer as follows:</span></span>
<span id="cb8-10"><a href="#cb8-10" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb8-11"><a href="#cb8-11" aria-hidden="true" tabindex="-1"></a><span class="st">Output:::</span></span>
<span id="cb8-12"><a href="#cb8-12" aria-hidden="true" tabindex="-1"></a><span class="st">Factoid question: (your factoid question)</span></span>
<span id="cb8-13"><a href="#cb8-13" aria-hidden="true" tabindex="-1"></a><span class="st">Answer: (your answer to the factoid question)</span></span>
<span id="cb8-14"><a href="#cb8-14" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb8-15"><a href="#cb8-15" aria-hidden="true" tabindex="-1"></a><span class="st">Now here is the context.</span></span>
<span id="cb8-16"><a href="#cb8-16" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb8-17"><a href="#cb8-17" aria-hidden="true" tabindex="-1"></a><span class="st">Context: </span><span class="sc">{context}</span><span class="ch">\n</span></span>
<span id="cb8-18"><a href="#cb8-18" aria-hidden="true" tabindex="-1"></a><span class="st">Output:::"""</span></span>
<span id="cb8-19"><a href="#cb8-19" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb8-20"><a href="#cb8-20" aria-hidden="true" tabindex="-1"></a>QA_generation_prompt <span class="op">=</span> ChatPromptTemplate.from_template(QA_generation_prompt)</span>
<span id="cb8-21"><a href="#cb8-21" aria-hidden="true" tabindex="-1"></a>QA_generation_agent <span class="op">=</span> QA_generation_prompt <span class="op">|</span> chat_model</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<p>Now let’s generate our QA couples. For this example, we generate only 10 QA couples and will load the rest from the Hub.</p>
<p>But for your specific knowledge base, given that you want to get at least ~100 test samples, and accounting for the fact that we will filter out around half of these with our critique agents later on, you should generate much more, in the >200 samples.</p>
<div id="66448027" class="cell" data-execution_count="9">
<div class="sourceCode cell-code" id="cb9"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb9-1"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> random</span>
<span id="cb9-2"><a href="#cb9-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb9-3"><a href="#cb9-3" aria-hidden="true" tabindex="-1"></a>N_GENERATIONS <span class="op">=</span> (</span>
<span id="cb9-4"><a href="#cb9-4" aria-hidden="true" tabindex="-1"></a> <span class="dv">10</span> <span class="co"># We intentionally generate only 10 QA couples here for cost and time considerations</span></span>
<span id="cb9-5"><a href="#cb9-5" aria-hidden="true" tabindex="-1"></a>)</span>
<span id="cb9-6"><a href="#cb9-6" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb9-7"><a href="#cb9-7" aria-hidden="true" tabindex="-1"></a><span class="bu">print</span>(<span class="ss">f"Generating </span><span class="sc">{</span>N_GENERATIONS<span class="sc">}</span><span class="ss"> QA couples..."</span>)</span>
<span id="cb9-8"><a href="#cb9-8" aria-hidden="true" tabindex="-1"></a>outputs <span class="op">=</span> []</span>
<span id="cb9-9"><a href="#cb9-9" aria-hidden="true" tabindex="-1"></a><span class="cf">for</span> context <span class="kw">in</span> tqdm(random.sample(langchain_docs, N_GENERATIONS)):</span>
<span id="cb9-10"><a href="#cb9-10" aria-hidden="true" tabindex="-1"></a> <span class="co"># Generate QA couple</span></span>
<span id="cb9-11"><a href="#cb9-11" aria-hidden="true" tabindex="-1"></a> output_QA_couple <span class="op">=</span> QA_generation_agent.invoke({<span class="st">"context"</span>: context.page_content}).content</span>
<span id="cb9-12"><a href="#cb9-12" aria-hidden="true" tabindex="-1"></a> <span class="cf">try</span>:</span>
<span id="cb9-13"><a href="#cb9-13" aria-hidden="true" tabindex="-1"></a> question <span class="op">=</span> output_QA_couple.split(<span class="st">"Factoid question: "</span>)[<span class="dv">1</span>].split(<span class="st">"Answer: "</span>)[<span class="dv">0</span>]</span>
<span id="cb9-14"><a href="#cb9-14" aria-hidden="true" tabindex="-1"></a> answer <span class="op">=</span> output_QA_couple.split(<span class="st">"Answer: "</span>)[<span class="dv">1</span>]</span>
<span id="cb9-15"><a href="#cb9-15" aria-hidden="true" tabindex="-1"></a> outputs.append(</span>
<span id="cb9-16"><a href="#cb9-16" aria-hidden="true" tabindex="-1"></a> {</span>
<span id="cb9-17"><a href="#cb9-17" aria-hidden="true" tabindex="-1"></a> <span class="st">"context"</span>: context.page_content,</span>
<span id="cb9-18"><a href="#cb9-18" aria-hidden="true" tabindex="-1"></a> <span class="st">"question"</span>: question,</span>
<span id="cb9-19"><a href="#cb9-19" aria-hidden="true" tabindex="-1"></a> <span class="st">"answer"</span>: answer,</span>
<span id="cb9-20"><a href="#cb9-20" aria-hidden="true" tabindex="-1"></a> <span class="st">"source_doc"</span>: context.metadata[<span class="st">"source"</span>],</span>
<span id="cb9-21"><a href="#cb9-21" aria-hidden="true" tabindex="-1"></a> }</span>
<span id="cb9-22"><a href="#cb9-22" aria-hidden="true" tabindex="-1"></a> )</span>
<span id="cb9-23"><a href="#cb9-23" aria-hidden="true" tabindex="-1"></a> <span class="cf">except</span>:</span>
<span id="cb9-24"><a href="#cb9-24" aria-hidden="true" tabindex="-1"></a> <span class="cf">continue</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div id="38586e3e" class="cell" data-execution_count="10">
<div class="sourceCode cell-code" id="cb10"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb10-1"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a>display(pd.DataFrame(outputs).head(<span class="dv">1</span>))</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
</section>
<section id="setup-critique-agents" class="level3">
<h3 class="anchored" data-anchor-id="setup-critique-agents">1.3. Setup critique agents</h3>
<p>The questions generated by the previous agent can have many flaws: we should do a quality check before validating these questions.</p>
<p>We thus build critique agents that will rate each question on several criteria, given in <a href="https://huggingface.co/papers/2312.10003">this paper</a>: - <strong>Groundedness:</strong> can the question be answered from the given context? - <strong>Relevance:</strong> is the question relevant to users? For instance, <code>"What is the date when transformers 4.29.1 was released?"</code> is not relevant for ML practicioners.</p>
<p>One last failure case we’ve noticed is when a function is tailored for the particular setting where the question was generated, but undecipherable by itself, like <code>"What is the name of the function used in this guide?"</code>. We also build a critique agent for this criteria: - <strong>Stand-alone</strong>: is the question understandable free of any context, for someone with domain knowledge/Internet access? The opposite of this would be <code>What is the function used in this article?</code> for a question generated from a specific blog article.</p>
<p>We systematically score functions with all these agents, and whenever the score is too low for any one of the agents, we eliminate the question from our eval dataset.</p>
<p>💡 <strong><em>When asking the agents to output a score, we first ask them to produce its rationale. This will help us verify scores, but most importantly, asking it to first output rationale gives the model more tokens to think and elaborate an answer before summarizing it into a single score token.</em></strong></p>
<p>We now build and run these critique agents.</p>
<div id="36f64eeb" class="cell" data-execution_count="11">
<div class="sourceCode cell-code" id="cb11"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb11-1"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a>question_groundedness_critique_prompt <span class="op">=</span> <span class="st">"""</span></span>
<span id="cb11-2"><a href="#cb11-2" aria-hidden="true" tabindex="-1"></a><span class="st">You will be given a context and a question.</span></span>
<span id="cb11-3"><a href="#cb11-3" aria-hidden="true" tabindex="-1"></a><span class="st">Your task is to provide a 'total rating' scoring how well one can answer the given question unambiguously with the given context.</span></span>
<span id="cb11-4"><a href="#cb11-4" aria-hidden="true" tabindex="-1"></a><span class="st">Give your answer on a scale of 1 to 5, where 1 means that the question is not answerable at all given the context, and 5 means that the question is clearly and unambiguously answerable with the context.</span></span>
<span id="cb11-5"><a href="#cb11-5" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-6"><a href="#cb11-6" aria-hidden="true" tabindex="-1"></a><span class="st">Provide your answer as follows:</span></span>
<span id="cb11-7"><a href="#cb11-7" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-8"><a href="#cb11-8" aria-hidden="true" tabindex="-1"></a><span class="st">Answer:::</span></span>
<span id="cb11-9"><a href="#cb11-9" aria-hidden="true" tabindex="-1"></a><span class="st">Evaluation: (your rationale for the rating)</span></span>
<span id="cb11-10"><a href="#cb11-10" aria-hidden="true" tabindex="-1"></a><span class="st">Total rating: (your rating)</span></span>
<span id="cb11-11"><a href="#cb11-11" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-12"><a href="#cb11-12" aria-hidden="true" tabindex="-1"></a><span class="st">Now here are the question and context.</span></span>
<span id="cb11-13"><a href="#cb11-13" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-14"><a href="#cb11-14" aria-hidden="true" tabindex="-1"></a><span class="st">Question: </span><span class="sc">{question}</span><span class="ch">\n</span></span>
<span id="cb11-15"><a href="#cb11-15" aria-hidden="true" tabindex="-1"></a><span class="st">Context: </span><span class="sc">{context}</span><span class="ch">\n</span></span>
<span id="cb11-16"><a href="#cb11-16" aria-hidden="true" tabindex="-1"></a><span class="st">Answer::: """</span></span>
<span id="cb11-17"><a href="#cb11-17" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-18"><a href="#cb11-18" aria-hidden="true" tabindex="-1"></a>question_relevance_critique_prompt <span class="op">=</span> <span class="st">"""</span></span>
<span id="cb11-19"><a href="#cb11-19" aria-hidden="true" tabindex="-1"></a><span class="st">You will be given a question.</span></span>
<span id="cb11-20"><a href="#cb11-20" aria-hidden="true" tabindex="-1"></a><span class="st">Your task is to provide a 'total rating' representing how useful this question can be to machine learning developers building NLP applications with the Hugging Face ecosystem.</span></span>
<span id="cb11-21"><a href="#cb11-21" aria-hidden="true" tabindex="-1"></a><span class="st">Give your answer on a scale of 1 to 5, where 1 means that the question is not useful at all, and 5 means that the question is extremely useful.</span></span>
<span id="cb11-22"><a href="#cb11-22" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-23"><a href="#cb11-23" aria-hidden="true" tabindex="-1"></a><span class="st">Provide your answer as follows:</span></span>
<span id="cb11-24"><a href="#cb11-24" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-25"><a href="#cb11-25" aria-hidden="true" tabindex="-1"></a><span class="st">Answer:::</span></span>
<span id="cb11-26"><a href="#cb11-26" aria-hidden="true" tabindex="-1"></a><span class="st">Evaluation: (your rationale for the rating)</span></span>
<span id="cb11-27"><a href="#cb11-27" aria-hidden="true" tabindex="-1"></a><span class="st">Total rating: (your rating)</span></span>
<span id="cb11-28"><a href="#cb11-28" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-29"><a href="#cb11-29" aria-hidden="true" tabindex="-1"></a><span class="st">Now here is the question.</span></span>
<span id="cb11-30"><a href="#cb11-30" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-31"><a href="#cb11-31" aria-hidden="true" tabindex="-1"></a><span class="st">Question: </span><span class="sc">{question}</span><span class="ch">\n</span></span>
<span id="cb11-32"><a href="#cb11-32" aria-hidden="true" tabindex="-1"></a><span class="st">Answer::: """</span></span>
<span id="cb11-33"><a href="#cb11-33" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-34"><a href="#cb11-34" aria-hidden="true" tabindex="-1"></a>question_standalone_critique_prompt <span class="op">=</span> <span class="st">"""</span></span>
<span id="cb11-35"><a href="#cb11-35" aria-hidden="true" tabindex="-1"></a><span class="st">You will be given a question.</span></span>
<span id="cb11-36"><a href="#cb11-36" aria-hidden="true" tabindex="-1"></a><span class="st">Your task is to provide a 'total rating' representing how context-independant this question is.</span></span>
<span id="cb11-37"><a href="#cb11-37" aria-hidden="true" tabindex="-1"></a><span class="st">Give your answer on a scale of 1 to 5, where 1 means that the question only makes sense in a specific context, and 5 means that the question makes sense by itself.</span></span>
<span id="cb11-38"><a href="#cb11-38" aria-hidden="true" tabindex="-1"></a><span class="st">For instance, if the question refers to a particular setting, like 'in the context' or 'in the document', the rating must be 1.</span></span>
<span id="cb11-39"><a href="#cb11-39" aria-hidden="true" tabindex="-1"></a><span class="st">The questions can contain obscure technical nouns or acronyms like Gradio, Hub, Hugging Face or Space and still be a 5: it must simply be clear to an operator with access to documentation what the question is about.</span></span>
<span id="cb11-40"><a href="#cb11-40" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-41"><a href="#cb11-41" aria-hidden="true" tabindex="-1"></a><span class="st">Provide your answer as follows:</span></span>
<span id="cb11-42"><a href="#cb11-42" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-43"><a href="#cb11-43" aria-hidden="true" tabindex="-1"></a><span class="st">Answer:::</span></span>
<span id="cb11-44"><a href="#cb11-44" aria-hidden="true" tabindex="-1"></a><span class="st">Evaluation: (your rationale for the rating)</span></span>
<span id="cb11-45"><a href="#cb11-45" aria-hidden="true" tabindex="-1"></a><span class="st">Total rating: (your rating)</span></span>
<span id="cb11-46"><a href="#cb11-46" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-47"><a href="#cb11-47" aria-hidden="true" tabindex="-1"></a><span class="st">Now here is the question.</span></span>
<span id="cb11-48"><a href="#cb11-48" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-49"><a href="#cb11-49" aria-hidden="true" tabindex="-1"></a><span class="st">Question: </span><span class="sc">{question}</span><span class="ch">\n</span></span>
<span id="cb11-50"><a href="#cb11-50" aria-hidden="true" tabindex="-1"></a><span class="st">Answer::: """</span></span>
<span id="cb11-51"><a href="#cb11-51" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-52"><a href="#cb11-52" aria-hidden="true" tabindex="-1"></a>question_groundedness_critique_prompt <span class="op">=</span> ChatPromptTemplate.from_template(</span>
<span id="cb11-53"><a href="#cb11-53" aria-hidden="true" tabindex="-1"></a> question_groundedness_critique_prompt</span>
<span id="cb11-54"><a href="#cb11-54" aria-hidden="true" tabindex="-1"></a>)</span>
<span id="cb11-55"><a href="#cb11-55" aria-hidden="true" tabindex="-1"></a>question_groundedness_critique_agent <span class="op">=</span> question_groundedness_critique_prompt <span class="op">|</span> chat_model</span>
<span id="cb11-56"><a href="#cb11-56" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-57"><a href="#cb11-57" aria-hidden="true" tabindex="-1"></a>question_relevance_critique_prompt <span class="op">=</span> ChatPromptTemplate.from_template(</span>
<span id="cb11-58"><a href="#cb11-58" aria-hidden="true" tabindex="-1"></a> question_relevance_critique_prompt</span>
<span id="cb11-59"><a href="#cb11-59" aria-hidden="true" tabindex="-1"></a>)</span>
<span id="cb11-60"><a href="#cb11-60" aria-hidden="true" tabindex="-1"></a>question_relevance_critique_agent <span class="op">=</span> question_relevance_critique_prompt <span class="op">|</span> chat_model</span>
<span id="cb11-61"><a href="#cb11-61" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb11-62"><a href="#cb11-62" aria-hidden="true" tabindex="-1"></a>question_standalone_critique_prompt <span class="op">=</span> ChatPromptTemplate.from_template(</span>
<span id="cb11-63"><a href="#cb11-63" aria-hidden="true" tabindex="-1"></a> question_standalone_critique_prompt</span>
<span id="cb11-64"><a href="#cb11-64" aria-hidden="true" tabindex="-1"></a>)</span>
<span id="cb11-65"><a href="#cb11-65" aria-hidden="true" tabindex="-1"></a>question_standalone_critique_agent <span class="op">=</span> question_standalone_critique_prompt <span class="op">|</span> chat_model</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div id="36a9f0a0" class="cell" data-execution_count="12">
<div class="sourceCode cell-code" id="cb12"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb12-1"><a href="#cb12-1" aria-hidden="true" tabindex="-1"></a><span class="bu">print</span>(<span class="st">"Generating critique for each QA couple..."</span>)</span>
<span id="cb12-2"><a href="#cb12-2" aria-hidden="true" tabindex="-1"></a><span class="cf">for</span> output <span class="kw">in</span> tqdm(outputs):</span>
<span id="cb12-3"><a href="#cb12-3" aria-hidden="true" tabindex="-1"></a> <span class="co"># Critique the generated QA couple</span></span>
<span id="cb12-4"><a href="#cb12-4" aria-hidden="true" tabindex="-1"></a> question_groundedness_evaluation <span class="op">=</span> question_groundedness_critique_agent.invoke(</span>
<span id="cb12-5"><a href="#cb12-5" aria-hidden="true" tabindex="-1"></a> {<span class="st">"context"</span>: output[<span class="st">"context"</span>], <span class="st">"question"</span>: output[<span class="st">"question"</span>]}</span>
<span id="cb12-6"><a href="#cb12-6" aria-hidden="true" tabindex="-1"></a> ).content</span>
<span id="cb12-7"><a href="#cb12-7" aria-hidden="true" tabindex="-1"></a> question_relevance_evaluation <span class="op">=</span> question_relevance_critique_agent.invoke(</span>
<span id="cb12-8"><a href="#cb12-8" aria-hidden="true" tabindex="-1"></a> {<span class="st">"question"</span>: output[<span class="st">"question"</span>]}</span>
<span id="cb12-9"><a href="#cb12-9" aria-hidden="true" tabindex="-1"></a> ).content</span>
<span id="cb12-10"><a href="#cb12-10" aria-hidden="true" tabindex="-1"></a> question_standalone_evaluation <span class="op">=</span> question_standalone_critique_agent.invoke(</span>
<span id="cb12-11"><a href="#cb12-11" aria-hidden="true" tabindex="-1"></a> {<span class="st">"question"</span>: output[<span class="st">"question"</span>]}</span>
<span id="cb12-12"><a href="#cb12-12" aria-hidden="true" tabindex="-1"></a> ).content</span>
<span id="cb12-13"><a href="#cb12-13" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb12-14"><a href="#cb12-14" aria-hidden="true" tabindex="-1"></a> <span class="cf">try</span>:</span>
<span id="cb12-15"><a href="#cb12-15" aria-hidden="true" tabindex="-1"></a> groundedness_score <span class="op">=</span> <span class="bu">int</span>(question_groundedness_evaluation.split(<span class="st">"Total rating: "</span>)[<span class="dv">1</span>][<span class="dv">0</span>])</span>
<span id="cb12-16"><a href="#cb12-16" aria-hidden="true" tabindex="-1"></a> groundedness_eval <span class="op">=</span> question_groundedness_evaluation.split(<span class="st">"Total rating: "</span>)[<span class="dv">0</span>].split(</span>
<span id="cb12-17"><a href="#cb12-17" aria-hidden="true" tabindex="-1"></a> <span class="st">"Evaluation: "</span></span>
<span id="cb12-18"><a href="#cb12-18" aria-hidden="true" tabindex="-1"></a> )[<span class="dv">1</span>]</span>
<span id="cb12-19"><a href="#cb12-19" aria-hidden="true" tabindex="-1"></a> relevance_score <span class="op">=</span> <span class="bu">int</span>(question_relevance_evaluation.split(<span class="st">"Total rating: "</span>)[<span class="dv">1</span>][<span class="dv">0</span>])</span>
<span id="cb12-20"><a href="#cb12-20" aria-hidden="true" tabindex="-1"></a> relevance_eval <span class="op">=</span> question_relevance_evaluation.split(<span class="st">"Total rating: "</span>)[<span class="dv">0</span>].split(</span>
<span id="cb12-21"><a href="#cb12-21" aria-hidden="true" tabindex="-1"></a> <span class="st">"Evaluation: "</span></span>
<span id="cb12-22"><a href="#cb12-22" aria-hidden="true" tabindex="-1"></a> )[<span class="dv">1</span>]</span>
<span id="cb12-23"><a href="#cb12-23" aria-hidden="true" tabindex="-1"></a> standalone_score <span class="op">=</span> <span class="bu">int</span>(question_standalone_evaluation.split(<span class="st">"Total rating: "</span>)[<span class="dv">1</span>][<span class="dv">0</span>])</span>
<span id="cb12-24"><a href="#cb12-24" aria-hidden="true" tabindex="-1"></a> standalone_eval <span class="op">=</span> question_standalone_evaluation.split(<span class="st">"Total rating: "</span>)[<span class="dv">0</span>].split(</span>
<span id="cb12-25"><a href="#cb12-25" aria-hidden="true" tabindex="-1"></a> <span class="st">"Evaluation: "</span></span>
<span id="cb12-26"><a href="#cb12-26" aria-hidden="true" tabindex="-1"></a> )[<span class="dv">1</span>]</span>
<span id="cb12-27"><a href="#cb12-27" aria-hidden="true" tabindex="-1"></a> output.update(</span>
<span id="cb12-28"><a href="#cb12-28" aria-hidden="true" tabindex="-1"></a> {</span>
<span id="cb12-29"><a href="#cb12-29" aria-hidden="true" tabindex="-1"></a> <span class="st">"groundedness_score"</span>: groundedness_score,</span>
<span id="cb12-30"><a href="#cb12-30" aria-hidden="true" tabindex="-1"></a> <span class="st">"groundedness_eval"</span>: groundedness_eval,</span>
<span id="cb12-31"><a href="#cb12-31" aria-hidden="true" tabindex="-1"></a> <span class="st">"relevance_score"</span>: relevance_score,</span>
<span id="cb12-32"><a href="#cb12-32" aria-hidden="true" tabindex="-1"></a> <span class="st">"relevance_eval"</span>: relevance_eval,</span>
<span id="cb12-33"><a href="#cb12-33" aria-hidden="true" tabindex="-1"></a> <span class="st">"standalone_score"</span>: standalone_score,</span>
<span id="cb12-34"><a href="#cb12-34" aria-hidden="true" tabindex="-1"></a> <span class="st">"standalone_eval"</span>: standalone_eval,</span>
<span id="cb12-35"><a href="#cb12-35" aria-hidden="true" tabindex="-1"></a> }</span>
<span id="cb12-36"><a href="#cb12-36" aria-hidden="true" tabindex="-1"></a> )</span>
<span id="cb12-37"><a href="#cb12-37" aria-hidden="true" tabindex="-1"></a> <span class="cf">except</span>:</span>
<span id="cb12-38"><a href="#cb12-38" aria-hidden="true" tabindex="-1"></a> <span class="cf">continue</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<p>Now let us filter out bad questions based on our critique agent scores:</p>
<div id="244dd1b5" class="cell" data-execution_count="13">
<div class="sourceCode cell-code" id="cb13"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb13-1"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> pandas <span class="im">as</span> pd</span>
<span id="cb13-2"><a href="#cb13-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb13-3"><a href="#cb13-3" aria-hidden="true" tabindex="-1"></a>pd.set_option(<span class="st">"display.max_colwidth"</span>, <span class="va">None</span>)</span>
<span id="cb13-4"><a href="#cb13-4" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb13-5"><a href="#cb13-5" aria-hidden="true" tabindex="-1"></a>generated_questions <span class="op">=</span> pd.DataFrame.from_dict(outputs)</span>
<span id="cb13-6"><a href="#cb13-6" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb13-7"><a href="#cb13-7" aria-hidden="true" tabindex="-1"></a><span class="bu">print</span>(<span class="st">"Evaluation dataset before filtering:"</span>)</span>
<span id="cb13-8"><a href="#cb13-8" aria-hidden="true" tabindex="-1"></a>display(</span>
<span id="cb13-9"><a href="#cb13-9" aria-hidden="true" tabindex="-1"></a> generated_questions[</span>
<span id="cb13-10"><a href="#cb13-10" aria-hidden="true" tabindex="-1"></a> [<span class="st">"question"</span>, <span class="st">"answer"</span>, <span class="st">"groundedness_score"</span>, <span class="st">"relevance_score"</span>, <span class="st">"standalone_score"</span>]</span>
<span id="cb13-11"><a href="#cb13-11" aria-hidden="true" tabindex="-1"></a> ]</span>
<span id="cb13-12"><a href="#cb13-12" aria-hidden="true" tabindex="-1"></a>)</span>
<span id="cb13-13"><a href="#cb13-13" aria-hidden="true" tabindex="-1"></a>generated_questions <span class="op">=</span> generated_questions.loc[</span>
<span id="cb13-14"><a href="#cb13-14" aria-hidden="true" tabindex="-1"></a> (generated_questions[<span class="st">"groundedness_score"</span>] <span class="op">>=</span> <span class="dv">4</span>)</span>
<span id="cb13-15"><a href="#cb13-15" aria-hidden="true" tabindex="-1"></a> <span class="op">&</span> (generated_questions[<span class="st">"relevance_score"</span>] <span class="op">>=</span> <span class="dv">4</span>)</span>
<span id="cb13-16"><a href="#cb13-16" aria-hidden="true" tabindex="-1"></a> <span class="op">&</span> (generated_questions[<span class="st">"standalone_score"</span>] <span class="op">>=</span> <span class="dv">4</span>)</span>
<span id="cb13-17"><a href="#cb13-17" aria-hidden="true" tabindex="-1"></a>]</span>
<span id="cb13-18"><a href="#cb13-18" aria-hidden="true" tabindex="-1"></a><span class="bu">print</span>(<span class="st">"============================================"</span>)</span>
<span id="cb13-19"><a href="#cb13-19" aria-hidden="true" tabindex="-1"></a><span class="bu">print</span>(<span class="st">"Final evaluation dataset:"</span>)</span>
<span id="cb13-20"><a href="#cb13-20" aria-hidden="true" tabindex="-1"></a>display(</span>
<span id="cb13-21"><a href="#cb13-21" aria-hidden="true" tabindex="-1"></a> generated_questions[</span>
<span id="cb13-22"><a href="#cb13-22" aria-hidden="true" tabindex="-1"></a> [<span class="st">"question"</span>, <span class="st">"answer"</span>, <span class="st">"groundedness_score"</span>, <span class="st">"relevance_score"</span>, <span class="st">"standalone_score"</span>]</span>
<span id="cb13-23"><a href="#cb13-23" aria-hidden="true" tabindex="-1"></a> ]</span>
<span id="cb13-24"><a href="#cb13-24" aria-hidden="true" tabindex="-1"></a>)</span>
<span id="cb13-25"><a href="#cb13-25" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb13-26"><a href="#cb13-26" aria-hidden="true" tabindex="-1"></a>eval_dataset <span class="op">=</span> datasets.Dataset.from_pandas(</span>
<span id="cb13-27"><a href="#cb13-27" aria-hidden="true" tabindex="-1"></a> generated_questions, split<span class="op">=</span><span class="st">"train"</span>, preserve_index<span class="op">=</span><span class="va">False</span></span>
<span id="cb13-28"><a href="#cb13-28" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<p>Now our synthetic evaluation dataset is complete! We can evaluate different RAG systems on this evaluation dataset.</p>
<p>We have generated only a few QA couples here to reduce time and cost. But let’s kick start the next part by loading a pre-generated dataset:</p>
<div id="9e9d2a9f" class="cell" data-execution_count="14">
<div class="sourceCode cell-code" id="cb14"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb14-1"><a href="#cb14-1" aria-hidden="true" tabindex="-1"></a>eval_dataset <span class="op">=</span> datasets.load_dataset(<span class="st">"m-ric/huggingface_doc_qa_eval"</span>, split<span class="op">=</span><span class="st">"train"</span>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
</section>
</section>
<section id="build-our-rag-system" class="level1">
<h1>2. Build our RAG System</h1>
<section id="preprocessing-documents-to-build-our-vector-database" class="level3">
<h3 class="anchored" data-anchor-id="preprocessing-documents-to-build-our-vector-database">2.1. Preprocessing documents to build our vector database</h3>
<ul>
<li>In this part, <strong>we split the documents from our knowledge base into smaller chunks</strong>: these will be the snippets that are picked by the Retriever, to then be ingested by the Reader LLM as supporting elements for its answer.</li>
<li>The goal is to build semantically relevant snippets: not too small to be sufficient for supporting an answer, and not too large too avoid diluting individual ideas.</li>
</ul>
<p>Many options exist for text splitting: - split every <code>n</code> words / characters, but this has the risk of cutting in half paragraphs or even sentences - split after <code>n</code> words / character, but only on sentence boundaries - <strong>recursive split</strong> tries to preserve even more of the document structure, by processing it tree-like way, splitting first on the largest units (chapters) then recursively splitting on smaller units (paragraphs, sentences).</p>
<p>To learn more about chunking, I recommend you read <a href="https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/5_Levels_Of_Text_Splitting.ipynb">this great notebook</a> by Greg Kamradt.</p>
<p><a href="https://huggingface.co/spaces/m-ric/chunk_visualizer">This space</a> lets you visualize how different splitting options affect the chunks you get.</p>
<blockquote class="blockquote">
<p>In the following, we use Langchain’s <code>RecursiveCharacterTextSplitter</code>.</p>
</blockquote>
<p>💡 <em>To measure chunk length in our Text Splitter, our length function will not be the count of characters, but the count of tokens in the tokenized text: indeed, for subsequent embedder that processes token, measuring length in tokens is more relevant and empirically performs better.</em></p>
<div id="94af026d" class="cell" data-execution_count="15">
<div class="sourceCode cell-code" id="cb15"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb15-1"><a href="#cb15-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.docstore.document <span class="im">import</span> Document <span class="im">as</span> LangchainDocument</span>
<span id="cb15-2"><a href="#cb15-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb15-3"><a href="#cb15-3" aria-hidden="true" tabindex="-1"></a>RAW_KNOWLEDGE_BASE <span class="op">=</span> [</span>
<span id="cb15-4"><a href="#cb15-4" aria-hidden="true" tabindex="-1"></a> LangchainDocument(page_content<span class="op">=</span>doc[<span class="st">"text"</span>], metadata<span class="op">=</span>{<span class="st">"source"</span>: doc[<span class="st">"source"</span>]})</span>
<span id="cb15-5"><a href="#cb15-5" aria-hidden="true" tabindex="-1"></a> <span class="cf">for</span> doc <span class="kw">in</span> tqdm(ds)</span>
<span id="cb15-6"><a href="#cb15-6" aria-hidden="true" tabindex="-1"></a>]</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div id="13cebd63" class="cell" data-execution_count="16">
<div class="sourceCode cell-code" id="cb16"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb16-1"><a href="#cb16-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.text_splitter <span class="im">import</span> RecursiveCharacterTextSplitter</span>
<span id="cb16-2"><a href="#cb16-2" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> transformers <span class="im">import</span> AutoTokenizer</span>
<span id="cb16-3"><a href="#cb16-3" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb16-4"><a href="#cb16-4" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb16-5"><a href="#cb16-5" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> split_documents(</span>
<span id="cb16-6"><a href="#cb16-6" aria-hidden="true" tabindex="-1"></a> chunk_size: <span class="bu">int</span>,</span>
<span id="cb16-7"><a href="#cb16-7" aria-hidden="true" tabindex="-1"></a> knowledge_base: List[LangchainDocument],</span>
<span id="cb16-8"><a href="#cb16-8" aria-hidden="true" tabindex="-1"></a> tokenizer_name: <span class="bu">str</span>,</span>
<span id="cb16-9"><a href="#cb16-9" aria-hidden="true" tabindex="-1"></a>) <span class="op">-></span> List[LangchainDocument]:</span>
<span id="cb16-10"><a href="#cb16-10" aria-hidden="true" tabindex="-1"></a> <span class="co">"""</span></span>
<span id="cb16-11"><a href="#cb16-11" aria-hidden="true" tabindex="-1"></a><span class="co"> Split documents into chunks of size `chunk_size` characters and return a list of documents.</span></span>
<span id="cb16-12"><a href="#cb16-12" aria-hidden="true" tabindex="-1"></a><span class="co"> """</span></span>
<span id="cb16-13"><a href="#cb16-13" aria-hidden="true" tabindex="-1"></a> text_splitter <span class="op">=</span> RecursiveCharacterTextSplitter.from_huggingface_tokenizer(</span>
<span id="cb16-14"><a href="#cb16-14" aria-hidden="true" tabindex="-1"></a> AutoTokenizer.from_pretrained(tokenizer_name),</span>
<span id="cb16-15"><a href="#cb16-15" aria-hidden="true" tabindex="-1"></a> chunk_size<span class="op">=</span>chunk_size,</span>
<span id="cb16-16"><a href="#cb16-16" aria-hidden="true" tabindex="-1"></a> chunk_overlap<span class="op">=</span><span class="bu">int</span>(chunk_size <span class="op">/</span> <span class="dv">10</span>),</span>
<span id="cb16-17"><a href="#cb16-17" aria-hidden="true" tabindex="-1"></a> add_start_index<span class="op">=</span><span class="va">True</span>,</span>
<span id="cb16-18"><a href="#cb16-18" aria-hidden="true" tabindex="-1"></a> strip_whitespace<span class="op">=</span><span class="va">True</span>,</span>
<span id="cb16-19"><a href="#cb16-19" aria-hidden="true" tabindex="-1"></a> separators<span class="op">=</span>[<span class="st">"</span><span class="ch">\n\n</span><span class="st">"</span>, <span class="st">"</span><span class="ch">\n</span><span class="st">"</span>, <span class="st">"."</span>, <span class="st">" "</span>, <span class="st">""</span>],</span>
<span id="cb16-20"><a href="#cb16-20" aria-hidden="true" tabindex="-1"></a> )</span>
<span id="cb16-21"><a href="#cb16-21" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb16-22"><a href="#cb16-22" aria-hidden="true" tabindex="-1"></a> docs_processed <span class="op">=</span> []</span>
<span id="cb16-23"><a href="#cb16-23" aria-hidden="true" tabindex="-1"></a> <span class="cf">for</span> doc <span class="kw">in</span> knowledge_base:</span>
<span id="cb16-24"><a href="#cb16-24" aria-hidden="true" tabindex="-1"></a> docs_processed <span class="op">+=</span> text_splitter.split_documents([doc])</span>
<span id="cb16-25"><a href="#cb16-25" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb16-26"><a href="#cb16-26" aria-hidden="true" tabindex="-1"></a> <span class="co"># Remove duplicates</span></span>
<span id="cb16-27"><a href="#cb16-27" aria-hidden="true" tabindex="-1"></a> unique_texts <span class="op">=</span> {}</span>
<span id="cb16-28"><a href="#cb16-28" aria-hidden="true" tabindex="-1"></a> docs_processed_unique <span class="op">=</span> []</span>
<span id="cb16-29"><a href="#cb16-29" aria-hidden="true" tabindex="-1"></a> <span class="cf">for</span> doc <span class="kw">in</span> docs_processed:</span>
<span id="cb16-30"><a href="#cb16-30" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> doc.page_content <span class="kw">not</span> <span class="kw">in</span> unique_texts:</span>
<span id="cb16-31"><a href="#cb16-31" aria-hidden="true" tabindex="-1"></a> unique_texts[doc.page_content] <span class="op">=</span> <span class="va">True</span></span>
<span id="cb16-32"><a href="#cb16-32" aria-hidden="true" tabindex="-1"></a> docs_processed_unique.append(doc)</span>
<span id="cb16-33"><a href="#cb16-33" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb16-34"><a href="#cb16-34" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> docs_processed_unique</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
</section>
<section id="retriever---embeddings" class="level3">
<h3 class="anchored" data-anchor-id="retriever---embeddings">2.2. Retriever - embeddings 🗂️</h3>
<p>The <strong>retriever acts like an internal search engine</strong>: given the user query, it returns the most relevant documents from your knowledge base.</p>
<blockquote class="blockquote">
<p>For the knowledge base, we use Langchain vector databases since <strong>it offers a convenient <a href="https://github.com/facebookresearch/faiss">FAISS</a> index and allows us to keep document metadata throughout the processing</strong>.</p>
</blockquote>
<p>🛠️ <strong>Options included:</strong></p>
<ul>
<li>Tune the chunking method:
<ul>
<li>Size of the chunks</li>
<li>Method: split on different separators, use <a href="https://python.langchain.com/docs/modules/data_connection/document_transformers/semantic-chunker">semantic chunking</a>…</li>
</ul></li>
<li>Change the embedding model</li>
</ul>
<div id="8f7371a4" class="cell" data-execution_count="17">
<div class="sourceCode cell-code" id="cb17"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb17-1"><a href="#cb17-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.vectorstores <span class="im">import</span> FAISS</span>
<span id="cb17-2"><a href="#cb17-2" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain_community.embeddings <span class="im">import</span> HuggingFaceEmbeddings</span>
<span id="cb17-3"><a href="#cb17-3" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain_community.vectorstores.utils <span class="im">import</span> DistanceStrategy</span>
<span id="cb17-4"><a href="#cb17-4" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> os</span>
<span id="cb17-5"><a href="#cb17-5" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb17-6"><a href="#cb17-6" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb17-7"><a href="#cb17-7" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> load_embeddings(</span>
<span id="cb17-8"><a href="#cb17-8" aria-hidden="true" tabindex="-1"></a> langchain_docs: List[LangchainDocument],</span>
<span id="cb17-9"><a href="#cb17-9" aria-hidden="true" tabindex="-1"></a> chunk_size: <span class="bu">int</span>,</span>
<span id="cb17-10"><a href="#cb17-10" aria-hidden="true" tabindex="-1"></a> embedding_model_name: Optional[<span class="bu">str</span>] <span class="op">=</span> <span class="st">"thenlper/gte-small"</span>,</span>
<span id="cb17-11"><a href="#cb17-11" aria-hidden="true" tabindex="-1"></a>) <span class="op">-></span> FAISS:</span>
<span id="cb17-12"><a href="#cb17-12" aria-hidden="true" tabindex="-1"></a> <span class="co">"""</span></span>
<span id="cb17-13"><a href="#cb17-13" aria-hidden="true" tabindex="-1"></a><span class="co"> Creates a FAISS index from the given embedding model and documents. Loads the index directly if it already exists.</span></span>
<span id="cb17-14"><a href="#cb17-14" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb17-15"><a href="#cb17-15" aria-hidden="true" tabindex="-1"></a><span class="co"> Args:</span></span>
<span id="cb17-16"><a href="#cb17-16" aria-hidden="true" tabindex="-1"></a><span class="co"> langchain_docs: list of documents</span></span>
<span id="cb17-17"><a href="#cb17-17" aria-hidden="true" tabindex="-1"></a><span class="co"> chunk_size: size of the chunks to split the documents into</span></span>
<span id="cb17-18"><a href="#cb17-18" aria-hidden="true" tabindex="-1"></a><span class="co"> embedding_model_name: name of the embedding model to use</span></span>
<span id="cb17-19"><a href="#cb17-19" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb17-20"><a href="#cb17-20" aria-hidden="true" tabindex="-1"></a><span class="co"> Returns:</span></span>
<span id="cb17-21"><a href="#cb17-21" aria-hidden="true" tabindex="-1"></a><span class="co"> FAISS index</span></span>
<span id="cb17-22"><a href="#cb17-22" aria-hidden="true" tabindex="-1"></a><span class="co"> """</span></span>
<span id="cb17-23"><a href="#cb17-23" aria-hidden="true" tabindex="-1"></a> <span class="co"># load embedding_model</span></span>
<span id="cb17-24"><a href="#cb17-24" aria-hidden="true" tabindex="-1"></a> embedding_model <span class="op">=</span> HuggingFaceEmbeddings(</span>
<span id="cb17-25"><a href="#cb17-25" aria-hidden="true" tabindex="-1"></a> model_name<span class="op">=</span>embedding_model_name,</span>
<span id="cb17-26"><a href="#cb17-26" aria-hidden="true" tabindex="-1"></a> multi_process<span class="op">=</span><span class="va">True</span>,</span>
<span id="cb17-27"><a href="#cb17-27" aria-hidden="true" tabindex="-1"></a> model_kwargs<span class="op">=</span>{<span class="st">"device"</span>: <span class="st">"cuda"</span>},</span>
<span id="cb17-28"><a href="#cb17-28" aria-hidden="true" tabindex="-1"></a> encode_kwargs<span class="op">=</span>{<span class="st">"normalize_embeddings"</span>: <span class="va">True</span>}, <span class="co"># set True to compute cosine similarity</span></span>
<span id="cb17-29"><a href="#cb17-29" aria-hidden="true" tabindex="-1"></a> )</span>
<span id="cb17-30"><a href="#cb17-30" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb17-31"><a href="#cb17-31" aria-hidden="true" tabindex="-1"></a> <span class="co"># Check if embeddings already exist on disk</span></span>
<span id="cb17-32"><a href="#cb17-32" aria-hidden="true" tabindex="-1"></a> index_name <span class="op">=</span> <span class="ss">f"index_chunk:</span><span class="sc">{</span>chunk_size<span class="sc">}</span><span class="ss">_embeddings:</span><span class="sc">{</span>embedding_model_name<span class="sc">.</span>replace(<span class="st">'/'</span>, <span class="st">'~'</span>)<span class="sc">}</span><span class="ss">"</span></span>
<span id="cb17-33"><a href="#cb17-33" aria-hidden="true" tabindex="-1"></a> index_folder_path <span class="op">=</span> <span class="ss">f"./data/indexes/</span><span class="sc">{</span>index_name<span class="sc">}</span><span class="ss">/"</span></span>
<span id="cb17-34"><a href="#cb17-34" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> os.path.isdir(index_folder_path):</span>
<span id="cb17-35"><a href="#cb17-35" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> FAISS.load_local(</span>
<span id="cb17-36"><a href="#cb17-36" aria-hidden="true" tabindex="-1"></a> index_folder_path,</span>
<span id="cb17-37"><a href="#cb17-37" aria-hidden="true" tabindex="-1"></a> embedding_model,</span>
<span id="cb17-38"><a href="#cb17-38" aria-hidden="true" tabindex="-1"></a> distance_strategy<span class="op">=</span>DistanceStrategy.COSINE,</span>
<span id="cb17-39"><a href="#cb17-39" aria-hidden="true" tabindex="-1"></a> )</span>
<span id="cb17-40"><a href="#cb17-40" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb17-41"><a href="#cb17-41" aria-hidden="true" tabindex="-1"></a> <span class="cf">else</span>:</span>
<span id="cb17-42"><a href="#cb17-42" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="st">"Index not found, generating it..."</span>)</span>
<span id="cb17-43"><a href="#cb17-43" aria-hidden="true" tabindex="-1"></a> docs_processed <span class="op">=</span> split_documents(</span>
<span id="cb17-44"><a href="#cb17-44" aria-hidden="true" tabindex="-1"></a> chunk_size,</span>
<span id="cb17-45"><a href="#cb17-45" aria-hidden="true" tabindex="-1"></a> langchain_docs,</span>
<span id="cb17-46"><a href="#cb17-46" aria-hidden="true" tabindex="-1"></a> embedding_model_name,</span>
<span id="cb17-47"><a href="#cb17-47" aria-hidden="true" tabindex="-1"></a> )</span>
<span id="cb17-48"><a href="#cb17-48" aria-hidden="true" tabindex="-1"></a> knowledge_index <span class="op">=</span> FAISS.from_documents(</span>
<span id="cb17-49"><a href="#cb17-49" aria-hidden="true" tabindex="-1"></a> docs_processed, embedding_model, distance_strategy<span class="op">=</span>DistanceStrategy.COSINE</span>
<span id="cb17-50"><a href="#cb17-50" aria-hidden="true" tabindex="-1"></a> )</span>
<span id="cb17-51"><a href="#cb17-51" aria-hidden="true" tabindex="-1"></a> knowledge_index.save_local(index_folder_path)</span>
<span id="cb17-52"><a href="#cb17-52" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> knowledge_index</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
</section>
<section id="reader---llm" class="level3">
<h3 class="anchored" data-anchor-id="reader---llm">2.3. Reader - LLM 💬</h3>
<p>In this part, the <strong>LLM Reader reads the retrieved documents to formulate its answer.</strong></p>
<p>🛠️ Here we tried the following options to improve results: - Switch reranking on/off - Change the reader model</p>
<div id="843d7987" class="cell" data-execution_count="18">
<div class="sourceCode cell-code" id="cb18"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb18-1"><a href="#cb18-1" aria-hidden="true" tabindex="-1"></a>RAG_PROMPT_TEMPLATE <span class="op">=</span> <span class="st">"""</span></span>
<span id="cb18-2"><a href="#cb18-2" aria-hidden="true" tabindex="-1"></a><span class="st"><|system|></span></span>
<span id="cb18-3"><a href="#cb18-3" aria-hidden="true" tabindex="-1"></a><span class="st">Using the information contained in the context,</span></span>
<span id="cb18-4"><a href="#cb18-4" aria-hidden="true" tabindex="-1"></a><span class="st">give a comprehensive answer to the question.</span></span>
<span id="cb18-5"><a href="#cb18-5" aria-hidden="true" tabindex="-1"></a><span class="st">Respond only to the question asked, response should be concise and relevant to the question.</span></span>
<span id="cb18-6"><a href="#cb18-6" aria-hidden="true" tabindex="-1"></a><span class="st">Provide the number of the source document when relevant.</span></span>
<span id="cb18-7"><a href="#cb18-7" aria-hidden="true" tabindex="-1"></a><span class="st">If the answer cannot be deduced from the context, do not give an answer.</s></span></span>
<span id="cb18-8"><a href="#cb18-8" aria-hidden="true" tabindex="-1"></a><span class="st"><|user|></span></span>
<span id="cb18-9"><a href="#cb18-9" aria-hidden="true" tabindex="-1"></a><span class="st">Context:</span></span>
<span id="cb18-10"><a href="#cb18-10" aria-hidden="true" tabindex="-1"></a><span class="sc">{context}</span></span>
<span id="cb18-11"><a href="#cb18-11" aria-hidden="true" tabindex="-1"></a><span class="st">---</span></span>
<span id="cb18-12"><a href="#cb18-12" aria-hidden="true" tabindex="-1"></a><span class="st">Now here is the question you need to answer.</span></span>
<span id="cb18-13"><a href="#cb18-13" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb18-14"><a href="#cb18-14" aria-hidden="true" tabindex="-1"></a><span class="st">Question: </span><span class="sc">{question}</span></span>
<span id="cb18-15"><a href="#cb18-15" aria-hidden="true" tabindex="-1"></a><span class="st"></s></span></span>
<span id="cb18-16"><a href="#cb18-16" aria-hidden="true" tabindex="-1"></a><span class="st"><|assistant|></span></span>
<span id="cb18-17"><a href="#cb18-17" aria-hidden="true" tabindex="-1"></a><span class="st">"""</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div id="6884550b" class="cell" data-execution_count="19">
<div class="sourceCode cell-code" id="cb19"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb19-1"><a href="#cb19-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain_community.llms <span class="im">import</span> HuggingFaceHub</span>
<span id="cb19-2"><a href="#cb19-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb19-3"><a href="#cb19-3" aria-hidden="true" tabindex="-1"></a>repo_id <span class="op">=</span> <span class="st">"HuggingFaceH4/zephyr-7b-beta"</span></span>
<span id="cb19-4"><a href="#cb19-4" aria-hidden="true" tabindex="-1"></a>READER_MODEL_NAME <span class="op">=</span> <span class="st">"zephyr-7b-beta"</span></span>
<span id="cb19-5"><a href="#cb19-5" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb19-6"><a href="#cb19-6" aria-hidden="true" tabindex="-1"></a>READER_LLM <span class="op">=</span> HuggingFaceHub(</span>
<span id="cb19-7"><a href="#cb19-7" aria-hidden="true" tabindex="-1"></a> repo_id<span class="op">=</span>repo_id,</span>
<span id="cb19-8"><a href="#cb19-8" aria-hidden="true" tabindex="-1"></a> task<span class="op">=</span><span class="st">"text-generation"</span>,</span>
<span id="cb19-9"><a href="#cb19-9" aria-hidden="true" tabindex="-1"></a> model_kwargs<span class="op">=</span>{</span>
<span id="cb19-10"><a href="#cb19-10" aria-hidden="true" tabindex="-1"></a> <span class="st">"max_new_tokens"</span>: <span class="dv">512</span>,</span>
<span id="cb19-11"><a href="#cb19-11" aria-hidden="true" tabindex="-1"></a> <span class="st">"top_k"</span>: <span class="dv">30</span>,</span>
<span id="cb19-12"><a href="#cb19-12" aria-hidden="true" tabindex="-1"></a> <span class="st">"temperature"</span>: <span class="fl">0.1</span>,</span>
<span id="cb19-13"><a href="#cb19-13" aria-hidden="true" tabindex="-1"></a> <span class="st">"repetition_penalty"</span>: <span class="fl">1.03</span>,</span>
<span id="cb19-14"><a href="#cb19-14" aria-hidden="true" tabindex="-1"></a> },</span>
<span id="cb19-15"><a href="#cb19-15" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div id="143d4d0b" class="cell" data-execution_count="20">
<div class="sourceCode cell-code" id="cb20"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb20-1"><a href="#cb20-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> ragatouille <span class="im">import</span> RAGPretrainedModel</span>
<span id="cb20-2"><a href="#cb20-2" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain_core.vectorstores <span class="im">import</span> VectorStore</span>
<span id="cb20-3"><a href="#cb20-3" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain_core.language_models.llms <span class="im">import</span> LLM</span>
<span id="cb20-4"><a href="#cb20-4" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb20-5"><a href="#cb20-5" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb20-6"><a href="#cb20-6" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> answer_with_rag(</span>
<span id="cb20-7"><a href="#cb20-7" aria-hidden="true" tabindex="-1"></a> question: <span class="bu">str</span>,</span>
<span id="cb20-8"><a href="#cb20-8" aria-hidden="true" tabindex="-1"></a> llm: LLM,</span>
<span id="cb20-9"><a href="#cb20-9" aria-hidden="true" tabindex="-1"></a> knowledge_index: VectorStore,</span>
<span id="cb20-10"><a href="#cb20-10" aria-hidden="true" tabindex="-1"></a> reranker: Optional[RAGPretrainedModel] <span class="op">=</span> <span class="va">None</span>,</span>
<span id="cb20-11"><a href="#cb20-11" aria-hidden="true" tabindex="-1"></a> num_retrieved_docs: <span class="bu">int</span> <span class="op">=</span> <span class="dv">30</span>,</span>
<span id="cb20-12"><a href="#cb20-12" aria-hidden="true" tabindex="-1"></a> num_docs_final: <span class="bu">int</span> <span class="op">=</span> <span class="dv">7</span>,</span>
<span id="cb20-13"><a href="#cb20-13" aria-hidden="true" tabindex="-1"></a>) <span class="op">-></span> Tuple[<span class="bu">str</span>, List[LangchainDocument]]:</span>
<span id="cb20-14"><a href="#cb20-14" aria-hidden="true" tabindex="-1"></a> <span class="co">"""Answer a question using RAG with the given knowledge index."""</span></span>
<span id="cb20-15"><a href="#cb20-15" aria-hidden="true" tabindex="-1"></a> <span class="co"># Gather documents with retriever</span></span>
<span id="cb20-16"><a href="#cb20-16" aria-hidden="true" tabindex="-1"></a> relevant_docs <span class="op">=</span> knowledge_index.similarity_search(query<span class="op">=</span>question, k<span class="op">=</span>num_retrieved_docs)</span>
<span id="cb20-17"><a href="#cb20-17" aria-hidden="true" tabindex="-1"></a> relevant_docs <span class="op">=</span> [doc.page_content <span class="cf">for</span> doc <span class="kw">in</span> relevant_docs] <span class="co"># keep only the text</span></span>
<span id="cb20-18"><a href="#cb20-18" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb20-19"><a href="#cb20-19" aria-hidden="true" tabindex="-1"></a> <span class="co"># Optionally rerank results</span></span>
<span id="cb20-20"><a href="#cb20-20" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> reranker:</span>
<span id="cb20-21"><a href="#cb20-21" aria-hidden="true" tabindex="-1"></a> relevant_docs <span class="op">=</span> reranker.rerank(question, relevant_docs, k<span class="op">=</span>num_docs_final)</span>
<span id="cb20-22"><a href="#cb20-22" aria-hidden="true" tabindex="-1"></a> relevant_docs <span class="op">=</span> [doc[<span class="st">"content"</span>] <span class="cf">for</span> doc <span class="kw">in</span> relevant_docs]</span>
<span id="cb20-23"><a href="#cb20-23" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb20-24"><a href="#cb20-24" aria-hidden="true" tabindex="-1"></a> relevant_docs <span class="op">=</span> relevant_docs[:num_docs_final]</span>
<span id="cb20-25"><a href="#cb20-25" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb20-26"><a href="#cb20-26" aria-hidden="true" tabindex="-1"></a> <span class="co"># Build the final prompt</span></span>
<span id="cb20-27"><a href="#cb20-27" aria-hidden="true" tabindex="-1"></a> context <span class="op">=</span> <span class="st">"</span><span class="ch">\n</span><span class="st">Extracted documents:</span><span class="ch">\n</span><span class="st">"</span></span>
<span id="cb20-28"><a href="#cb20-28" aria-hidden="true" tabindex="-1"></a> context <span class="op">+=</span> <span class="st">""</span>.join([<span class="ss">f"Document </span><span class="sc">{</span><span class="bu">str</span>(i)<span class="sc">}</span><span class="ss">:::</span><span class="ch">\n</span><span class="ss">"</span> <span class="op">+</span> doc <span class="cf">for</span> i, doc <span class="kw">in</span> <span class="bu">enumerate</span>(relevant_docs)])</span>
<span id="cb20-29"><a href="#cb20-29" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb20-30"><a href="#cb20-30" aria-hidden="true" tabindex="-1"></a> final_prompt <span class="op">=</span> RAG_PROMPT_TEMPLATE.<span class="bu">format</span>(question<span class="op">=</span>question, context<span class="op">=</span>context)</span>
<span id="cb20-31"><a href="#cb20-31" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb20-32"><a href="#cb20-32" aria-hidden="true" tabindex="-1"></a> <span class="co"># Redact an answer</span></span>
<span id="cb20-33"><a href="#cb20-33" aria-hidden="true" tabindex="-1"></a> answer <span class="op">=</span> llm(final_prompt)</span>
<span id="cb20-34"><a href="#cb20-34" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb20-35"><a href="#cb20-35" aria-hidden="true" tabindex="-1"></a> <span class="cf">return</span> answer, relevant_docs</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
</section>
</section>
<section id="benchmarking-the-rag-system" class="level1">
<h1>3. Benchmarking the RAG system</h1>
<p>The RAG system and the evaluation datasets are now ready. The last step is to judge the RAG system’s output on this evlauation dataset.</p>
<p>To this end, <strong>we setup a judge agent</strong>. ⚖️🤖</p>
<p>Out of <a href="https://docs.ragas.io/en/latest/concepts/metrics/index.html">the different RAG evaluation metrics</a>, we choose to focus only on faithfulness since it the best end-to-end metric of our system’s performance.</p>
<blockquote class="blockquote">
<p>We use GPT4 as a judge for its empirically good performance, but you could try with other models such as <a href="https://huggingface.co/kaist-ai/prometheus-13b-v1.0">kaist-ai/prometheus-13b-v1.0</a> or <a href="https://huggingface.co/BAAI/JudgeLM-33B-v1.0">BAAI/JudgeLM-33B-v1.0</a>.</p>
</blockquote>
<p>💡 <em>In the evaluation prompt, we give a detailed description each metric on the scale 1-5, as is done in <a href="https://huggingface.co/kaist-ai/prometheus-13b-v1.0">Prometheus’s prompt template</a>: this helps the model ground its metric precisely. If instead you give the judge LLM a vague scale to work with, the outputs will not be consistent enough between different examples.</em></p>
<p>💡 <em>Again, prompting the LLM to output rationale before giving its final score gives it more tokens to help it formalize and elaborate a judgement.</em></p>
<div id="ce53b5ec" class="cell" data-execution_count="21">
<div class="sourceCode cell-code" id="cb21"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb21-1"><a href="#cb21-1" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> run_rag_tests(</span>
<span id="cb21-2"><a href="#cb21-2" aria-hidden="true" tabindex="-1"></a> eval_dataset: datasets.Dataset,</span>
<span id="cb21-3"><a href="#cb21-3" aria-hidden="true" tabindex="-1"></a> llm: BaseChatModel,</span>
<span id="cb21-4"><a href="#cb21-4" aria-hidden="true" tabindex="-1"></a> knowledge_index: VectorStore,</span>
<span id="cb21-5"><a href="#cb21-5" aria-hidden="true" tabindex="-1"></a> output_file: <span class="bu">str</span>,</span>
<span id="cb21-6"><a href="#cb21-6" aria-hidden="true" tabindex="-1"></a> reranker: Optional[RAGPretrainedModel] <span class="op">=</span> <span class="va">None</span>,</span>
<span id="cb21-7"><a href="#cb21-7" aria-hidden="true" tabindex="-1"></a> verbose: Optional[<span class="bu">bool</span>] <span class="op">=</span> <span class="va">True</span>,</span>
<span id="cb21-8"><a href="#cb21-8" aria-hidden="true" tabindex="-1"></a> test_settings: Optional[<span class="bu">str</span>] <span class="op">=</span> <span class="va">None</span>, <span class="co"># To document the test settings used</span></span>
<span id="cb21-9"><a href="#cb21-9" aria-hidden="true" tabindex="-1"></a>):</span>
<span id="cb21-10"><a href="#cb21-10" aria-hidden="true" tabindex="-1"></a> <span class="co">"""Runs RAG tests on the given dataset and saves the results to the given output file."""</span></span>
<span id="cb21-11"><a href="#cb21-11" aria-hidden="true" tabindex="-1"></a> <span class="cf">try</span>: <span class="co"># load previous generations if they exist</span></span>
<span id="cb21-12"><a href="#cb21-12" aria-hidden="true" tabindex="-1"></a> <span class="cf">with</span> <span class="bu">open</span>(output_file, <span class="st">"r"</span>) <span class="im">as</span> f:</span>
<span id="cb21-13"><a href="#cb21-13" aria-hidden="true" tabindex="-1"></a> outputs <span class="op">=</span> json.load(f)</span>
<span id="cb21-14"><a href="#cb21-14" aria-hidden="true" tabindex="-1"></a> <span class="cf">except</span>:</span>
<span id="cb21-15"><a href="#cb21-15" aria-hidden="true" tabindex="-1"></a> outputs <span class="op">=</span> []</span>
<span id="cb21-16"><a href="#cb21-16" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb21-17"><a href="#cb21-17" aria-hidden="true" tabindex="-1"></a> <span class="cf">for</span> example <span class="kw">in</span> tqdm(eval_dataset):</span>
<span id="cb21-18"><a href="#cb21-18" aria-hidden="true" tabindex="-1"></a> question <span class="op">=</span> example[<span class="st">"question"</span>]</span>
<span id="cb21-19"><a href="#cb21-19" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> question <span class="kw">in</span> [output[<span class="st">"question"</span>] <span class="cf">for</span> output <span class="kw">in</span> outputs]:</span>
<span id="cb21-20"><a href="#cb21-20" aria-hidden="true" tabindex="-1"></a> <span class="cf">continue</span></span>
<span id="cb21-21"><a href="#cb21-21" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb21-22"><a href="#cb21-22" aria-hidden="true" tabindex="-1"></a> answer, relevant_docs <span class="op">=</span> answer_with_rag(question, llm, knowledge_index, reranker<span class="op">=</span>reranker)</span>
<span id="cb21-23"><a href="#cb21-23" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> verbose:</span>
<span id="cb21-24"><a href="#cb21-24" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="st">"======================================================="</span>)</span>
<span id="cb21-25"><a href="#cb21-25" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="ss">f"Question: </span><span class="sc">{</span>question<span class="sc">}</span><span class="ss">"</span>)</span>
<span id="cb21-26"><a href="#cb21-26" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="ss">f"Answer: </span><span class="sc">{</span>answer<span class="sc">}</span><span class="ss">"</span>)</span>
<span id="cb21-27"><a href="#cb21-27" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="ss">f'True answer: </span><span class="sc">{</span>example[<span class="st">"answer"</span>]<span class="sc">}</span><span class="ss">'</span>)</span>
<span id="cb21-28"><a href="#cb21-28" aria-hidden="true" tabindex="-1"></a> result <span class="op">=</span> {</span>
<span id="cb21-29"><a href="#cb21-29" aria-hidden="true" tabindex="-1"></a> <span class="st">"question"</span>: question,</span>
<span id="cb21-30"><a href="#cb21-30" aria-hidden="true" tabindex="-1"></a> <span class="st">"true_answer"</span>: example[<span class="st">"answer"</span>],</span>
<span id="cb21-31"><a href="#cb21-31" aria-hidden="true" tabindex="-1"></a> <span class="st">"source_doc"</span>: example[<span class="st">"source_doc"</span>],</span>
<span id="cb21-32"><a href="#cb21-32" aria-hidden="true" tabindex="-1"></a> <span class="st">"generated_answer"</span>: answer,</span>
<span id="cb21-33"><a href="#cb21-33" aria-hidden="true" tabindex="-1"></a> <span class="st">"retrieved_docs"</span>: [doc <span class="cf">for</span> doc <span class="kw">in</span> relevant_docs],</span>
<span id="cb21-34"><a href="#cb21-34" aria-hidden="true" tabindex="-1"></a> }</span>
<span id="cb21-35"><a href="#cb21-35" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> test_settings:</span>
<span id="cb21-36"><a href="#cb21-36" aria-hidden="true" tabindex="-1"></a> result[<span class="st">"test_settings"</span>] <span class="op">=</span> test_settings</span>
<span id="cb21-37"><a href="#cb21-37" aria-hidden="true" tabindex="-1"></a> outputs.append(result)</span>
<span id="cb21-38"><a href="#cb21-38" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb21-39"><a href="#cb21-39" aria-hidden="true" tabindex="-1"></a> <span class="cf">with</span> <span class="bu">open</span>(output_file, <span class="st">"w"</span>) <span class="im">as</span> f:</span>
<span id="cb21-40"><a href="#cb21-40" aria-hidden="true" tabindex="-1"></a> json.dump(outputs, f)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div id="49f7ef44" class="cell" data-execution_count="22">
<div class="sourceCode cell-code" id="cb22"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb22-1"><a href="#cb22-1" aria-hidden="true" tabindex="-1"></a>EVALUATION_PROMPT <span class="op">=</span> <span class="st">"""###Task Description:</span></span>
<span id="cb22-2"><a href="#cb22-2" aria-hidden="true" tabindex="-1"></a><span class="st">An instruction (might include an Input inside it), a response to evaluate, a reference answer that gets a score of 5, and a score rubric representing a evaluation criteria are given.</span></span>
<span id="cb22-3"><a href="#cb22-3" aria-hidden="true" tabindex="-1"></a><span class="st">1. Write a detailed feedback that assess the quality of the response strictly based on the given score rubric, not evaluating in general.</span></span>
<span id="cb22-4"><a href="#cb22-4" aria-hidden="true" tabindex="-1"></a><span class="st">2. After writing a feedback, write a score that is an integer between 1 and 5. You should refer to the score rubric.</span></span>
<span id="cb22-5"><a href="#cb22-5" aria-hidden="true" tabindex="-1"></a><span class="st">3. The output format should look as follows: </span><span class="ch">\"</span><span class="st">Feedback: </span><span class="sc">{{</span><span class="st">write a feedback for criteria</span><span class="sc">}}</span><span class="st"> [RESULT] </span><span class="sc">{{</span><span class="st">an integer number between 1 and 5</span><span class="sc">}}</span><span class="ch">\"</span></span>
<span id="cb22-6"><a href="#cb22-6" aria-hidden="true" tabindex="-1"></a><span class="st">4. Please do not generate any other opening, closing, and explanations. Be sure to include [RESULT] in your output.</span></span>
<span id="cb22-7"><a href="#cb22-7" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb22-8"><a href="#cb22-8" aria-hidden="true" tabindex="-1"></a><span class="st">###The instruction to evaluate:</span></span>
<span id="cb22-9"><a href="#cb22-9" aria-hidden="true" tabindex="-1"></a><span class="sc">{instruction}</span></span>
<span id="cb22-10"><a href="#cb22-10" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb22-11"><a href="#cb22-11" aria-hidden="true" tabindex="-1"></a><span class="st">###Response to evaluate:</span></span>
<span id="cb22-12"><a href="#cb22-12" aria-hidden="true" tabindex="-1"></a><span class="sc">{response}</span></span>
<span id="cb22-13"><a href="#cb22-13" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb22-14"><a href="#cb22-14" aria-hidden="true" tabindex="-1"></a><span class="st">###Reference Answer (Score 5):</span></span>
<span id="cb22-15"><a href="#cb22-15" aria-hidden="true" tabindex="-1"></a><span class="sc">{reference_answer}</span></span>
<span id="cb22-16"><a href="#cb22-16" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb22-17"><a href="#cb22-17" aria-hidden="true" tabindex="-1"></a><span class="st">###Score Rubrics:</span></span>
<span id="cb22-18"><a href="#cb22-18" aria-hidden="true" tabindex="-1"></a><span class="st">[Is the response correct, accurate, and factual based on the reference answer?]</span></span>
<span id="cb22-19"><a href="#cb22-19" aria-hidden="true" tabindex="-1"></a><span class="st">Score 1: The response is completely incorrect, inaccurate, and/or not factual.</span></span>
<span id="cb22-20"><a href="#cb22-20" aria-hidden="true" tabindex="-1"></a><span class="st">Score 2: The response is mostly incorrect, inaccurate, and/or not factual.</span></span>
<span id="cb22-21"><a href="#cb22-21" aria-hidden="true" tabindex="-1"></a><span class="st">Score 3: The response is somewhat correct, accurate, and/or factual.</span></span>
<span id="cb22-22"><a href="#cb22-22" aria-hidden="true" tabindex="-1"></a><span class="st">Score 4: The response is mostly correct, accurate, and factual.</span></span>
<span id="cb22-23"><a href="#cb22-23" aria-hidden="true" tabindex="-1"></a><span class="st">Score 5: The response is completely correct, accurate, and factual.</span></span>
<span id="cb22-24"><a href="#cb22-24" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb22-25"><a href="#cb22-25" aria-hidden="true" tabindex="-1"></a><span class="st">###Feedback:"""</span></span>
<span id="cb22-26"><a href="#cb22-26" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb22-27"><a href="#cb22-27" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.prompts.chat <span class="im">import</span> (</span>
<span id="cb22-28"><a href="#cb22-28" aria-hidden="true" tabindex="-1"></a> ChatPromptTemplate,</span>
<span id="cb22-29"><a href="#cb22-29" aria-hidden="true" tabindex="-1"></a> HumanMessagePromptTemplate,</span>
<span id="cb22-30"><a href="#cb22-30" aria-hidden="true" tabindex="-1"></a>)</span>
<span id="cb22-31"><a href="#cb22-31" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.schema <span class="im">import</span> SystemMessage</span>
<span id="cb22-32"><a href="#cb22-32" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb22-33"><a href="#cb22-33" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb22-34"><a href="#cb22-34" aria-hidden="true" tabindex="-1"></a>evaluation_prompt_template <span class="op">=</span> ChatPromptTemplate.from_messages(</span>
<span id="cb22-35"><a href="#cb22-35" aria-hidden="true" tabindex="-1"></a> [</span>
<span id="cb22-36"><a href="#cb22-36" aria-hidden="true" tabindex="-1"></a> SystemMessage(content<span class="op">=</span><span class="st">"You are a fair evaluator language model."</span>),</span>
<span id="cb22-37"><a href="#cb22-37" aria-hidden="true" tabindex="-1"></a> HumanMessagePromptTemplate.from_template(EVALUATION_PROMPT),</span>
<span id="cb22-38"><a href="#cb22-38" aria-hidden="true" tabindex="-1"></a> ]</span>
<span id="cb22-39"><a href="#cb22-39" aria-hidden="true" tabindex="-1"></a>)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div id="b678d8fe" class="cell" data-execution_count="23">
<div class="sourceCode cell-code" id="cb23"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb23-1"><a href="#cb23-1" aria-hidden="true" tabindex="-1"></a><span class="im">from</span> langchain.chat_models <span class="im">import</span> ChatOpenAI</span>
<span id="cb23-2"><a href="#cb23-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb23-3"><a href="#cb23-3" aria-hidden="true" tabindex="-1"></a>eval_chat_model <span class="op">=</span> ChatOpenAI(model<span class="op">=</span><span class="st">"gpt-4-1106-preview"</span>, temperature<span class="op">=</span><span class="dv">0</span>)</span>
<span id="cb23-4"><a href="#cb23-4" aria-hidden="true" tabindex="-1"></a>evaluator_name <span class="op">=</span> <span class="st">"GPT4"</span></span>
<span id="cb23-5"><a href="#cb23-5" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb23-6"><a href="#cb23-6" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb23-7"><a href="#cb23-7" aria-hidden="true" tabindex="-1"></a><span class="kw">def</span> evaluate_answers(</span>
<span id="cb23-8"><a href="#cb23-8" aria-hidden="true" tabindex="-1"></a> answer_path: <span class="bu">str</span>,</span>
<span id="cb23-9"><a href="#cb23-9" aria-hidden="true" tabindex="-1"></a> eval_chat_model: BaseChatModel,</span>
<span id="cb23-10"><a href="#cb23-10" aria-hidden="true" tabindex="-1"></a> evaluator_name: <span class="bu">str</span>,</span>
<span id="cb23-11"><a href="#cb23-11" aria-hidden="true" tabindex="-1"></a> evaluation_prompt_template: ChatPromptTemplate,</span>
<span id="cb23-12"><a href="#cb23-12" aria-hidden="true" tabindex="-1"></a>) <span class="op">-></span> <span class="va">None</span>:</span>
<span id="cb23-13"><a href="#cb23-13" aria-hidden="true" tabindex="-1"></a> <span class="co">"""Evaluates generated answers. Modifies the given answer file in place for better checkpointing."""</span></span>
<span id="cb23-14"><a href="#cb23-14" aria-hidden="true" tabindex="-1"></a> answers <span class="op">=</span> []</span>
<span id="cb23-15"><a href="#cb23-15" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> os.path.isfile(answer_path): <span class="co"># load previous generations if they exist</span></span>
<span id="cb23-16"><a href="#cb23-16" aria-hidden="true" tabindex="-1"></a> answers <span class="op">=</span> json.load(<span class="bu">open</span>(answer_path, <span class="st">"r"</span>))</span>
<span id="cb23-17"><a href="#cb23-17" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb23-18"><a href="#cb23-18" aria-hidden="true" tabindex="-1"></a> <span class="cf">for</span> experiment <span class="kw">in</span> tqdm(answers):</span>
<span id="cb23-19"><a href="#cb23-19" aria-hidden="true" tabindex="-1"></a> <span class="cf">if</span> <span class="ss">f"eval_score_</span><span class="sc">{</span>evaluator_name<span class="sc">}</span><span class="ss">"</span> <span class="kw">in</span> experiment:</span>
<span id="cb23-20"><a href="#cb23-20" aria-hidden="true" tabindex="-1"></a> <span class="cf">continue</span></span>
<span id="cb23-21"><a href="#cb23-21" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb23-22"><a href="#cb23-22" aria-hidden="true" tabindex="-1"></a> eval_prompt <span class="op">=</span> evaluation_prompt_template.format_messages(</span>
<span id="cb23-23"><a href="#cb23-23" aria-hidden="true" tabindex="-1"></a> instruction<span class="op">=</span>experiment[<span class="st">"question"</span>],</span>
<span id="cb23-24"><a href="#cb23-24" aria-hidden="true" tabindex="-1"></a> response<span class="op">=</span>experiment[<span class="st">"generated_answer"</span>],</span>
<span id="cb23-25"><a href="#cb23-25" aria-hidden="true" tabindex="-1"></a> reference_answer<span class="op">=</span>experiment[<span class="st">"true_answer"</span>],</span>
<span id="cb23-26"><a href="#cb23-26" aria-hidden="true" tabindex="-1"></a> )</span>
<span id="cb23-27"><a href="#cb23-27" aria-hidden="true" tabindex="-1"></a> eval_result <span class="op">=</span> eval_chat_model.invoke(eval_prompt)</span>
<span id="cb23-28"><a href="#cb23-28" aria-hidden="true" tabindex="-1"></a> feedback, score <span class="op">=</span> [item.strip() <span class="cf">for</span> item <span class="kw">in</span> eval_result.content.split(<span class="st">"[RESULT]"</span>)]</span>
<span id="cb23-29"><a href="#cb23-29" aria-hidden="true" tabindex="-1"></a> experiment[<span class="ss">f"eval_score_</span><span class="sc">{</span>evaluator_name<span class="sc">}</span><span class="ss">"</span>] <span class="op">=</span> score</span>
<span id="cb23-30"><a href="#cb23-30" aria-hidden="true" tabindex="-1"></a> experiment[<span class="ss">f"eval_feedback_</span><span class="sc">{</span>evaluator_name<span class="sc">}</span><span class="ss">"</span>] <span class="op">=</span> feedback</span>
<span id="cb23-31"><a href="#cb23-31" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb23-32"><a href="#cb23-32" aria-hidden="true" tabindex="-1"></a> <span class="cf">with</span> <span class="bu">open</span>(answer_path, <span class="st">"w"</span>) <span class="im">as</span> f:</span>
<span id="cb23-33"><a href="#cb23-33" aria-hidden="true" tabindex="-1"></a> json.dump(answers, f)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<p>🚀 Let’s run the tests and evaluate answers!👇</p>
<div id="55f9f502" class="cell" data-execution_count="24">
<div class="sourceCode cell-code" id="cb24"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb24-1"><a href="#cb24-1" aria-hidden="true" tabindex="-1"></a><span class="cf">if</span> <span class="kw">not</span> os.path.exists(<span class="st">"./output"</span>):</span>
<span id="cb24-2"><a href="#cb24-2" aria-hidden="true" tabindex="-1"></a> os.mkdir(<span class="st">"./output"</span>)</span>
<span id="cb24-3"><a href="#cb24-3" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb24-4"><a href="#cb24-4" aria-hidden="true" tabindex="-1"></a><span class="cf">for</span> chunk_size <span class="kw">in</span> [<span class="dv">200</span>]: <span class="co"># Add other chunk sizes (in tokens) as needed</span></span>
<span id="cb24-5"><a href="#cb24-5" aria-hidden="true" tabindex="-1"></a> <span class="cf">for</span> embeddings <span class="kw">in</span> [<span class="st">"thenlper/gte-small"</span>]: <span class="co"># Add other embeddings as needed</span></span>
<span id="cb24-6"><a href="#cb24-6" aria-hidden="true" tabindex="-1"></a> <span class="cf">for</span> rerank <span class="kw">in</span> [<span class="va">True</span>, <span class="va">False</span>]:</span>
<span id="cb24-7"><a href="#cb24-7" aria-hidden="true" tabindex="-1"></a> settings_name <span class="op">=</span> <span class="ss">f"chunk:</span><span class="sc">{</span>chunk_size<span class="sc">}</span><span class="ss">_embeddings:</span><span class="sc">{</span>embeddings<span class="sc">.</span>replace(<span class="st">'/'</span>, <span class="st">'~'</span>)<span class="sc">}</span><span class="ss">_rerank:</span><span class="sc">{</span>rerank<span class="sc">}</span><span class="ss">_reader-model:</span><span class="sc">{</span>READER_MODEL_NAME<span class="sc">}</span><span class="ss">"</span></span>
<span id="cb24-8"><a href="#cb24-8" aria-hidden="true" tabindex="-1"></a> output_file_name <span class="op">=</span> <span class="ss">f"./output/rag_</span><span class="sc">{</span>settings_name<span class="sc">}</span><span class="ss">.json"</span></span>
<span id="cb24-9"><a href="#cb24-9" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb24-10"><a href="#cb24-10" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="ss">f"Running evaluation for </span><span class="sc">{</span>settings_name<span class="sc">}</span><span class="ss">:"</span>)</span>
<span id="cb24-11"><a href="#cb24-11" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb24-12"><a href="#cb24-12" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="st">"Loading knowledge base embeddings..."</span>)</span>
<span id="cb24-13"><a href="#cb24-13" aria-hidden="true" tabindex="-1"></a> knowledge_index <span class="op">=</span> load_embeddings(</span>
<span id="cb24-14"><a href="#cb24-14" aria-hidden="true" tabindex="-1"></a> RAW_KNOWLEDGE_BASE,</span>
<span id="cb24-15"><a href="#cb24-15" aria-hidden="true" tabindex="-1"></a> chunk_size<span class="op">=</span>chunk_size,</span>
<span id="cb24-16"><a href="#cb24-16" aria-hidden="true" tabindex="-1"></a> embedding_model_name<span class="op">=</span>embeddings,</span>
<span id="cb24-17"><a href="#cb24-17" aria-hidden="true" tabindex="-1"></a> )</span>
<span id="cb24-18"><a href="#cb24-18" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb24-19"><a href="#cb24-19" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="st">"Running RAG..."</span>)</span>
<span id="cb24-20"><a href="#cb24-20" aria-hidden="true" tabindex="-1"></a> reranker <span class="op">=</span> (</span>
<span id="cb24-21"><a href="#cb24-21" aria-hidden="true" tabindex="-1"></a> RAGPretrainedModel.from_pretrained(<span class="st">"colbert-ir/colbertv2.0"</span>) <span class="cf">if</span> rerank <span class="cf">else</span> <span class="va">None</span></span>
<span id="cb24-22"><a href="#cb24-22" aria-hidden="true" tabindex="-1"></a> )</span>
<span id="cb24-23"><a href="#cb24-23" aria-hidden="true" tabindex="-1"></a> run_rag_tests(</span>
<span id="cb24-24"><a href="#cb24-24" aria-hidden="true" tabindex="-1"></a> eval_dataset<span class="op">=</span>eval_dataset,</span>
<span id="cb24-25"><a href="#cb24-25" aria-hidden="true" tabindex="-1"></a> llm<span class="op">=</span>READER_LLM,</span>
<span id="cb24-26"><a href="#cb24-26" aria-hidden="true" tabindex="-1"></a> knowledge_index<span class="op">=</span>knowledge_index,</span>
<span id="cb24-27"><a href="#cb24-27" aria-hidden="true" tabindex="-1"></a> output_file<span class="op">=</span>output_file_name,</span>
<span id="cb24-28"><a href="#cb24-28" aria-hidden="true" tabindex="-1"></a> reranker<span class="op">=</span>reranker,</span>
<span id="cb24-29"><a href="#cb24-29" aria-hidden="true" tabindex="-1"></a> verbose<span class="op">=</span><span class="va">False</span>,</span>
<span id="cb24-30"><a href="#cb24-30" aria-hidden="true" tabindex="-1"></a> test_settings<span class="op">=</span>settings_name,</span>
<span id="cb24-31"><a href="#cb24-31" aria-hidden="true" tabindex="-1"></a> )</span>
<span id="cb24-32"><a href="#cb24-32" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb24-33"><a href="#cb24-33" aria-hidden="true" tabindex="-1"></a> <span class="bu">print</span>(<span class="st">"Running evaluation..."</span>)</span>
<span id="cb24-34"><a href="#cb24-34" aria-hidden="true" tabindex="-1"></a> evaluate_answers(</span>
<span id="cb24-35"><a href="#cb24-35" aria-hidden="true" tabindex="-1"></a> output_file_name,</span>
<span id="cb24-36"><a href="#cb24-36" aria-hidden="true" tabindex="-1"></a> eval_chat_model,</span>
<span id="cb24-37"><a href="#cb24-37" aria-hidden="true" tabindex="-1"></a> evaluator_name,</span>
<span id="cb24-38"><a href="#cb24-38" aria-hidden="true" tabindex="-1"></a> evaluation_prompt_template,</span>
<span id="cb24-39"><a href="#cb24-39" aria-hidden="true" tabindex="-1"></a> )</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<section id="inspect-results" class="level3">
<h3 class="anchored" data-anchor-id="inspect-results">Inspect results</h3>
<div id="9fbbe7e3" class="cell" data-execution_count="25">
<div class="sourceCode cell-code" id="cb25"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb25-1"><a href="#cb25-1" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> glob</span>
<span id="cb25-2"><a href="#cb25-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb25-3"><a href="#cb25-3" aria-hidden="true" tabindex="-1"></a>outputs <span class="op">=</span> []</span>
<span id="cb25-4"><a href="#cb25-4" aria-hidden="true" tabindex="-1"></a><span class="cf">for</span> <span class="bu">file</span> <span class="kw">in</span> glob.glob(<span class="st">"./output/*.json"</span>):</span>
<span id="cb25-5"><a href="#cb25-5" aria-hidden="true" tabindex="-1"></a> output <span class="op">=</span> pd.DataFrame(json.load(<span class="bu">open</span>(<span class="bu">file</span>, <span class="st">"r"</span>)))</span>
<span id="cb25-6"><a href="#cb25-6" aria-hidden="true" tabindex="-1"></a> output[<span class="st">"settings"</span>] <span class="op">=</span> <span class="bu">file</span></span>
<span id="cb25-7"><a href="#cb25-7" aria-hidden="true" tabindex="-1"></a> outputs.append(output)</span>
<span id="cb25-8"><a href="#cb25-8" aria-hidden="true" tabindex="-1"></a>result <span class="op">=</span> pd.concat(outputs)</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div id="8e32ac07" class="cell" data-execution_count="26">
<div class="sourceCode cell-code" id="cb26"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb26-1"><a href="#cb26-1" aria-hidden="true" tabindex="-1"></a>result[<span class="st">"eval_score_GPT4"</span>] <span class="op">=</span> result[<span class="st">"eval_score_GPT4"</span>].<span class="bu">apply</span>(</span>
<span id="cb26-2"><a href="#cb26-2" aria-hidden="true" tabindex="-1"></a> <span class="kw">lambda</span> x: <span class="bu">int</span>(x) <span class="cf">if</span> <span class="bu">isinstance</span>(x, <span class="bu">str</span>) <span class="cf">else</span> <span class="dv">1</span></span>
<span id="cb26-3"><a href="#cb26-3" aria-hidden="true" tabindex="-1"></a>)</span>
<span id="cb26-4"><a href="#cb26-4" aria-hidden="true" tabindex="-1"></a>result[<span class="st">"eval_score_GPT4"</span>] <span class="op">=</span> (result[<span class="st">"eval_score_GPT4"</span>] <span class="op">-</span> <span class="dv">1</span>) <span class="op">/</span> <span class="dv">4</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div id="14c33cb4" class="cell" data-execution_count="27">
<div class="sourceCode cell-code" id="cb27"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb27-1"><a href="#cb27-1" aria-hidden="true" tabindex="-1"></a>average_scores <span class="op">=</span> result.groupby(<span class="st">"settings"</span>)[<span class="st">"eval_score_GPT4"</span>].mean()</span>
<span id="cb27-2"><a href="#cb27-2" aria-hidden="true" tabindex="-1"></a>average_scores.sort_values()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
</section>
<section id="example-results" class="level2">
<h2 class="anchored" data-anchor-id="example-results">Example results</h2>
<p>Let us load the results that I obtained by tweaking the different options available in this notebook. For more detail on why these options could work on not, see the notebook on <a href="advanced_rag">advanced_RAG</a>.</p>
<p>As you can see in the graph below, some tweaks do not bring any improvement, some give huge performance boosts.</p>
<p>➡️ <strong><em>There is no single good recipe: you should try several different directions when tuning your RAG systems.</em></strong></p>
<div id="0f27b105" class="cell" data-execution_count="28">
<div class="sourceCode cell-code" id="cb28"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb28-1"><a href="#cb28-1" aria-hidden="true" tabindex="-1"></a><span class="im">import</span> plotly.express <span class="im">as</span> px</span>
<span id="cb28-2"><a href="#cb28-2" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb28-3"><a href="#cb28-3" aria-hidden="true" tabindex="-1"></a>scores <span class="op">=</span> datasets.load_dataset(<span class="st">"m-ric/rag_scores_cookbook"</span>, split<span class="op">=</span><span class="st">"train"</span>)</span>
<span id="cb28-4"><a href="#cb28-4" aria-hidden="true" tabindex="-1"></a>scores <span class="op">=</span> pd.Series(scores[<span class="st">"score"</span>], index<span class="op">=</span>scores[<span class="st">"settings"</span>])</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<div id="abdb166c" class="cell" data-execution_count="29">
<div class="sourceCode cell-code" id="cb29"><pre class="sourceCode python code-with-copy"><code class="sourceCode python"><span id="cb29-1"><a href="#cb29-1" aria-hidden="true" tabindex="-1"></a>fig <span class="op">=</span> px.bar(</span>
<span id="cb29-2"><a href="#cb29-2" aria-hidden="true" tabindex="-1"></a> scores,</span>
<span id="cb29-3"><a href="#cb29-3" aria-hidden="true" tabindex="-1"></a> color<span class="op">=</span>scores,</span>
<span id="cb29-4"><a href="#cb29-4" aria-hidden="true" tabindex="-1"></a> labels<span class="op">=</span>{</span>
<span id="cb29-5"><a href="#cb29-5" aria-hidden="true" tabindex="-1"></a> <span class="st">"value"</span>: <span class="st">"Accuracy"</span>,</span>
<span id="cb29-6"><a href="#cb29-6" aria-hidden="true" tabindex="-1"></a> <span class="st">"settings"</span>: <span class="st">"Configuration"</span>,</span>
<span id="cb29-7"><a href="#cb29-7" aria-hidden="true" tabindex="-1"></a> },</span>
<span id="cb29-8"><a href="#cb29-8" aria-hidden="true" tabindex="-1"></a> color_continuous_scale<span class="op">=</span><span class="st">"bluered"</span>,</span>
<span id="cb29-9"><a href="#cb29-9" aria-hidden="true" tabindex="-1"></a>)</span>
<span id="cb29-10"><a href="#cb29-10" aria-hidden="true" tabindex="-1"></a>fig.update_layout(w</span>
<span id="cb29-11"><a href="#cb29-11" aria-hidden="true" tabindex="-1"></a> width<span class="op">=</span><span class="dv">1000</span>,</span>
<span id="cb29-12"><a href="#cb29-12" aria-hidden="true" tabindex="-1"></a> height<span class="op">=</span><span class="dv">600</span>,</span>
<span id="cb29-13"><a href="#cb29-13" aria-hidden="true" tabindex="-1"></a> barmode<span class="op">=</span><span class="st">"group"</span>,</span>
<span id="cb29-14"><a href="#cb29-14" aria-hidden="true" tabindex="-1"></a> yaxis_range<span class="op">=</span>[<span class="dv">0</span>, <span class="dv">100</span>],</span>
<span id="cb29-15"><a href="#cb29-15" aria-hidden="true" tabindex="-1"></a> title<span class="op">=</span><span class="st">"<b>Accuracy of different RAG configurations</b>"</span>,</span>
<span id="cb29-16"><a href="#cb29-16" aria-hidden="true" tabindex="-1"></a> xaxis_title<span class="op">=</span><span class="st">"RAG settings"</span>,</span>
<span id="cb29-17"><a href="#cb29-17" aria-hidden="true" tabindex="-1"></a> font<span class="op">=</span><span class="bu">dict</span>(size<span class="op">=</span><span class="dv">15</span>),</span>
<span id="cb29-18"><a href="#cb29-18" aria-hidden="true" tabindex="-1"></a>)</span>
<span id="cb29-19"><a href="#cb29-19" aria-hidden="true" tabindex="-1"></a>fig.layout.yaxis.ticksuffix <span class="op">=</span> <span class="st">"%"</span></span>
<span id="cb29-20"><a href="#cb29-20" aria-hidden="true" tabindex="-1"></a>fig.update_coloraxes(showscale<span class="op">=</span><span class="va">False</span>)</span>
<span id="cb29-21"><a href="#cb29-21" aria-hidden="true" tabindex="-1"></a>fig.update_traces(texttemplate<span class="op">=</span><span class="st">"%</span><span class="sc">{y:.1f}</span><span class="st">"</span>, textposition<span class="op">=</span><span class="st">"outside"</span>)</span>
<span id="cb29-22"><a href="#cb29-22" aria-hidden="true" tabindex="-1"></a>fig.show()</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
</div>
<p><img src="https://huggingface.co/datasets/huggingface/cookbook-images/resolve/main/RAG_settings_accuracy.png" height="500" width="800"></p>
<p>As you can see, these had varying impact on performance. In particular, tuning the chunk size is both easy and very impactful.</p>
<p>But this is our case: your results could be very different: now that you have a robust evaluation pipeline, you can set on to explore other options! 🗺️</p>
</section>
</section>
</main> <!-- /main -->
<script id="quarto-html-after-body" type="application/javascript">
window.document.addEventListener("DOMContentLoaded", function (event) {
const toggleBodyColorMode = (bsSheetEl) => {
const mode = bsSheetEl.getAttribute("data-mode");
const bodyEl = window.document.querySelector("body");
if (mode === "dark") {
bodyEl.classList.add("quarto-dark");
bodyEl.classList.remove("quarto-light");
} else {
bodyEl.classList.add("quarto-light");
bodyEl.classList.remove("quarto-dark");
}
}
const toggleBodyColorPrimary = () => {
const bsSheetEl = window.document.querySelector("link#quarto-bootstrap");
if (bsSheetEl) {
toggleBodyColorMode(bsSheetEl);
}
}
toggleBodyColorPrimary();
const icon = "";
const anchorJS = new window.AnchorJS();
anchorJS.options = {
placement: 'right',
icon: icon
};
anchorJS.add('.anchored');
const isCodeAnnotation = (el) => {
for (const clz of el.classList) {
if (clz.startsWith('code-annotation-')) {
return true;
}
}
return false;
}
const onCopySuccess = function(e) {
// button target
const button = e.trigger;
// don't keep focus
button.blur();
// flash "checked"
button.classList.add('code-copy-button-checked');
var currentTitle = button.getAttribute("title");
button.setAttribute("title", "Copied!");
let tooltip;
if (window.bootstrap) {
button.setAttribute("data-bs-toggle", "tooltip");
button.setAttribute("data-bs-placement", "left");
button.setAttribute("data-bs-title", "Copied!");
tooltip = new bootstrap.Tooltip(button,
{ trigger: "manual",
customClass: "code-copy-button-tooltip",
offset: [0, -8]});
tooltip.show();
}
setTimeout(function() {
if (tooltip) {
tooltip.hide();
button.removeAttribute("data-bs-title");
button.removeAttribute("data-bs-toggle");
button.removeAttribute("data-bs-placement");
}
button.setAttribute("title", currentTitle);
button.classList.remove('code-copy-button-checked');
}, 1000);
// clear code selection
e.clearSelection();
}
const getTextToCopy = function(trigger) {
const codeEl = trigger.previousElementSibling.cloneNode(true);
for (const childEl of codeEl.children) {
if (isCodeAnnotation(childEl)) {
childEl.remove();
}
}
return codeEl.innerText;
}
const clipboard = new window.ClipboardJS('.code-copy-button:not([data-in-quarto-modal])', {
text: getTextToCopy
});
clipboard.on('success', onCopySuccess);
if (window.document.getElementById('quarto-embedded-source-code-modal')) {
const clipboardModal = new window.ClipboardJS('.code-copy-button[data-in-quarto-modal]', {
text: getTextToCopy,
container: window.document.getElementById('quarto-embedded-source-code-modal')
});
clipboardModal.on('success', onCopySuccess);
}
var localhostRegex = new RegExp(/^(?:http|https):\/\/localhost\:?[0-9]*\//);
var mailtoRegex = new RegExp(/^mailto:/);
var filterRegex = new RegExp('/' + window.location.host + '/');
var isInternal = (href) => {
return filterRegex.test(href) || localhostRegex.test(href) || mailtoRegex.test(href);
}
// Inspect non-navigation links and adorn them if external
var links = window.document.querySelectorAll('a[href]:not(.nav-link):not(.navbar-brand):not(.toc-action):not(.sidebar-link):not(.sidebar-item-toggle):not(.pagination-link):not(.no-external):not([aria-hidden]):not(.dropdown-item):not(.quarto-navigation-tool):not(.about-link)');
for (var i=0; i<links.length; i++) {
const link = links[i];
if (!isInternal(link.href)) {
// undo the damage that might have been done by quarto-nav.js in the case of
// links that we want to consider external
if (link.dataset.originalHref !== undefined) {
link.href = link.dataset.originalHref;
}
}
}
function tippyHover(el, contentFn, onTriggerFn, onUntriggerFn) {
const config = {
allowHTML: true,
maxWidth: 500,
delay: 100,
arrow: false,
appendTo: function(el) {
return el.parentElement;
},
interactive: true,
interactiveBorder: 10,
theme: 'quarto',
placement: 'bottom-start',
};
if (contentFn) {
config.content = contentFn;
}
if (onTriggerFn) {
config.onTrigger = onTriggerFn;
}
if (onUntriggerFn) {
config.onUntrigger = onUntriggerFn;
}
window.tippy(el, config);
}
const noterefs = window.document.querySelectorAll('a[role="doc-noteref"]');
for (var i=0; i<noterefs.length; i++) {
const ref = noterefs[i];
tippyHover(ref, function() {
// use id or data attribute instead here
let href = ref.getAttribute('data-footnote-href') || ref.getAttribute('href');
try { href = new URL(href).hash; } catch {}
const id = href.replace(/^#\/?/, "");
const note = window.document.getElementById(id);
if (note) {
return note.innerHTML;
} else {
return "";
}
});
}
const xrefs = window.document.querySelectorAll('a.quarto-xref');
const processXRef = (id, note) => {
// Strip column container classes
const stripColumnClz = (el) => {
el.classList.remove("page-full", "page-columns");
if (el.children) {
for (const child of el.children) {
stripColumnClz(child);
}
}
}
stripColumnClz(note)
if (id === null || id.startsWith('sec-')) {
// Special case sections, only their first couple elements
const container = document.createElement("div");
if (note.children && note.children.length > 2) {
container.appendChild(note.children[0].cloneNode(true));
for (let i = 1; i < note.children.length; i++) {
const child = note.children[i];
if (child.tagName === "P" && child.innerText === "") {
continue;
} else {
container.appendChild(child.cloneNode(true));
break;
}
}
if (window.Quarto?.typesetMath) {
window.Quarto.typesetMath(container);
}
return container.innerHTML
} else {
if (window.Quarto?.typesetMath) {
window.Quarto.typesetMath(note);
}
return note.innerHTML;
}
} else {
// Remove any anchor links if they are present
const anchorLink = note.querySelector('a.anchorjs-link');
if (anchorLink) {
anchorLink.remove();
}
if (window.Quarto?.typesetMath) {
window.Quarto.typesetMath(note);
}
if (note.classList.contains("callout")) {
return note.outerHTML;
} else {
return note.innerHTML;
}
}
}
for (var i=0; i<xrefs.length; i++) {
const xref = xrefs[i];
tippyHover(xref, undefined, function(instance) {
instance.disable();
let url = xref.getAttribute('href');
let hash = undefined;
if (url.startsWith('#')) {
hash = url;
} else {
try { hash = new URL(url).hash; } catch {}
}
if (hash) {
const id = hash.replace(/^#\/?/, "");
const note = window.document.getElementById(id);
if (note !== null) {
try {
const html = processXRef(id, note.cloneNode(true));
instance.setContent(html);
} finally {
instance.enable();
instance.show();
}
} else {
// See if we can fetch this
fetch(url.split('#')[0])
.then(res => res.text())
.then(html => {
const parser = new DOMParser();
const htmlDoc = parser.parseFromString(html, "text/html");
const note = htmlDoc.getElementById(id);
if (note !== null) {
const html = processXRef(id, note);
instance.setContent(html);
}
}).finally(() => {
instance.enable();
instance.show();
});
}
} else {
// See if we can fetch a full url (with no hash to target)
// This is a special case and we should probably do some content thinning / targeting
fetch(url)
.then(res => res.text())
.then(html => {
const parser = new DOMParser();
const htmlDoc = parser.parseFromString(html, "text/html");
const note = htmlDoc.querySelector('main.content');
if (note !== null) {
// This should only happen for chapter cross references
// (since there is no id in the URL)
// remove the first header
if (note.children.length > 0 && note.children[0].tagName === "HEADER") {
note.children[0].remove();
}
const html = processXRef(null, note);
instance.setContent(html);
}
}).finally(() => {
instance.enable();
instance.show();
});
}
}, function(instance) {
});
}
let selectedAnnoteEl;
const selectorForAnnotation = ( cell, annotation) => {
let cellAttr = 'data-code-cell="' + cell + '"';
let lineAttr = 'data-code-annotation="' + annotation + '"';
const selector = 'span[' + cellAttr + '][' + lineAttr + ']';
return selector;
}
const selectCodeLines = (annoteEl) => {
const doc = window.document;
const targetCell = annoteEl.getAttribute("data-target-cell");
const targetAnnotation = annoteEl.getAttribute("data-target-annotation");
const annoteSpan = window.document.querySelector(selectorForAnnotation(targetCell, targetAnnotation));
const lines = annoteSpan.getAttribute("data-code-lines").split(",");
const lineIds = lines.map((line) => {
return targetCell + "-" + line;
})
let top = null;
let height = null;
let parent = null;
if (lineIds.length > 0) {
//compute the position of the single el (top and bottom and make a div)
const el = window.document.getElementById(lineIds[0]);
top = el.offsetTop;
height = el.offsetHeight;
parent = el.parentElement.parentElement;
if (lineIds.length > 1) {
const lastEl = window.document.getElementById(lineIds[lineIds.length - 1]);
const bottom = lastEl.offsetTop + lastEl.offsetHeight;
height = bottom - top;
}
if (top !== null && height !== null && parent !== null) {
// cook up a div (if necessary) and position it
let div = window.document.getElementById("code-annotation-line-highlight");
if (div === null) {
div = window.document.createElement("div");
div.setAttribute("id", "code-annotation-line-highlight");
div.style.position = 'absolute';
parent.appendChild(div);
}
div.style.top = top - 2 + "px";
div.style.height = height + 4 + "px";
div.style.left = 0;
let gutterDiv = window.document.getElementById("code-annotation-line-highlight-gutter");
if (gutterDiv === null) {
gutterDiv = window.document.createElement("div");
gutterDiv.setAttribute("id", "code-annotation-line-highlight-gutter");
gutterDiv.style.position = 'absolute';
const codeCell = window.document.getElementById(targetCell);
const gutter = codeCell.querySelector('.code-annotation-gutter');
gutter.appendChild(gutterDiv);
}
gutterDiv.style.top = top - 2 + "px";
gutterDiv.style.height = height + 4 + "px";
}
selectedAnnoteEl = annoteEl;
}
};
const unselectCodeLines = () => {
const elementsIds = ["code-annotation-line-highlight", "code-annotation-line-highlight-gutter"];
elementsIds.forEach((elId) => {
const div = window.document.getElementById(elId);
if (div) {
div.remove();
}
});
selectedAnnoteEl = undefined;
};
// Handle positioning of the toggle
window.addEventListener(
"resize",
throttle(() => {
elRect = undefined;
if (selectedAnnoteEl) {
selectCodeLines(selectedAnnoteEl);
}
}, 10)
);
function throttle(fn, ms) {
let throttle = false;
let timer;
return (...args) => {
if(!throttle) { // first call gets through
fn.apply(this, args);
throttle = true;
} else { // all the others get throttled
if(timer) clearTimeout(timer); // cancel #2
timer = setTimeout(() => {
fn.apply(this, args);
timer = throttle = false;
}, ms);
}
};
}
// Attach click handler to the DT
const annoteDls = window.document.querySelectorAll('dt[data-target-cell]');
for (const annoteDlNode of annoteDls) {
annoteDlNode.addEventListener('click', (event) => {
const clickedEl = event.target;
if (clickedEl !== selectedAnnoteEl) {
unselectCodeLines();
const activeEl = window.document.querySelector('dt[data-target-cell].code-annotation-active');
if (activeEl) {
activeEl.classList.remove('code-annotation-active');
}
selectCodeLines(clickedEl);
clickedEl.classList.add('code-annotation-active');
} else {
// Unselect the line
unselectCodeLines();
clickedEl.classList.remove('code-annotation-active');
}
});
}
const findCites = (el) => {
const parentEl = el.parentElement;
if (parentEl) {
const cites = parentEl.dataset.cites;
if (cites) {
return {
el,
cites: cites.split(' ')
};
} else {
return findCites(el.parentElement)
}
} else {
return undefined;
}
};
var bibliorefs = window.document.querySelectorAll('a[role="doc-biblioref"]');
for (var i=0; i<bibliorefs.length; i++) {
const ref = bibliorefs[i];
const citeInfo = findCites(ref);
if (citeInfo) {
tippyHover(citeInfo.el, function() {
var popup = window.document.createElement('div');
citeInfo.cites.forEach(function(cite) {
var citeDiv = window.document.createElement('div');
citeDiv.classList.add('hanging-indent');
citeDiv.classList.add('csl-entry');
var biblioDiv = window.document.getElementById('ref-' + cite);
if (biblioDiv) {
citeDiv.innerHTML = biblioDiv.innerHTML;
}
popup.appendChild(citeDiv);
});
return popup.innerHTML;
});
}
}
});
</script>
</div> <!-- /content -->
</body></html> |