File size: 67,330 Bytes
a392ebe 5a9500d a392ebe 5a9500d a392ebe 5a9500d a392ebe |
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 |
{
"cells": [
{
"cell_type": "markdown",
"id": "vKn48gXttML_",
"metadata": {
"id": "vKn48gXttML_"
},
"source": [
"## **Use ensemble for LLM model**"
]
},
{
"cell_type": "markdown",
"id": "252c5160-b5be-4f0e-b072-bf76af1885c3",
"metadata": {
"id": "252c5160-b5be-4f0e-b072-bf76af1885c3"
},
"source": [
"## To load the index and run query"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "2drQV0WqPolq",
"metadata": {
"id": "2drQV0WqPolq"
},
"outputs": [],
"source": [
"# !pip install -q huggingface_hub\n",
"# !pip install -q llama-index\n",
"# !pip install -q transformers\n",
"# !pip install -q torch\n",
"# !pip install -q gradio\n",
"# !pip install -q llama-index-llms-huggingface\n",
"# !pip install -q llama-index-llms-huggingface-api\n",
"# !pip install -q llama-index-embeddings-huggingface\n",
"# !pip install -q llama-index-llms-groq\n",
"# !pip install -q llama-index-llms-gemini"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "BjM4cigtuIrv",
"metadata": {
"id": "BjM4cigtuIrv"
},
"outputs": [
{
"ename": "ModuleNotFoundError",
"evalue": "No module named 'google.colab'",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[2], line 1\u001b[0m\n\u001b[1;32m----> 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mgoogle\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcolab\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m drive\n\u001b[0;32m 2\u001b[0m drive\u001b[38;5;241m.\u001b[39mmount(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m/content/drive\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
"\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'google.colab'"
]
}
],
"source": [
"from google.colab import drive\n",
"drive.mount('/content/drive')"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "63f9de39-5393-463c-954d-5f1b7760db6f",
"metadata": {
"id": "63f9de39-5393-463c-954d-5f1b7760db6f"
},
"outputs": [
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[12], line 31\u001b[0m\n\u001b[0;32m 22\u001b[0m Settings\u001b[38;5;241m.\u001b[39membed_model \u001b[38;5;241m=\u001b[39m embed_model\n\u001b[0;32m 24\u001b[0m \u001b[38;5;66;03m#load indexs store in presist_dir\u001b[39;00m\n\u001b[0;32m 25\u001b[0m \n\u001b[0;32m 26\u001b[0m \u001b[38;5;66;03m## Note: Use folder in the google drive which having indexes (do not use folder having .txt file).\u001b[39;00m\n\u001b[0;32m 27\u001b[0m \u001b[38;5;66;03m## Indexed are build and kept in sum_key_vector_index_ensemble folder on gDrive.\u001b[39;00m\n\u001b[0;32m 28\u001b[0m \u001b[38;5;66;03m## Location - https://drive.google.com/drive/folders/14ASzYUxIPeUCtsxFY9Jwzb1FKXY08lA5?usp=share_link\u001b[39;00m\n\u001b[0;32m 29\u001b[0m \u001b[38;5;66;03m## If required, you can built it again. Please let us know to do it.\u001b[39;00m\n\u001b[1;32m---> 31\u001b[0m storage_context \u001b[38;5;241m=\u001b[39m \u001b[43mStorageContext\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_defaults\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpersist_dir\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;124;43mr\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mC:\u001b[39;49m\u001b[38;5;124;43m\\\u001b[39;49m\u001b[38;5;124;43mUsers\u001b[39;49m\u001b[38;5;124;43m\\\u001b[39;49m\u001b[38;5;124;43magshi\u001b[39;49m\u001b[38;5;124;43m\\\u001b[39;49m\u001b[38;5;124;43mDownloads\u001b[39;49m\u001b[38;5;124;43m\\\u001b[39;49m\u001b[38;5;124;43msum_key_vector_index_ensemble-20240909T154445Z-001-20240911T083314Z-001\u001b[39;49m\u001b[38;5;124;43m\\\u001b[39;49m\u001b[38;5;124;43msum_key_vector_index_ensemble-20240909T154445Z-001\u001b[39;49m\u001b[38;5;124;43m\\\u001b[39;49m\u001b[38;5;124;43msum_key_vector_index_ensemble\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[0;32m 32\u001b[0m vector_index \u001b[38;5;241m=\u001b[39m load_index_from_storage(storage_context, index_id \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m9ff973d9-c21b-4710-a8e6-dfe399aa2cd5\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 33\u001b[0m keyword_index \u001b[38;5;241m=\u001b[39m load_index_from_storage(storage_context, index_id \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m34a4783e-7bbe-4eb9-acc6-0227b9173688\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\llama_index\\core\\storage\\storage_context.py:134\u001b[0m, in \u001b[0;36mStorageContext.from_defaults\u001b[1;34m(cls, docstore, index_store, vector_store, image_store, vector_stores, graph_store, property_graph_store, persist_dir, fs)\u001b[0m\n\u001b[0;32m 132\u001b[0m vector_stores \u001b[38;5;241m=\u001b[39m vector_stores\n\u001b[0;32m 133\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 134\u001b[0m vector_stores \u001b[38;5;241m=\u001b[39m \u001b[43mSimpleVectorStore\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_namespaced_persist_dir\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 135\u001b[0m \u001b[43m \u001b[49m\u001b[43mpersist_dir\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfs\u001b[49m\n\u001b[0;32m 136\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 137\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m image_store:\n\u001b[0;32m 138\u001b[0m \u001b[38;5;66;03m# append image store to vector stores\u001b[39;00m\n\u001b[0;32m 139\u001b[0m vector_stores[IMAGE_VECTOR_STORE_NAMESPACE] \u001b[38;5;241m=\u001b[39m image_store \u001b[38;5;66;03m# type: ignore\u001b[39;00m\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\llama_index\\core\\vector_stores\\simple.py:203\u001b[0m, in \u001b[0;36mSimpleVectorStore.from_namespaced_persist_dir\u001b[1;34m(cls, persist_dir, fs)\u001b[0m\n\u001b[0;32m 199\u001b[0m vector_stores[DEFAULT_VECTOR_STORE] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39mfrom_persist_dir(\n\u001b[0;32m 200\u001b[0m persist_dir\u001b[38;5;241m=\u001b[39mpersist_dir, fs\u001b[38;5;241m=\u001b[39mfs\n\u001b[0;32m 201\u001b[0m )\n\u001b[0;32m 202\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 203\u001b[0m vector_stores[namespace] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_persist_dir\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 204\u001b[0m \u001b[43m \u001b[49m\u001b[43mpersist_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpersist_dir\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnamespace\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnamespace\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfs\u001b[49m\n\u001b[0;32m 205\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 206\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n\u001b[0;32m 207\u001b[0m \u001b[38;5;66;03m# failed to listdir, so assume there is only one store\u001b[39;00m\n\u001b[0;32m 208\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\llama_index\\core\\vector_stores\\simple.py:179\u001b[0m, in \u001b[0;36mSimpleVectorStore.from_persist_dir\u001b[1;34m(cls, persist_dir, namespace, fs)\u001b[0m\n\u001b[0;32m 177\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 178\u001b[0m persist_path \u001b[38;5;241m=\u001b[39m os\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mjoin(persist_dir, persist_fname)\n\u001b[1;32m--> 179\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_persist_path\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpersist_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfs\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\llama_index\\core\\vector_stores\\simple.py:415\u001b[0m, in \u001b[0;36mSimpleVectorStore.from_persist_path\u001b[1;34m(cls, persist_path, fs)\u001b[0m\n\u001b[0;32m 413\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m fs\u001b[38;5;241m.\u001b[39mopen(persist_path, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrb\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mas\u001b[39;00m f:\n\u001b[0;32m 414\u001b[0m data_dict \u001b[38;5;241m=\u001b[39m json\u001b[38;5;241m.\u001b[39mload(f)\n\u001b[1;32m--> 415\u001b[0m data \u001b[38;5;241m=\u001b[39m \u001b[43mSimpleVectorStoreData\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_dict\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata_dict\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 416\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mcls\u001b[39m(data)\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\dataclasses_json\\api.py:70\u001b[0m, in \u001b[0;36mDataClassJsonMixin.from_dict\u001b[1;34m(cls, kvs, infer_missing)\u001b[0m\n\u001b[0;32m 65\u001b[0m \u001b[38;5;129m@classmethod\u001b[39m\n\u001b[0;32m 66\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mfrom_dict\u001b[39m(\u001b[38;5;28mcls\u001b[39m: Type[A],\n\u001b[0;32m 67\u001b[0m kvs: Json,\n\u001b[0;32m 68\u001b[0m \u001b[38;5;241m*\u001b[39m,\n\u001b[0;32m 69\u001b[0m infer_missing\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m A:\n\u001b[1;32m---> 70\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_decode_dataclass\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mcls\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkvs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minfer_missing\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\dataclasses_json\\core.py:233\u001b[0m, in \u001b[0;36m_decode_dataclass\u001b[1;34m(cls, kvs, infer_missing)\u001b[0m\n\u001b[0;32m 231\u001b[0m init_kwargs[field\u001b[38;5;241m.\u001b[39mname] \u001b[38;5;241m=\u001b[39m value\n\u001b[0;32m 232\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m _is_supported_generic(field_type) \u001b[38;5;129;01mand\u001b[39;00m field_type \u001b[38;5;241m!=\u001b[39m \u001b[38;5;28mstr\u001b[39m:\n\u001b[1;32m--> 233\u001b[0m init_kwargs[field\u001b[38;5;241m.\u001b[39mname] \u001b[38;5;241m=\u001b[39m \u001b[43m_decode_generic\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfield_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 234\u001b[0m \u001b[43m \u001b[49m\u001b[43mfield_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 235\u001b[0m \u001b[43m \u001b[49m\u001b[43minfer_missing\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 236\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 237\u001b[0m init_kwargs[field\u001b[38;5;241m.\u001b[39mname] \u001b[38;5;241m=\u001b[39m _support_extended_types(field_type,\n\u001b[0;32m 238\u001b[0m field_value)\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\dataclasses_json\\core.py:304\u001b[0m, in \u001b[0;36m_decode_generic\u001b[1;34m(type_, value, infer_missing)\u001b[0m\n\u001b[0;32m 301\u001b[0m \u001b[38;5;66;03m# a mapping type has `.keys()` and `.values()`\u001b[39;00m\n\u001b[0;32m 302\u001b[0m \u001b[38;5;66;03m# (see collections.abc)\u001b[39;00m\n\u001b[0;32m 303\u001b[0m ks \u001b[38;5;241m=\u001b[39m _decode_dict_keys(k_type, value\u001b[38;5;241m.\u001b[39mkeys(), infer_missing)\n\u001b[1;32m--> 304\u001b[0m vs \u001b[38;5;241m=\u001b[39m \u001b[43m_decode_items\u001b[49m\u001b[43m(\u001b[49m\u001b[43mv_type\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalue\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mvalues\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minfer_missing\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 305\u001b[0m xs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mzip\u001b[39m(ks, vs)\n\u001b[0;32m 306\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m _is_tuple(type_):\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\dataclasses_json\\core.py:410\u001b[0m, in \u001b[0;36m_decode_items\u001b[1;34m(type_args, xs, infer_missing)\u001b[0m\n\u001b[0;32m 405\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 406\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNumber of types specified in the collection type \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mstr\u001b[39m(type_args)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 407\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdoes not match number of elements in the collection. In case you are working with tuples\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 408\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtake a look at this document \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 409\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdocs.python.org/3/library/typing.html#annotating-tuples.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m--> 410\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mlist\u001b[39m(_decode_type(type_args, x, infer_missing) \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m xs)\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\dataclasses_json\\core.py:410\u001b[0m, in \u001b[0;36m<genexpr>\u001b[1;34m(.0)\u001b[0m\n\u001b[0;32m 405\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 406\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNumber of types specified in the collection type \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mstr\u001b[39m(type_args)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 407\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdoes not match number of elements in the collection. In case you are working with tuples\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 408\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtake a look at this document \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 409\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdocs.python.org/3/library/typing.html#annotating-tuples.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m--> 410\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mlist\u001b[39m(\u001b[43m_decode_type\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtype_args\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minfer_missing\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m xs)\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\dataclasses_json\\core.py:247\u001b[0m, in \u001b[0;36m_decode_type\u001b[1;34m(type_, value, infer_missing)\u001b[0m\n\u001b[0;32m 245\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _get_decoder_in_global_config(type_)(value)\n\u001b[0;32m 246\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m _is_supported_generic(type_):\n\u001b[1;32m--> 247\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_decode_generic\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtype_\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minfer_missing\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 248\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_dataclass(type_) \u001b[38;5;129;01mor\u001b[39;00m is_dataclass(value):\n\u001b[0;32m 249\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _decode_dataclass(type_, value, infer_missing)\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\dataclasses_json\\core.py:315\u001b[0m, in \u001b[0;36m_decode_generic\u001b[1;34m(type_, value, infer_missing)\u001b[0m\n\u001b[0;32m 313\u001b[0m xs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mdict\u001b[39m(\u001b[38;5;28mzip\u001b[39m(_decode_items(_get_type_arg_param(type_, \u001b[38;5;241m0\u001b[39m), value\u001b[38;5;241m.\u001b[39mkeys(), infer_missing), value\u001b[38;5;241m.\u001b[39mvalues()))\n\u001b[0;32m 314\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 315\u001b[0m xs \u001b[38;5;241m=\u001b[39m \u001b[43m_decode_items\u001b[49m\u001b[43m(\u001b[49m\u001b[43m_get_type_arg_param\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtype_\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minfer_missing\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 317\u001b[0m collection_type \u001b[38;5;241m=\u001b[39m _resolve_collection_type_to_decode_to(type_)\n\u001b[0;32m 318\u001b[0m res \u001b[38;5;241m=\u001b[39m collection_type(xs)\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\dataclasses_json\\core.py:410\u001b[0m, in \u001b[0;36m_decode_items\u001b[1;34m(type_args, xs, infer_missing)\u001b[0m\n\u001b[0;32m 405\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 406\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNumber of types specified in the collection type \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mstr\u001b[39m(type_args)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 407\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdoes not match number of elements in the collection. In case you are working with tuples\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 408\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtake a look at this document \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 409\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdocs.python.org/3/library/typing.html#annotating-tuples.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m--> 410\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mlist\u001b[39m(_decode_type(type_args, x, infer_missing) \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m xs)\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\dataclasses_json\\core.py:410\u001b[0m, in \u001b[0;36m<genexpr>\u001b[1;34m(.0)\u001b[0m\n\u001b[0;32m 405\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 406\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNumber of types specified in the collection type \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mstr\u001b[39m(type_args)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 407\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdoes not match number of elements in the collection. In case you are working with tuples\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 408\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtake a look at this document \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 409\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdocs.python.org/3/library/typing.html#annotating-tuples.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m--> 410\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mlist\u001b[39m(\u001b[43m_decode_type\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtype_args\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minfer_missing\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m xs)\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\dataclasses_json\\core.py:250\u001b[0m, in \u001b[0;36m_decode_type\u001b[1;34m(type_, value, infer_missing)\u001b[0m\n\u001b[0;32m 248\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_dataclass(type_) \u001b[38;5;129;01mor\u001b[39;00m is_dataclass(value):\n\u001b[0;32m 249\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _decode_dataclass(type_, value, infer_missing)\n\u001b[1;32m--> 250\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_support_extended_types\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtype_\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mvalue\u001b[49m\u001b[43m)\u001b[49m\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\dataclasses_json\\core.py:271\u001b[0m, in \u001b[0;36m_support_extended_types\u001b[1;34m(field_type, field_value)\u001b[0m\n\u001b[0;32m 267\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m _issubclass_safe(field_type, UUID):\n\u001b[0;32m 268\u001b[0m res \u001b[38;5;241m=\u001b[39m (field_value\n\u001b[0;32m 269\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(field_value, UUID)\n\u001b[0;32m 270\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m UUID(field_value))\n\u001b[1;32m--> 271\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[43m_issubclass_safe\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfield_type\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mint\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mfloat\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mstr\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mbool\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m:\n\u001b[0;32m 272\u001b[0m res \u001b[38;5;241m=\u001b[39m (field_value\n\u001b[0;32m 273\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(field_value, field_type)\n\u001b[0;32m 274\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m field_type(field_value))\n\u001b[0;32m 275\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\dataclasses_json\\utils.py:118\u001b[0m, in \u001b[0;36m_issubclass_safe\u001b[1;34m(cls, classinfo)\u001b[0m\n\u001b[0;32m 116\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_issubclass_safe\u001b[39m(\u001b[38;5;28mcls\u001b[39m, classinfo):\n\u001b[0;32m 117\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 118\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28missubclass\u001b[39m(\u001b[38;5;28mcls\u001b[39m, classinfo)\n\u001b[0;32m 119\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n\u001b[0;32m 120\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m (_is_new_type_subclass_safe(\u001b[38;5;28mcls\u001b[39m, classinfo)\n\u001b[0;32m 121\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m _is_new_type(\u001b[38;5;28mcls\u001b[39m)\n\u001b[0;32m 122\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mFalse\u001b[39;00m)\n",
"\u001b[1;31mKeyboardInterrupt\u001b[0m: "
]
},
{
"ename": "",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n",
"\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n",
"\u001b[1;31mClick <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. \n",
"\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
]
}
],
"source": [
"from llama_index.core import Settings\n",
"from llama_index.llms.groq import Groq\n",
"from llama_index.llms.huggingface import HuggingFaceLLM\n",
"from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI\n",
"from llama_index.embeddings.huggingface import HuggingFaceEmbedding\n",
"from llama_index.core import StorageContext\n",
"from llama_index.core import load_index_from_storage\n",
"from llama_index.core import SummaryIndex\n",
"from llama_index.core import PromptTemplate\n",
"from llama_index.core.tools import QueryEngineTool\n",
"import pandas as pd\n",
"import nest_asyncio\n",
"nest_asyncio.apply()\n",
"\n",
"# define LLM, Embed models\n",
"\n",
"## Note: Please replace API keys with your own API keys here.\n",
"\n",
"Settings.llm = Groq(model=\"llama-3.1-8b-instant\", api_key=\"your key\")\n",
"Settings.chunk_size = 1024\n",
"embed_model = HuggingFaceEmbedding(model_name=\"thenlper/gte-large\")\n",
"Settings.embed_model = embed_model\n",
"\n",
"#load indexs store in presist_dir\n",
"\n",
"## Note: Use folder in the google drive which having indexes (do not use folder having .txt file).\n",
"## Indexed are build and kept in sum_key_vector_index_ensemble folder on gDrive.\n",
"## Location - https://drive.google.com/drive/folders/14ASzYUxIPeUCtsxFY9Jwzb1FKXY08lA5?usp=share_link\n",
"## If required, you can built it again. Please let us know to do it.\n",
"\n",
"storage_context = StorageContext.from_defaults(persist_dir = r'C:\\Users\\agshi\\Downloads\\sum_key_vector_index_ensemble-20240909T154445Z-001-20240911T083314Z-001\\sum_key_vector_index_ensemble-20240909T154445Z-001\\sum_key_vector_index_ensemble')\n",
"vector_index = load_index_from_storage(storage_context, index_id = \"9ff973d9-c21b-4710-a8e6-dfe399aa2cd5\")\n",
"keyword_index = load_index_from_storage(storage_context, index_id = \"34a4783e-7bbe-4eb9-acc6-0227b9173688\")\n",
"summary_index = load_index_from_storage(storage_context, index_id = \"1f3c9c00-00af-4435-be85-78e07c12417e\")\n",
"\n",
"#the default question answer prompt template\n",
"\n",
"QA_PROMPT_TMPL = (\n",
" \"Context information is below.\\n\"\n",
" \"---------------------\\n\"\n",
" \"{context_str}\\n\"\n",
" \"---------------------\\n\"\n",
" \"Given the context information and not prior knowledge, \"\n",
" \"answer the question. If the answer is not in the context, inform \"\n",
" \"the user that you can't answer the question - DO NOT MAKE UP AN ANSWER.\\n\"\n",
" \"Question: {query_str}\\n\"\n",
" \"Answer : \"\n",
")\n",
"QA_PROMPT = PromptTemplate(QA_PROMPT_TMPL)\n",
"\n",
"# assign prompt to query_engine\n",
"\n",
"keyword_query_engine = keyword_index.as_query_engine(\n",
" text_qa_template=QA_PROMPT\n",
")\n",
"vector_query_engine = vector_index.as_query_engine(text_qa_template=QA_PROMPT)\n",
"\n",
"summary_query_engine = summary_index.as_query_engine(text_qa_template=QA_PROMPT)\n",
"\n",
"\n",
"# Convert them to queryenginetools\n",
"\n",
"keyword_tool = QueryEngineTool.from_defaults(\n",
" query_engine=keyword_query_engine,\n",
" description=\"Useful for answering questions about this context\",\n",
")\n",
"\n",
"vector_tool = QueryEngineTool.from_defaults(\n",
" query_engine=vector_query_engine,\n",
" description=\"Useful for answering questions about this context\",\n",
")\n",
"\n",
"summary_tool = QueryEngineTool.from_defaults(\n",
" query_engine=summary_query_engine,\n",
" description=\"Useful for answering questions about this context\",\n",
")\n",
"\n",
"# To enable synthesis between documents\n",
"\n",
"from llama_index.core.query_engine import RouterQueryEngine\n",
"from llama_index.core.selectors import LLMSingleSelector, LLMMultiSelector\n",
"from llama_index.core.selectors import (\n",
" PydanticMultiSelector,\n",
" PydanticSingleSelector,\n",
")\n",
"from llama_index.core.response_synthesizers import TreeSummarize\n",
"\n",
"TREE_SUMMARIZE_PROMPT_TMPL = (\n",
" \"Context information from multiple sources is below. Each source may or\"\n",
" \" may not have \\na relevance score attached to\"\n",
" \" it.\\n---------------------\\n{context_str}\\n---------------------\\nGiven\"\n",
" \" the information from multiple sources and their associated relevance\"\n",
" \" scores (if provided) and not prior knowledge, answer the question. If\"\n",
" \" the answer is not in the context, inform the user that you can't answer\"\n",
" \" the question.\\nQuestion: {query_str}\\nAnswer: \"\n",
")\n",
"\n",
"tree_summarize = TreeSummarize(\n",
" summary_template=PromptTemplate(TREE_SUMMARIZE_PROMPT_TMPL)\n",
")\n",
"\n",
"#this the final query_engine\n",
"\n",
"query_engine = RouterQueryEngine(\n",
" selector=LLMMultiSelector.from_defaults(),\n",
" query_engine_tools=[\n",
" keyword_tool,\n",
" vector_tool,\n",
" summary_tool,\n",
" ],\n",
" summarizer=tree_summarize,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "ac39e364-1be3-46e8-bf84-55148d1786fa",
"metadata": {
"id": "ac39e364-1be3-46e8-bf84-55148d1786fa"
},
"source": [
"### without any query transform"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "49fa4f27-4d8a-4074-bf27-a5195e73bdce",
"metadata": {
"id": "49fa4f27-4d8a-4074-bf27-a5195e73bdce"
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\agshi\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\transformers\\models\\bert\\modeling_bert.py:439: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\\aten\\src\\ATen\\native\\transformers\\cuda\\sdp_utils.cpp:455.)\n",
" attn_output = torch.nn.functional.scaled_dot_product_attention(\n"
]
},
{
"data": {
"text/markdown": [
"**`Final Response:`** I'm ready to answer your question based on the provided context information, specifically regarding the disclosure and use of confidential information as per the Global Minimum Tax Act and related legislation. Please go ahead and ask your question."
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"response = await query_engine.aquery(\n",
" \" \"\n",
")\n",
"\n",
"from llama_index.core.response.notebook_utils import display_response\n",
"\n",
"display_response(response)"
]
},
{
"cell_type": "markdown",
"id": "b2940a9f-b335-4740-955a-b0ed46861541",
"metadata": {
"id": "b2940a9f-b335-4740-955a-b0ed46861541"
},
"source": [
"### add query transformation improve retrival"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "42bf1a09-69e8-48f9-95c0-017d28ce43f4",
"metadata": {
"id": "42bf1a09-69e8-48f9-95c0-017d28ce43f4"
},
"outputs": [],
"source": [
"def refine_query(query: str) -> str:\n",
" refined_query = f\"Provide a detailed answer about '{query}' in the context of legal enquiries\"\n",
" return refined_query"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "bdf741e8-bdf1-4a32-9cb1-f01a1e5b7264",
"metadata": {
"id": "bdf741e8-bdf1-4a32-9cb1-f01a1e5b7264"
},
"outputs": [],
"source": [
"original_query = \"How much can the Minister of Health pay out of the Consolidated Revenue Fund in relation to coronavirus disease 2019 (COVID-19) tests\"\n",
"refined_query = refine_query(original_query)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "b0dc9029-8ab3-4bba-bf83-2dffba2baf39",
"metadata": {
"id": "b0dc9029-8ab3-4bba-bf83-2dffba2baf39"
},
"outputs": [
{
"data": {
"text/markdown": [
"**`Final Response:`** Based on the provided context information from Bill C-10 and Bill C-8, the Minister of Health is authorized to make payments out of the Consolidated Revenue Fund in relation to coronavirus disease 2019 (COVID-19) tests.\n",
"\n",
"From Bill C-10, it is stated that the Minister of Health can pay up to $2.5 billion out of the Consolidated Revenue Fund in relation to COVID-19 tests. This is stated in Section 1 of the Act, which reads: \"The Minister of Health may make payments, the total of which may not exceed $2.5 billion, out of the Consolidated Revenue Fund for any expenses incurred on or after January 1, 2022 in relation to coronavirus disease 2019 (COVID-19) tests.\"\n",
"\n",
"From Bill C-8, it is stated that the Minister of Health can also pay up to $1.72 billion out of the Consolidated Revenue Fund in relation to COVID-19 tests. This is stated in Part 6 of the Act, which reads: \"Part 6 authorizes the Minister of Health to make payments of up to $1.72 billion out of the Consolidated Revenue Fund in relation to coronavirus disease 2019 (COVID-19) tests.\"\n",
"\n",
"It is worth noting that these two bills may have different purposes and provisions, but in the context of the question, both bills provide information on the Minister of Health's authority to make payments out of the Consolidated Revenue Fund in relation to COVID-19 tests.\n",
"\n",
"Therefore, the total amount that the Minister of Health can pay out of the Consolidated Revenue Fund in relation to coronavirus disease 2019 (COVID-19) tests is the sum of the authorized amounts from both bills, which is $2.5 billion + $1.72 billion = $4.22 billion.\n",
"\n",
"However, it is also possible that the Minister of Health may only be authorized to make payments up to the lower of the two amounts, which is $1.72 billion, if the expenses incurred are only up to that amount. But based on the information provided, it seems that the Minister of Health has the authority to make payments up to the higher amount of $2.5 billion."
],
"text/plain": [
"<IPython.core.display.Markdown object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"response = await query_engine.aquery(\n",
" refined_query\n",
")\n",
"\n",
"from llama_index.core.response.notebook_utils import display_response\n",
"\n",
"display_response(response)"
]
},
{
"cell_type": "markdown",
"id": "9622762a-0109-4a35-ad70-eae7291f53d4",
"metadata": {
"id": "9622762a-0109-4a35-ad70-eae7291f53d4"
},
"source": [
"## Evaluation"
]
},
{
"cell_type": "markdown",
"id": "2GjZqIeUIQ0r",
"metadata": {
"id": "2GjZqIeUIQ0r"
},
"source": [
"## Proviing API key for Google Gemini API"
]
},
{
"cell_type": "markdown",
"id": "tg6gD-aaJig7",
"metadata": {
"id": "tg6gD-aaJig7"
},
"source": [
"## loading the data from google drive"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "8rfq-4aHIODo",
"metadata": {
"id": "8rfq-4aHIODo"
},
"outputs": [
{
"ename": "ImportError",
"evalue": "`llama-index-readers-file` package not found",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mImportError\u001b[0m Traceback (most recent call last)",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\llama_index\\core\\readers\\file\\base.py:52\u001b[0m, in \u001b[0;36m_try_loading_included_file_formats\u001b[1;34m()\u001b[0m\n\u001b[0;32m 51\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m---> 52\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mllama_index\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mreaders\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfile\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[0;32m 53\u001b[0m DocxReader,\n\u001b[0;32m 54\u001b[0m EpubReader,\n\u001b[0;32m 55\u001b[0m HWPReader,\n\u001b[0;32m 56\u001b[0m ImageReader,\n\u001b[0;32m 57\u001b[0m IPYNBReader,\n\u001b[0;32m 58\u001b[0m MarkdownReader,\n\u001b[0;32m 59\u001b[0m MboxReader,\n\u001b[0;32m 60\u001b[0m PandasCSVReader,\n\u001b[0;32m 61\u001b[0m PandasExcelReader,\n\u001b[0;32m 62\u001b[0m PDFReader,\n\u001b[0;32m 63\u001b[0m PptxReader,\n\u001b[0;32m 64\u001b[0m VideoAudioReader,\n\u001b[0;32m 65\u001b[0m ) \u001b[38;5;66;03m# pants: no-infer-dep\u001b[39;00m\n\u001b[0;32m 66\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m:\n",
"\u001b[1;31mImportError\u001b[0m: cannot import name 'DocxReader' from 'llama_index.readers.file' (unknown location)",
"\nDuring handling of the above exception, another exception occurred:\n",
"\u001b[1;31mImportError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[11], line 2\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mllama_index\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m SimpleDirectoryReader\n\u001b[1;32m----> 2\u001b[0m documents \u001b[38;5;241m=\u001b[39m \u001b[43mSimpleDirectoryReader\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43mr\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mC:\u001b[39;49m\u001b[38;5;124;43m\\\u001b[39;49m\u001b[38;5;124;43mUsers\u001b[39;49m\u001b[38;5;124;43m\\\u001b[39;49m\u001b[38;5;124;43magshi\u001b[39;49m\u001b[38;5;124;43m\\\u001b[39;49m\u001b[38;5;124;43mDownloads\u001b[39;49m\u001b[38;5;124;43m\\\u001b[39;49m\u001b[38;5;124;43mdiscussion_data-20240911T083316Z-001\u001b[39;49m\u001b[38;5;124;43m\\\u001b[39;49m\u001b[38;5;124;43mdiscussion_data\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfilename_as_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload_data\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 3\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mLoaded \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mlen\u001b[39m(documents)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m documents.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\llama_index\\core\\readers\\file\\base.py:697\u001b[0m, in \u001b[0;36mSimpleDirectoryReader.load_data\u001b[1;34m(self, show_progress, num_workers, fs)\u001b[0m\n\u001b[0;32m 692\u001b[0m files_to_process \u001b[38;5;241m=\u001b[39m tqdm(\n\u001b[0;32m 693\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minput_files, desc\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mLoading files\u001b[39m\u001b[38;5;124m\"\u001b[39m, unit\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfile\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 694\u001b[0m )\n\u001b[0;32m 695\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m input_file \u001b[38;5;129;01min\u001b[39;00m files_to_process:\n\u001b[0;32m 696\u001b[0m documents\u001b[38;5;241m.\u001b[39mextend(\n\u001b[1;32m--> 697\u001b[0m \u001b[43mSimpleDirectoryReader\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mload_file\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m 698\u001b[0m \u001b[43m \u001b[49m\u001b[43minput_file\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minput_file\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 699\u001b[0m \u001b[43m \u001b[49m\u001b[43mfile_metadata\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfile_metadata\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 700\u001b[0m \u001b[43m \u001b[49m\u001b[43mfile_extractor\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfile_extractor\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 701\u001b[0m \u001b[43m \u001b[49m\u001b[43mfilename_as_id\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfilename_as_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 702\u001b[0m \u001b[43m \u001b[49m\u001b[43mencoding\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoding\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 703\u001b[0m \u001b[43m \u001b[49m\u001b[43merrors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43merrors\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 704\u001b[0m \u001b[43m \u001b[49m\u001b[43mraise_on_error\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mraise_on_error\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 705\u001b[0m \u001b[43m \u001b[49m\u001b[43mfs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m 706\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 707\u001b[0m )\n\u001b[0;32m 709\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_exclude_metadata(documents)\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\llama_index\\core\\readers\\file\\base.py:518\u001b[0m, in \u001b[0;36mSimpleDirectoryReader.load_file\u001b[1;34m(input_file, file_metadata, file_extractor, filename_as_id, encoding, errors, raise_on_error, fs)\u001b[0m\n\u001b[0;32m 485\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 486\u001b[0m \u001b[38;5;124;03mStatic method for loading file.\u001b[39;00m\n\u001b[0;32m 487\u001b[0m \n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 515\u001b[0m \u001b[38;5;124;03m List[Document]: loaded documents\u001b[39;00m\n\u001b[0;32m 516\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 517\u001b[0m \u001b[38;5;66;03m# TODO: make this less redundant\u001b[39;00m\n\u001b[1;32m--> 518\u001b[0m default_file_reader_cls \u001b[38;5;241m=\u001b[39m \u001b[43mSimpleDirectoryReader\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msupported_suffix_fn\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 519\u001b[0m default_file_reader_suffix \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(default_file_reader_cls\u001b[38;5;241m.\u001b[39mkeys())\n\u001b[0;32m 520\u001b[0m metadata: Optional[\u001b[38;5;28mdict\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\llama_index\\core\\readers\\file\\base.py:67\u001b[0m, in \u001b[0;36m_try_loading_included_file_formats\u001b[1;34m()\u001b[0m\n\u001b[0;32m 52\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mllama_index\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mreaders\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mfile\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m (\n\u001b[0;32m 53\u001b[0m DocxReader,\n\u001b[0;32m 54\u001b[0m EpubReader,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 64\u001b[0m VideoAudioReader,\n\u001b[0;32m 65\u001b[0m ) \u001b[38;5;66;03m# pants: no-infer-dep\u001b[39;00m\n\u001b[0;32m 66\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m:\n\u001b[1;32m---> 67\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mImportError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`llama-index-readers-file` package not found\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 69\u001b[0m default_file_reader_cls: Dict[\u001b[38;5;28mstr\u001b[39m, Type[BaseReader]] \u001b[38;5;241m=\u001b[39m {\n\u001b[0;32m 70\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.hwp\u001b[39m\u001b[38;5;124m\"\u001b[39m: HWPReader,\n\u001b[0;32m 71\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.pdf\u001b[39m\u001b[38;5;124m\"\u001b[39m: PDFReader,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 89\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.xlsx\u001b[39m\u001b[38;5;124m\"\u001b[39m: PandasExcelReader,\n\u001b[0;32m 90\u001b[0m }\n\u001b[0;32m 91\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m default_file_reader_cls\n",
"\u001b[1;31mImportError\u001b[0m: `llama-index-readers-file` package not found"
]
}
],
"source": [
"from llama_index.core import SimpleDirectoryReader\n",
"documents = SimpleDirectoryReader(r\"C:\\Users\\agshi\\Downloads\\discussion_data-20240911T083316Z-001\\discussion_data\", filename_as_id=True).load_data()\n",
"print(f\"Loaded {len(documents)} documents.\")"
]
},
{
"cell_type": "markdown",
"id": "kRpFq6vyLnXR",
"metadata": {
"id": "kRpFq6vyLnXR"
},
"source": [
"## Generating the questions for evaluation"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "XhHDA90HJfaF",
"metadata": {
"id": "XhHDA90HJfaF"
},
"outputs": [
{
"ename": "TypeError",
"evalue": "Expected: str, Model, or TunedModel",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)",
"Cell \u001b[1;32mIn[3], line 10\u001b[0m\n\u001b[0;32m 8\u001b[0m \u001b[38;5;66;03m# create llm\u001b[39;00m\n\u001b[0;32m 9\u001b[0m os\u001b[38;5;241m.\u001b[39menviron[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mGOOGLE_API_KEY\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAIzaSyC_UnbyMmhvklBRyjLvdEWXuhXim_BX0fk\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m---> 10\u001b[0m Settings\u001b[38;5;241m.\u001b[39mllm \u001b[38;5;241m=\u001b[39m \u001b[43mGemini\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mmodels/gemini-pro\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtemperature\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[0;32m 11\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mquestion_dataset_generator\u001b[39m(document):\n\u001b[0;32m 12\u001b[0m dataset_generator \u001b[38;5;241m=\u001b[39m RagDatasetGenerator\u001b[38;5;241m.\u001b[39mfrom_documents(\n\u001b[0;32m 13\u001b[0m documents\u001b[38;5;241m=\u001b[39mdocument,\n\u001b[0;32m 14\u001b[0m llm\u001b[38;5;241m=\u001b[39mllm,\n\u001b[0;32m 15\u001b[0m num_questions_per_chunk\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m2\u001b[39m,\n\u001b[0;32m 16\u001b[0m show_progress\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m \u001b[38;5;66;03m# set the number of qu/estions per nodes\u001b[39;00m\n\u001b[0;32m 17\u001b[0m )\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\llama_index\\llms\\gemini\\base.py:147\u001b[0m, in \u001b[0;36mGemini.__init__\u001b[1;34m(self, api_key, model, temperature, max_tokens, generation_config, safety_settings, callback_manager, api_base, transport, model_name, default_headers, **generate_kwargs)\u001b[0m\n\u001b[0;32m 139\u001b[0m final_gen_config \u001b[38;5;241m=\u001b[39m {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtemperature\u001b[39m\u001b[38;5;124m\"\u001b[39m: temperature, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mbase_gen_config}\n\u001b[0;32m 141\u001b[0m model \u001b[38;5;241m=\u001b[39m genai\u001b[38;5;241m.\u001b[39mGenerativeModel(\n\u001b[0;32m 142\u001b[0m model_name\u001b[38;5;241m=\u001b[39mmodel,\n\u001b[0;32m 143\u001b[0m generation_config\u001b[38;5;241m=\u001b[39mfinal_gen_config,\n\u001b[0;32m 144\u001b[0m safety_settings\u001b[38;5;241m=\u001b[39msafety_settings,\n\u001b[0;32m 145\u001b[0m )\n\u001b[1;32m--> 147\u001b[0m model_meta \u001b[38;5;241m=\u001b[39m \u001b[43mgenai\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_model\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 149\u001b[0m supported_methods \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_model_meta\u001b[38;5;241m.\u001b[39msupported_generation_methods\n\u001b[0;32m 150\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mgenerateContent\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m supported_methods:\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\google\\generativeai\\models.py:52\u001b[0m, in \u001b[0;36mget_model\u001b[1;34m(name, client, request_options)\u001b[0m\n\u001b[0;32m 30\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mget_model\u001b[39m(\n\u001b[0;32m 31\u001b[0m name: model_types\u001b[38;5;241m.\u001b[39mAnyModelNameOptions,\n\u001b[0;32m 32\u001b[0m \u001b[38;5;241m*\u001b[39m,\n\u001b[0;32m 33\u001b[0m client\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m 34\u001b[0m request_options: \u001b[38;5;28mdict\u001b[39m[\u001b[38;5;28mstr\u001b[39m, Any] \u001b[38;5;241m|\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m,\n\u001b[0;32m 35\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m model_types\u001b[38;5;241m.\u001b[39mModel \u001b[38;5;241m|\u001b[39m model_types\u001b[38;5;241m.\u001b[39mTunedModel:\n\u001b[0;32m 36\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Given a model name, fetch the `types.Model` or `types.TunedModel` object.\u001b[39;00m\n\u001b[0;32m 37\u001b[0m \n\u001b[0;32m 38\u001b[0m \u001b[38;5;124;03m ```\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 50\u001b[0m \u001b[38;5;124;03m A `types.Model` or `types.TunedModel` object.\u001b[39;00m\n\u001b[0;32m 51\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[1;32m---> 52\u001b[0m name \u001b[38;5;241m=\u001b[39m \u001b[43mmodel_types\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmake_model_name\u001b[49m\u001b[43m(\u001b[49m\u001b[43mname\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m 53\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m name\u001b[38;5;241m.\u001b[39mstartswith(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodels/\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[0;32m 54\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m get_base_model(name, client\u001b[38;5;241m=\u001b[39mclient, request_options\u001b[38;5;241m=\u001b[39mrequest_options)\n",
"File \u001b[1;32m~\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\google\\generativeai\\types\\model_types.py:350\u001b[0m, in \u001b[0;36mmake_model_name\u001b[1;34m(name)\u001b[0m\n\u001b[0;32m 348\u001b[0m name \u001b[38;5;241m=\u001b[39m name\n\u001b[0;32m 349\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 350\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mExpected: str, Model, or TunedModel\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 352\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (name\u001b[38;5;241m.\u001b[39mstartswith(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmodels/\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m name\u001b[38;5;241m.\u001b[39mstartswith(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtunedModels/\u001b[39m\u001b[38;5;124m\"\u001b[39m)):\n\u001b[0;32m 353\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mModel names should start with `models/` or `tunedModels/`, got: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
"\u001b[1;31mTypeError\u001b[0m: Expected: str, Model, or TunedModel"
]
}
],
"source": [
"from llama_index.core import SimpleDirectoryReader\n",
"from llama_index.core.llama_dataset.generator import RagDatasetGenerator\n",
"from llama_index.llms.gemini import Gemini\n",
"import os\n",
"import nest_asyncio\n",
"nest_asyncio.apply()\n",
"# create llm\n",
"os.environ[\"GOOGLE_API_KEY\"] = \"your key\"\n",
"Settings.llm = Gemini(model=\"models/gemini-pro\", temperature=0)\n",
"def question_dataset_generator(document):\n",
" dataset_generator = RagDatasetGenerator.from_documents(\n",
" documents=document,\n",
" llm=llm,\n",
" num_questions_per_chunk=2,\n",
" show_progress=True # set the number of qu/estions per nodes\n",
" )\n",
"\n",
" rag_dataset = dataset_generator.generate_questions_from_nodes()\n",
" question = [e.query for e in rag_dataset.examples]\n",
" return question"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "tzOWBcXLQ_yx",
"metadata": {
"id": "tzOWBcXLQ_yx"
},
"outputs": [],
"source": [
"def chunk_document(document, chunk_size):\n",
" # Split the document into chunks of the specified chunk size\n",
" return [document[i:i+chunk_size] for i in range(0, len(document), chunk_size)]\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "x5Kal2KNR9Ly",
"metadata": {
"id": "x5Kal2KNR9Ly"
},
"outputs": [],
"source": [
"questions = []\n",
"for i in range(0, len(documents)-76, 2):\n",
" print(i)\n",
" document_pair = documents[i:i+2] # Take two documents at a time\n",
" question = question_dataset_generator(document_pair)\n",
" questions.extend(question)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8ngVuNi0UJ3Y",
"metadata": {
"id": "8ngVuNi0UJ3Y"
},
"outputs": [],
"source": [
"question_dataset_generator(documents[3:4])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "n3vCCfpCMjCD",
"metadata": {
"id": "n3vCCfpCMjCD"
},
"outputs": [],
"source": [
"from llama_index.core.evaluation import BatchEvalRunner\n",
"from llama_index.core.evaluation import RelevancyEvaluator\n",
"from llama_index.core.evaluation import FaithfulnessEvaluator\n",
"from llama_index.llms.groq import Groq\n",
"import os\n",
"from llama_index.llms.gemini import Gemini\n",
"\n",
"os.environ[\"GOOGLE_API_KEY\"] = \"your key\"\n",
"llm = Gemini(model=\"models/gemini-pro\", temperature=0)\n",
"relevancy_evaluator = RelevancyEvaluator(llm=llm)\n",
"faithfulness_evaluator = FaithfulnessEvaluator(llm=llm)\n",
"runner = BatchEvalRunner(\n",
" {\"faithfulness\": faithfulness_evaluator, \"relevancy\": relevancy_evaluator},\n",
" workers=8,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "il3Ft3BwXh6y",
"metadata": {
"id": "il3Ft3BwXh6y"
},
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"id": "PvuRHPsHNz3W",
"metadata": {
"id": "PvuRHPsHNz3W"
},
"outputs": [],
"source": [
"def extract_elements(eval_result):\n",
" # Dictionary to store the extracted elements\n",
" extracted_data = {\n",
" \"contexts\": [eval_result.contexts],\n",
" \"response\": [eval_result.response],\n",
" \"passing\": [eval_result.passing],\n",
" \"feedback\": [eval_result.feedback],\n",
" \"score\": [eval_result.score],\n",
" \"pairwise_source\": [eval_result.pairwise_source],\n",
" \"invalid_result\": [eval_result.invalid_result],\n",
" \"invalid_reason\": [eval_result.invalid_reason]\n",
" }\n",
"\n",
" # Convert the dictionary into a DataFrame\n",
" df = pd.DataFrame(extracted_data)\n",
" return df\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dPhc-s5vXa3U",
"metadata": {
"id": "dPhc-s5vXa3U"
},
"outputs": [],
"source": [
"import time\n",
"faithfulness_df = pd.DataFrame()\n",
"relevancy_df = pd.DataFrame()\n",
"\n",
"for question in questions:\n",
" response = query_engine.query(question)\n",
"\n",
" # Evaluate faithfulness\n",
" eval_result = faithfulness_evaluator.evaluate_response(query=question, response=response)\n",
" faithfulness_elements = extract_elements(eval_result)\n",
" faithfulness_df = pd.concat([faithfulness_df, faithfulness_elements], ignore_index=True)\n",
"\n",
" # Evaluate relevancy\n",
" eval_result = relevancy_evaluator.evaluate_response( query=question, response=response)\n",
" relevancy_elements = extract_elements(eval_result)\n",
" relevancy_df = pd.concat([relevancy_df,relevancy_elements], ignore_index=True)\n",
"\n",
" time.sleep(60)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "_4GcnTTspCye",
"metadata": {
"id": "_4GcnTTspCye"
},
"outputs": [],
"source": [
"relevancy_df"
]
},
{
"cell_type": "markdown",
"id": "HKJjb133Pris",
"metadata": {
"id": "HKJjb133Pris"
},
"source": [
"## Creating dataframe for average score calculation"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "PWUJhbKZRhk4",
"metadata": {
"id": "PWUJhbKZRhk4"
},
"outputs": [],
"source": [
"def calculate_average_scores(faithfulness_df,relevancy_df):\n",
" avg_faithfulness_score = faithfulness_df['score'].mean()\n",
" avg_relevancy_score = relevancy_df['score'].mean()\n",
" return {\n",
" \"average_faithfulness_score\": avg_faithfulness_score,\n",
" \"average_relevancy_score\": avg_relevancy_score\n",
" }"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "rsu0PaLIT3kP",
"metadata": {
"id": "rsu0PaLIT3kP"
},
"outputs": [],
"source": [
"calculate_average_scores(faithfulness_df,relevancy_df)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6vNdJLyNT6UC",
"metadata": {
"id": "6vNdJLyNT6UC"
},
"outputs": [],
"source": [
"faithfulness_df"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bkrArTVUjaQU",
"metadata": {
"id": "bkrArTVUjaQU"
},
"outputs": [],
"source": []
}
],
"metadata": {
"colab": {
"private_outputs": true,
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|