File size: 51,944 Bytes
de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 ee39a70 de7c780 12defec ee39a70 12defec ee39a70 12defec ee39a70 de7c780 12defec ee39a70 12defec ee39a70 de7c780 12defec ee39a70 12defec ee39a70 12defec ee39a70 12defec ee39a70 12defec ee39a70 12defec ee39a70 12defec ee39a70 12defec ee39a70 12defec ee39a70 12defec ee39a70 12defec ee39a70 12defec 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 061aa4e ee39a70 de7c780 ee39a70 4856f42 ee39a70 de7c780 4856f42 de7c780 6674a75 de7c780 6674a75 8337858 de7c780 8337858 de7c780 4b9f80a ddcaad4 4b9f80a de7c780 4b9f80a de7c780 |
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 |
from api.settings import RetCode
from test_sdkbase import TestSdk
from ragflow import RAGFlow
import pytest
from common import API_KEY, HOST_ADDRESS
class TestFile(TestSdk):
"""
This class contains a suite of tests for the content management functionality within the dataset.
It ensures that the following functionalities as expected:
1. upload local files
2. upload remote files
3. download a file
4. delete a file
5. enable rename
6. list files
7. start parsing
8. end parsing
9. check the status of the file
10. list the chunks
11. delete a chunk
12. insert a new chunk
13. edit the status of chunk
14. get the specific chunk
15. retrieval test
"""
# ----------------------------upload local files-----------------------------------------------------
def test_upload_two_files(self):
"""
Test uploading two files with success.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_upload_two_files")
dataset_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
res = ragflow.upload_local_file(dataset_id, file_paths)
assert res["code"] == RetCode.SUCCESS and res["message"] == "success"
def test_upload_one_file(self):
"""
Test uploading one file with success.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_upload_one_file")
dataset_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt"]
res = ragflow.upload_local_file(dataset_id, file_paths)
assert res["code"] == RetCode.SUCCESS and res["message"] == "success"
def test_upload_nonexistent_files(self):
"""
Test uploading a file which does not exist.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_upload_nonexistent_files")
dataset_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/imagination.txt"]
res = ragflow.upload_local_file(dataset_id, file_paths)
assert res["code"] == RetCode.DATA_ERROR and "does not exist" in res["message"]
def test_upload_file_if_dataset_does_not_exist(self):
"""
Test uploading files if the dataset id does not exist.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
file_paths = ["test_data/test.txt"]
res = ragflow.upload_local_file("111", file_paths)
assert res["code"] == RetCode.DATA_ERROR and res["message"] == "Can't find this dataset"
def test_upload_file_without_name(self):
"""
Test uploading files that do not have name.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_upload_file_without_name")
dataset_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/.txt"]
res = ragflow.upload_local_file(dataset_id, file_paths)
assert res["code"] == RetCode.SUCCESS
def test_upload_file_without_name1(self):
"""
Test uploading files that do not have name.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_upload_file_without_name")
dataset_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/.txt", "test_data/empty.txt"]
res = ragflow.upload_local_file(dataset_id, file_paths)
assert res["code"] == RetCode.SUCCESS
def test_upload_files_exceeding_the_number_limit(self):
"""
Test uploading files whose number exceeds the limit.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_upload_files_exceeding_the_number_limit")
dataset_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt", "test_data/test1.txt"] * 256
res = ragflow.upload_local_file(dataset_id, file_paths)
assert (res["message"] ==
"You try to upload 512 files, which exceeds the maximum number of uploading files: 256"
and res["code"] == RetCode.DATA_ERROR)
def test_upload_files_without_files(self):
"""
Test uploading files without files.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_upload_files_without_files")
dataset_id = created_res["data"]["dataset_id"]
file_paths = [None]
res = ragflow.upload_local_file(dataset_id, file_paths)
assert (res["message"] == "None is not string." and res["code"] == RetCode.ARGUMENT_ERROR)
def test_upload_files_with_two_files_with_same_name(self):
"""
Test uploading files with the same name.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_upload_files_with_two_files_with_same_name")
dataset_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt"] * 2
res = ragflow.upload_local_file(dataset_id, file_paths)
assert (res["message"] == "success" and res["code"] == RetCode.SUCCESS)
def test_upload_files_with_file_paths(self):
"""
Test uploading files with only specifying the file path's repo.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_upload_files_with_file_paths")
dataset_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/"]
res = ragflow.upload_local_file(dataset_id, file_paths)
assert (res["message"] == "The file test_data/ does not exist" and res["code"] == RetCode.DATA_ERROR)
def test_upload_files_with_remote_file_path(self):
"""
Test uploading files with remote files.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_upload_files_with_remote_file_path")
dataset_id = created_res["data"]["dataset_id"]
file_paths = ["https://github.com/genostack/ragflow"]
res = ragflow.upload_local_file(dataset_id, file_paths)
assert res["code"] == RetCode.ARGUMENT_ERROR and res["message"] == "Remote files have not unsupported."
# ----------------------------delete a file-----------------------------------------------------
def test_delete_one_file(self):
"""
Test deleting one file with success.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_delete_one_file")
dataset_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt"]
res = ragflow.upload_local_file(dataset_id, file_paths)
# get the doc_id
data = res["data"][0]
doc_id = data["id"]
# delete the files
deleted_res = ragflow.delete_files(doc_id, dataset_id)
# assert value
assert deleted_res["code"] == RetCode.SUCCESS and deleted_res["data"] is True
def test_delete_document_with_not_existing_document(self):
"""
Test deleting a document that does not exist with failure.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_delete_document_with_not_existing_document")
dataset_id = created_res["data"]["dataset_id"]
res = ragflow.delete_files("111", dataset_id)
assert res["code"] == RetCode.DATA_ERROR and res["message"] == "Document 111 not found!"
def test_delete_document_with_creating_100_documents_and_deleting_100_documents(self):
"""
Test deleting documents when uploading 100 docs and deleting 100 docs.
"""
# upload 100 docs
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_delete_one_file")
dataset_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt"] * 100
res = ragflow.upload_local_file(dataset_id, file_paths)
# get the doc_id
data = res["data"]
for d in data:
doc_id = d["id"]
# delete the files
deleted_res = ragflow.delete_files(doc_id, dataset_id)
# assert value
assert deleted_res["code"] == RetCode.SUCCESS and deleted_res["data"] is True
def test_delete_document_from_nonexistent_dataset(self):
"""
Test deleting documents from a non-existent dataset
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_delete_one_file")
dataset_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt"]
res = ragflow.upload_local_file(dataset_id, file_paths)
# get the doc_id
data = res["data"][0]
doc_id = data["id"]
# delete the files
deleted_res = ragflow.delete_files(doc_id, "000")
# assert value
assert (deleted_res["code"] == RetCode.ARGUMENT_ERROR and deleted_res["message"] ==
f"The document {doc_id} is not in the dataset: 000, but in the dataset: {dataset_id}.")
def test_delete_document_which_is_located_in_other_dataset(self):
"""
Test deleting a document which is located in other dataset.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
# upload a document
created_res = ragflow.create_dataset("test_delete_document_which_is_located_in_other_dataset")
created_res_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt"]
res = ragflow.upload_local_file(created_res_id, file_paths)
# other dataset
other_res = ragflow.create_dataset("other_dataset")
other_dataset_id = other_res["data"]["dataset_id"]
# get the doc_id
data = res["data"][0]
doc_id = data["id"]
# delete the files from the other dataset
deleted_res = ragflow.delete_files(doc_id, other_dataset_id)
# assert value
assert (deleted_res["code"] == RetCode.ARGUMENT_ERROR and deleted_res["message"] ==
f"The document {doc_id} is not in the dataset: {other_dataset_id}, but in the dataset: {created_res_id}.")
# ----------------------------list files-----------------------------------------------------
def test_list_documents_with_success(self):
"""
Test listing documents with a successful outcome.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
# upload a document
created_res = ragflow.create_dataset("test_list_documents_with_success")
created_res_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt"]
ragflow.upload_local_file(created_res_id, file_paths)
# Call the list_document method
response = ragflow.list_files(created_res_id)
assert response["code"] == RetCode.SUCCESS and len(response["data"]["docs"]) == 1
def test_list_documents_with_checking_size(self):
"""
Test listing documents and verify the size and names of the documents.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
# upload 10 documents
created_res = ragflow.create_dataset("test_list_documents_with_checking_size")
created_res_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt"] * 10
ragflow.upload_local_file(created_res_id, file_paths)
# Call the list_document method
response = ragflow.list_files(created_res_id)
assert response["code"] == RetCode.SUCCESS and len(response["data"]["docs"]) == 10
def test_list_documents_with_getting_empty_result(self):
"""
Test listing documents that should be empty.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
# upload 0 documents
created_res = ragflow.create_dataset("test_list_documents_with_getting_empty_result")
created_res_id = created_res["data"]["dataset_id"]
# Call the list_document method
response = ragflow.list_files(created_res_id)
assert response["code"] == RetCode.SUCCESS and len(response["data"]["docs"]) == 0
def test_list_documents_with_creating_100_documents(self):
"""
Test listing 100 documents and verify the size of these documents.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
# upload 100 documents
created_res = ragflow.create_dataset("test_list_documents_with_creating_100_documents")
created_res_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt"] * 100
ragflow.upload_local_file(created_res_id, file_paths)
# Call the list_document method
response = ragflow.list_files(created_res_id)
assert response["code"] == RetCode.SUCCESS and len(response["data"]["docs"]) == 100
def test_list_document_with_failure(self):
"""
Test listing documents with IndexError.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_list_document_with_failure")
created_res_id = created_res["data"]["dataset_id"]
response = ragflow.list_files(created_res_id, offset=-1, count=-1)
assert "IndexError" in response["message"] and response["code"] == RetCode.EXCEPTION_ERROR
def test_list_document_with_verifying_offset_and_count(self):
"""
Test listing documents with verifying the functionalities of offset and count.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_list_document_with_verifying_offset_and_count")
created_res_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt", "test_data/empty.txt"] * 10
ragflow.upload_local_file(created_res_id, file_paths)
# Call the list_document method
response = ragflow.list_files(created_res_id, offset=2, count=10)
assert response["code"] == RetCode.SUCCESS and len(response["data"]["docs"]) == 10
def test_list_document_with_verifying_keywords(self):
"""
Test listing documents with verifying the functionality of searching keywords.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_list_document_with_verifying_keywords")
created_res_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt", "test_data/empty.txt"]
ragflow.upload_local_file(created_res_id, file_paths)
# Call the list_document method
response = ragflow.list_files(created_res_id, keywords="empty")
assert response["code"] == RetCode.SUCCESS and len(response["data"]["docs"]) == 1
def test_list_document_with_verifying_order_by_and_descend(self):
"""
Test listing documents with verifying the functionality of order_by and descend.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_list_document_with_verifying_order_by_and_descend")
created_res_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt", "test_data/empty.txt"]
ragflow.upload_local_file(created_res_id, file_paths)
# Call the list_document method
response = ragflow.list_files(created_res_id)
assert response["code"] == RetCode.SUCCESS and len(response["data"]["docs"]) == 2
docs = response["data"]["docs"]
# reverse
i = 1
for doc in docs:
assert doc["name"] in file_paths[i]
i -= 1
def test_list_document_with_verifying_order_by_and_ascend(self):
"""
Test listing documents with verifying the functionality of order_by and ascend.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_list_document_with_verifying_order_by_and_ascend")
created_res_id = created_res["data"]["dataset_id"]
file_paths = ["test_data/test.txt", "test_data/test1.txt", "test_data/empty.txt"]
ragflow.upload_local_file(created_res_id, file_paths)
# Call the list_document method
response = ragflow.list_files(created_res_id, descend=False)
assert response["code"] == RetCode.SUCCESS and len(response["data"]["docs"]) == 3
docs = response["data"]["docs"]
i = 0
for doc in docs:
assert doc["name"] in file_paths[i]
i += 1
# ----------------------------update files: enable, rename, template_type-------------------------------------------
def test_update_nonexistent_document(self):
"""
Test updating a document which does not exist.
"""
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_update_nonexistent_document")
created_res_id = created_res["data"]["dataset_id"]
params = {
"name": "new_name"
}
res = ragflow.update_file(created_res_id, "weird_doc_id", **params)
assert res["code"] == RetCode.ARGUMENT_ERROR and res["message"] == f"This document weird_doc_id cannot be found!"
def test_update_document_without_parameters(self):
"""
Test updating a document without giving parameters.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_update_document_without_parameters")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# update file
params = {
}
update_res = ragflow.update_file(created_res_id, doc_id, **params)
assert (update_res["code"] == RetCode.DATA_ERROR and
update_res["message"] == "Please input at least one parameter that you want to update!")
def test_update_document_in_nonexistent_dataset(self):
"""
Test updating a document in the nonexistent dataset.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_update_document_in_nonexistent_dataset")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# update file
params = {
"name": "new_name"
}
update_res = ragflow.update_file("fake_dataset_id", doc_id, **params)
assert (update_res["code"] == RetCode.DATA_ERROR and
update_res["message"] == f"This dataset fake_dataset_id cannot be found!")
def test_update_document_with_different_extension_name(self):
"""
Test the updating of a document with an extension name that differs from its original.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_update_document_with_different_extension_name")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# update file
params = {
"name": "new_name.doc"
}
update_res = ragflow.update_file(created_res_id, doc_id, **params)
assert (update_res["code"] == RetCode.ARGUMENT_ERROR and
update_res["message"] == "The extension of file cannot be changed")
def test_update_document_with_duplicate_name(self):
"""
Test the updating of a document with a duplicate name.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_update_document_with_different_extension_name")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# update file
params = {
"name": "test.txt"
}
update_res = ragflow.update_file(created_res_id, doc_id, **params)
assert (update_res["code"] == RetCode.ARGUMENT_ERROR and
update_res["message"] == "Duplicated document name in the same dataset.")
def test_update_document_with_updating_its_name_with_success(self):
"""
Test the updating of a document's name with success.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_update_document_with_updating_its_name_with_success")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# update file
params = {
"name": "new_name.txt"
}
update_res = ragflow.update_file(created_res_id, doc_id, **params)
assert (update_res["code"] == RetCode.SUCCESS and
update_res["message"] == "Success" and update_res["data"]["name"] == "new_name.txt")
def test_update_document_with_updating_its_template_type_with_success(self):
"""
Test the updating of a document's template type with success.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_update_document_with_updating_its_template_type_with_success")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# update file
params = {
"template_type": "laws"
}
update_res = ragflow.update_file(created_res_id, doc_id, **params)
assert (update_res["code"] == RetCode.SUCCESS and
update_res["message"] == "Success" and update_res["data"]["parser_id"] == "laws")
def test_update_document_with_updating_its_enable_value_with_success(self):
"""
Test the updating of a document's enable value with success.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_update_document_with_updating_its_enable_value_with_success")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# update file
params = {
"enable": "0"
}
update_res = ragflow.update_file(created_res_id, doc_id, **params)
assert (update_res["code"] == RetCode.SUCCESS and
update_res["message"] == "Success" and update_res["data"]["status"] == "0")
def test_update_document_with_updating_illegal_parameter(self):
"""
Test the updating of a document's illegal parameter.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_update_document_with_updating_illegal_parameter")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# update file
params = {
"illegal_parameter": "0"
}
update_res = ragflow.update_file(created_res_id, doc_id, **params)
assert (update_res["code"] == RetCode.ARGUMENT_ERROR and
update_res["message"] == "illegal_parameter is an illegal parameter.")
def test_update_document_with_giving_its_name_value(self):
"""
Test the updating of a document's name without its name value.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_update_document_with_updating_its_name_with_success")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# update file
params = {
"name": ""
}
update_res = ragflow.update_file(created_res_id, doc_id, **params)
assert (update_res["code"] == RetCode.DATA_ERROR and
update_res["message"] == "There is no new name.")
def test_update_document_with_giving_illegal_value_for_enable(self):
"""
Test the updating of a document's with giving illegal enable's value.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_update_document_with_updating_its_name_with_success")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# update file
params = {
"enable": "?"
}
update_res = ragflow.update_file(created_res_id, doc_id, **params)
assert (update_res["code"] == RetCode.DATA_ERROR and
update_res["message"] == "Illegal value ? for 'enable' field.")
def test_update_document_with_giving_illegal_value_for_type(self):
"""
Test the updating of a document's with giving illegal type's value.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_update_document_with_updating_its_name_with_success")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# update file
params = {
"template_type": "?"
}
update_res = ragflow.update_file(created_res_id, doc_id, **params)
assert (update_res["code"] == RetCode.DATA_ERROR and
update_res["message"] == "Illegal value ? for 'template_type' field.")
# ----------------------------download a file-----------------------------------------------------
def test_download_nonexistent_document(self):
"""
Test downloading a document which does not exist.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_download_nonexistent_document")
created_res_id = created_res["data"]["dataset_id"]
res = ragflow.download_file(created_res_id, "imagination")
assert res["code"] == RetCode.ARGUMENT_ERROR and res["message"] == f"This document 'imagination' cannot be found!"
def test_download_document_in_nonexistent_dataset(self):
"""
Test downloading a document whose dataset is nonexistent.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_download_nonexistent_document")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# download file
res = ragflow.download_file("imagination", doc_id)
assert res["code"] == RetCode.DATA_ERROR and res["message"] == f"This dataset 'imagination' cannot be found!"
def test_download_document_with_success(self):
"""
Test the downloading of a document with success.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_download_nonexistent_document")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# download file
with open("test_data/test.txt", "rb") as file:
binary_data = file.read()
res = ragflow.download_file(created_res_id, doc_id)
assert res["code"] == RetCode.SUCCESS and res["data"] == binary_data
def test_download_an_empty_document(self):
"""
Test the downloading of an empty document.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_download_nonexistent_document")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/empty.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# download file
res = ragflow.download_file(created_res_id, doc_id)
assert res["code"] == RetCode.DATA_ERROR and res["message"] == "This file is empty."
# ----------------------------start parsing-----------------------------------------------------
def test_start_parsing_document_with_success(self):
"""
Test the parsing of a document with success.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_start_parsing_document_with_success")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/lol.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# parse file
res = ragflow.start_parsing_document(created_res_id, doc_id)
assert res["code"] == RetCode.SUCCESS and res["message"] == ""
def test_start_parsing_nonexistent_document(self):
"""
Test the parsing a document which does not exist.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_start_parsing_nonexistent_document")
created_res_id = created_res["data"]["dataset_id"]
res = ragflow.start_parsing_document(created_res_id, "imagination")
assert res["code"] == RetCode.ARGUMENT_ERROR and res["message"] == "This document 'imagination' cannot be found!"
def test_start_parsing_document_in_nonexistent_dataset(self):
"""
Test the parsing a document whose dataset is nonexistent.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_download_nonexistent_document")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# parse
res = ragflow.start_parsing_document("imagination", doc_id)
assert res["code"] == RetCode.DATA_ERROR and res["message"] == "This dataset 'imagination' cannot be found!"
def test_start_parsing_an_empty_document(self):
"""
Test the parsing of an empty document.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_download_nonexistent_document")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/empty.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
res = ragflow.start_parsing_document(created_res_id, doc_id)
assert res["code"] == RetCode.SUCCESS and res["message"] == "Empty data in the document: empty.txt; "
# ------------------------parsing multiple documents----------------------------
def test_start_parsing_documents_in_nonexistent_dataset(self):
"""
Test the parsing documents whose dataset is nonexistent.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_download_nonexistent_document")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# parse
res = ragflow.start_parsing_documents("imagination")
assert res["code"] == RetCode.DATA_ERROR and res["message"] == "This dataset 'imagination' cannot be found!"
def test_start_parsing_multiple_documents(self):
"""
Test the parsing documents with a success.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset(" test_start_parsing_multiple_documents")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
ragflow.upload_local_file(created_res_id, file_paths)
res = ragflow.start_parsing_documents(created_res_id)
assert res["code"] == RetCode.SUCCESS and res["data"] is True and res["message"] == ""
def test_start_parsing_multiple_documents_with_one_empty_file(self):
"""
Test the parsing documents, one of which is empty.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset(" test_start_parsing_multiple_documents")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt", "test_data/empty.txt"]
ragflow.upload_local_file(created_res_id, file_paths)
res = ragflow.start_parsing_documents(created_res_id)
assert res["code"] == RetCode.SUCCESS and res["message"] == "Empty data in the document: empty.txt; "
def test_start_parsing_multiple_specific_documents(self):
"""
Test the parsing documents whose document ids are specified.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset(" test_start_parsing_multiple_documents")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"]
doc_ids = []
for d in data:
doc_ids.append(d["id"])
res = ragflow.start_parsing_documents(created_res_id, doc_ids)
assert res["code"] == RetCode.SUCCESS and res["message"] == ""
def test_start_re_parsing_multiple_specific_documents(self):
"""
Test the re-parsing documents.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset(" test_start_parsing_multiple_documents")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"]
doc_ids = []
for d in data:
doc_ids.append(d["id"])
res = ragflow.start_parsing_documents(created_res_id, doc_ids)
assert res["code"] == RetCode.SUCCESS and res["message"] == ""
# re-parse
res = ragflow.start_parsing_documents(created_res_id, doc_ids)
assert res["code"] == RetCode.SUCCESS and res["message"] == ""
def test_start_re_parsing_multiple_specific_documents_with_changing_parser_id(self):
"""
Test the re-parsing documents after changing the parser id.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset(" test_start_parsing_multiple_documents")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"]
doc_ids = []
for d in data:
doc_ids.append(d["id"])
res = ragflow.start_parsing_documents(created_res_id, doc_ids)
assert res["code"] == RetCode.SUCCESS and res["message"] == ""
# general -> laws
params = {
"template_type": "laws"
}
ragflow.update_file(created_res_id, doc_ids[0], **params)
# re-parse
res = ragflow.start_parsing_documents(created_res_id, doc_ids)
assert res["code"] == RetCode.SUCCESS and res["message"] == ""
def test_start_re_parsing_multiple_specific_documents_with_changing_illegal_parser_id(self):
"""
Test the re-parsing documents after changing an illegal parser id.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset(" test_start_parsing_multiple_documents")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"]
doc_ids = []
for d in data:
doc_ids.append(d["id"])
res = ragflow.start_parsing_documents(created_res_id, doc_ids)
assert res["code"] == RetCode.SUCCESS and res["message"] == ""
# general -> illegal
params = {
"template_type": "illegal"
}
res = ragflow.update_file(created_res_id, doc_ids[0], **params)
assert res["code"] == RetCode.DATA_ERROR and res["message"] == "Illegal value illegal for 'template_type' field."
# re-parse
res = ragflow.start_parsing_documents(created_res_id, doc_ids)
assert res["code"] == RetCode.SUCCESS and res["message"] == ""
def test_start_parsing_multiple_specific_documents_with_changing_illegal_parser_id(self):
"""
Test the parsing documents after changing an illegal parser id.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset(" test_start_parsing_multiple_documents")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"]
doc_ids = []
for d in data:
doc_ids.append(d["id"])
# general -> illegal
params = {
"template_type": "illegal"
}
res = ragflow.update_file(created_res_id, doc_ids[0], **params)
assert res["code"] == RetCode.DATA_ERROR and res["message"] == "Illegal value illegal for 'template_type' field."
# re-parse
res = ragflow.start_parsing_documents(created_res_id, doc_ids)
assert res["code"] == RetCode.SUCCESS and res["message"] == ""
def test_start_parsing_multiple_documents_in_the_dataset_whose_parser_id_is_illegal(self):
"""
Test the parsing documents whose dataset's parser id is illegal.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_start_parsing_multiple_documents_in_the_dataset_whose_parser_id_is_illegal")
created_res_id = created_res["data"]["dataset_id"]
# update the parser id
params = {
"chunk_method": "illegal"
}
res = ragflow.update_dataset("test_start_parsing_multiple_documents_in_the_dataset_whose_parser_id_is_illegal", **params)
assert res["code"] == RetCode.DATA_ERROR and res["message"] == "Illegal value illegal for 'chunk_method' field."
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"]
doc_ids = []
for d in data:
doc_ids.append(d["id"])
# parse
res = ragflow.start_parsing_documents(created_res_id, doc_ids)
assert res["code"] == RetCode.SUCCESS and res["message"] == ""
# ----------------------------stop parsing-----------------------------------------------------
def test_stop_parsing_document_with_success(self):
"""
Test the stopping parsing of a document with success.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_start_parsing_document_with_success")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/lol.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# parse file
res = ragflow.start_parsing_document(created_res_id, doc_id)
assert res["code"] == RetCode.SUCCESS and res["message"] == ""
res = ragflow.stop_parsing_document(created_res_id, doc_id)
assert res["code"] == RetCode.SUCCESS and res["message"] == ""
def test_stop_parsing_nonexistent_document(self):
"""
Test the stopping parsing a document which does not exist.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_start_parsing_nonexistent_document")
created_res_id = created_res["data"]["dataset_id"]
res = ragflow.stop_parsing_document(created_res_id, "imagination.txt")
assert res["code"] == RetCode.ARGUMENT_ERROR and res["message"] == "This document 'imagination.txt' cannot be found!"
def test_stop_parsing_document_in_nonexistent_dataset(self):
"""
Test the stopping parsing a document whose dataset is nonexistent.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_download_nonexistent_document")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# parse
res = ragflow.stop_parsing_document("imagination", doc_id)
assert res["code"] == RetCode.DATA_ERROR and res["message"] == "This dataset 'imagination' cannot be found!"
# ------------------------stop parsing multiple documents----------------------------
def test_stop_parsing_documents_in_nonexistent_dataset(self):
"""
Test the stopping parsing documents whose dataset is nonexistent.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_download_nonexistent_document")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# parse
res = ragflow.stop_parsing_documents("imagination")
assert res["code"] == RetCode.DATA_ERROR and res["message"] == "This dataset 'imagination' cannot be found!"
def test_stop_parsing_multiple_documents(self):
"""
Test the stopping parsing documents with a success.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_start_parsing_multiple_documents")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
ragflow.upload_local_file(created_res_id, file_paths)
res = ragflow.start_parsing_documents(created_res_id)
assert res["code"] == RetCode.SUCCESS and res["data"] is True and res["message"] == ""
res = ragflow.stop_parsing_documents(created_res_id)
assert res["code"] == RetCode.SUCCESS and res["data"] is True and res["message"] == ""
def test_stop_parsing_multiple_documents_with_one_empty_file(self):
"""
Test the stopping parsing documents, one of which is empty.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset(" test_start_parsing_multiple_documents")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt", "test_data/empty.txt"]
ragflow.upload_local_file(created_res_id, file_paths)
res = ragflow.start_parsing_documents(created_res_id)
assert res["code"] == RetCode.SUCCESS and res["message"] == "Empty data in the document: empty.txt; "
res = ragflow.stop_parsing_documents(created_res_id)
assert res["code"] == RetCode.SUCCESS and res["data"] is True and res["message"] == ""
def test_stop_parsing_multiple_specific_documents(self):
"""
Test the stopping parsing documents whose document ids are specified.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset(" test_start_parsing_multiple_documents")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt", "test_data/test1.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"]
doc_ids = []
for d in data:
doc_ids.append(d["id"])
res = ragflow.start_parsing_documents(created_res_id, doc_ids)
assert res["code"] == RetCode.SUCCESS and res["message"] == ""
res = ragflow.stop_parsing_documents(created_res_id, doc_ids)
assert res["code"] == RetCode.SUCCESS and res["data"] is True and res["message"] == ""
# ----------------------------show the status of the file-----------------------------------------------------
def test_show_status_with_success(self):
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_show_status_with_success")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/lol.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# parse file
res = ragflow.start_parsing_document(created_res_id, doc_id)
assert res["code"] == RetCode.SUCCESS and res["message"] == ""
# show status
status_res = ragflow.show_parsing_status(created_res_id, doc_id)
assert status_res["code"] == RetCode.SUCCESS and status_res["data"]["status"] == "RUNNING"
def test_show_status_nonexistent_document(self):
"""
Test showing the status of a document which does not exist.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_show_status_nonexistent_document")
created_res_id = created_res["data"]["dataset_id"]
res = ragflow.show_parsing_status(created_res_id, "imagination")
assert res["code"] == RetCode.DATA_ERROR and res["message"] == "This document: 'imagination' is not a valid document."
def test_show_status_document_in_nonexistent_dataset(self):
"""
Test showing the status of a document whose dataset is nonexistent.
"""
# create a dataset
ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
created_res = ragflow.create_dataset("test_show_status_document_in_nonexistent_dataset")
created_res_id = created_res["data"]["dataset_id"]
# upload files
file_paths = ["test_data/test.txt"]
uploading_res = ragflow.upload_local_file(created_res_id, file_paths)
# get the doc_id
data = uploading_res["data"][0]
doc_id = data["id"]
# parse
res = ragflow.show_parsing_status("imagination", doc_id)
assert res["code"] == RetCode.DATA_ERROR and res["message"] == "This dataset: 'imagination' cannot be found!"
# ----------------------------list the chunks of the file-----------------------------------------------------
# ----------------------------delete the chunk-----------------------------------------------------
# ----------------------------edit the status of the chunk-----------------------------------------------------
# ----------------------------insert a new chunk-----------------------------------------------------
# ----------------------------get a specific chunk-----------------------------------------------------
# ----------------------------retrieval test-----------------------------------------------------
|