Spaces:
Running
Running
File size: 88,867 Bytes
e91ac58 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 |
from dataclasses import dataclass
from langchain_core.pydantic_v1 import BaseModel, Field, create_model
import yaml, json
# catalog = PromptCatalog(OCR="Sample OCR text", domain_knowledge_example="Sample domain knowledge", similarity="0.9")
### Required if you want to use the Pydantic JSON parser for langchain
class SLTPvA(BaseModel):
catalogNumber: str = Field(description="Barcode identifier, typically a number with at least 6 digits, but fewer than 30 digits.")
order: str = Field(description="The full scientific name of the order in which the taxon is classified. Order must be capitalized.")
family: str = Field(description="The full scientific name of the family in which the taxon is classified. Family must be capitalized.")
scientificName: str = Field(description="The scientific name of the taxon including genus, specific epithet, and any lower classifications.")
scientificNameAuthorship: str = Field(description="The authorship information for the scientificName formatted according to the conventions of the applicable Darwin Core nomenclaturalCode.")
genus: str = Field(description="Taxonomic determination to genus. Genus must be capitalized. If genus is not present use the taxonomic family name followed by the word 'indet'.")
subgenus: str = Field(description="The full scientific name of the subgenus in which the taxon is classified. Values should include the genus to avoid homonym confusion.")
specificEpithet: str = Field(description="The name of the first or species epithet of the scientificName. Only include the species epithet.")
infraspecificEpithet: str = Field(description="The name of the lowest or terminal infraspecific epithet of the scientificName, excluding any rank designation.")
identifiedBy: str = Field(description="A comma separated list of names of people, groups, or organizations who assigned the taxon to the subject organism. This is not the specimen collector.")
recordedBy: str = Field(description="A comma separated list of names of people, groups, or organizations responsible for observing, recording, collecting, or presenting the original specimen. The primary collector or observer should be listed first.")
recordNumber: str = Field(description="An identifier given to the occurrence at the time it was recorded. Often serves as a link between str = Field notes and an occurrence record, such as a specimen collector's number.")
verbatimEventDate: str = Field(description="The verbatim original representation of the date and time information for when the specimen was collected. Date of collection exactly as it appears on the label. Do not change the format or correct typos.")
eventDate:str = Field(description=" Date the specimen was collected formatted as year-month-day. If specific components of the date are unknown, they should be replaced with zeros. Examples '0000-00-00' if the entire date is unknown, 'YYYY-00-00' if only the year is known, and 'YYYY-MM-00' if year and month are known but day is not.")
habitat: str = Field(description="A category or description of the habitat in which the specimen collection event occurred.")
occurrenceRemarks: str = Field(description="Text describing the specimen's geographic location. Text describing the appearance of the specimen. A statement about the presence or absence of a taxon at a the collection location. Text describing the significance of the specimen, such as a specific expedition or notable collection. Description of plant features such as leaf shape, size, color, stem texture, height, flower structure, scent, fruit or seed characteristics, root system type, overall growth habit and form, any notable aroma or secretions, presence of hairs or bristles, and any other distinguishing morphological or physiological characteristics.")
country: str = Field(description="The name of the country or major administrative unit in which the specimen was originally collected.")
stateProvince: str = Field(description="The name of the next smaller administrative region than country (state, province, canton, department, region, etc.) in which the specimen was originally collected.")
county:str = Field(description=" The full, unabbreviated name of the next smaller administrative region than stateProvince (county, shire, department, parish etc.) in which the specimen was originally collected.")
municipality: str = Field(description="The full, unabbreviated name of the next smaller administrative region than county (city, municipality, etc.) in which the specimen was originally collected.")
locality: str = Field(description="Description of geographic location, landscape, landmarks, regional features, nearby places, or any contextual information aiding in pinpointing the exact origin or location of the specimen.")
degreeOfEstablishment: str = Field(description="Cultivated plants are intentionally grown by humans. In text descriptions, look for planting dates, garden locations, ornamental, cultivar names, garden, or farm to indicate cultivated plant. Other possible designiations include - unknown, native, captive, cultivated, released, failing, casual, reproducing, established, colonising, invasive, widespreadInvasive. Based on the OCR text, assign the most suitable designiation and use the term unknown as the default designiation.")
decimalLatitude: str = Field(description="Latitude decimal coordinate. Correct and convert the verbatim location coordinates to conform with the decimal degrees GPS coordinate format.")
decimalLongitude: str = Field(description="Longitude decimal coordinate. Correct and convert the verbatim location coordinates to conform with the decimal degrees GPS coordinate format.")
verbatimCoordinates: str = Field(description="Verbatim location coordinates as they appear on the label. Do not convert formats. Possible coordinate types include [Lat, Long, UTM, TRS].")
minimumElevationInMeters: str = Field(description="Minimum elevation or altitude in meters. Only if units are explicit then convert from feet ('ft' or 'ft.'' or 'feet') to meters ('m' or 'm.' or 'meters'). Round to integer.")
maximumElevationInMeters: str = Field(description="Maximum elevation or altitude in meters. If only one elevation is present, then max_elevation should be set to the null_value. Only if units are explicit then convert from feet ('ft' or 'ft.' or 'feet') to meters ('m' or 'm.' or 'meters'). Round to integer.")
@dataclass
class PromptCatalog:
domain_knowledge_example: str = ""
similarity: str = ""
OCR: str = ""
n_fields: int = 0
# def PROMPT_UMICH_skeleton_all_asia(self, OCR=None, domain_knowledge_example=None, similarity=None):
def prompt_v1_verbose(self, OCR=None, domain_knowledge_example=None, similarity=None):
self.OCR = OCR or self.OCR
self.domain_knowledge_example = domain_knowledge_example or self.domain_knowledge_example
self.similarity = similarity or self.similarity
self.n_fields = 22 or self.n_fields
set_rules = """
Please note that your task is to generate a dictionary, following the below rules:
1. Refactor the unstructured OCR text into a dictionary based on the reference dictionary structure (ref_dict).
2. Each field of OCR corresponds to a column of the ref_dict. You should correctly map the values from OCR to the respective fields in ref_dict.
3. If the OCR is mostly empty and contains substantially less text than the ref_dict examples, then only return "None".
4. If there is a field in the ref_dict that does not have a corresponding value in the OCR text, fill it based on your knowledge but don't generate new information.
5. Do not use any text from the ref_dict values in the new dict, but you must use the headers from ref_dict.
6. Duplicate dictionary fields are not allowed.
7. Only return the new dictionary. You should not explain your answer.
8. Your output should be a Python dictionary represented as a JSON string.
"""
umich_all_asia_rules = """{
"Catalog Number": {
"format": "[Catalog Number]",
"null_value": "",
"description": "The barcode identifier, typically a number with at least 6 digits, but fewer than 30 digits"
},
"Genus": {
"format": "[Genus] or '[Family] indet' if no genus",
"null_value": "",
"description": "Taxonomic determination to genus, do capitalize genus"
},
"Species": {
"format": "[species] or 'indet' if no species",
"null_value": "",
"description": "Taxonomic determination to species, do not capitalize species"
},
"subspecies": {
"format": "[subspecies]",
"null_value": "",
"description": "Taxonomic determination to subspecies (subsp.)"
},
"variety": {
"format": "[variety]",
"null_value": "",
"description": "Taxonomic determination to variety (var)"
},
"forma": {
"format": "[form]",
"null_value": "",
"description": "Taxonomic determination to form (f.)"
},
"Country": {
"format": "[Country]",
"null_value": "",
"description": "Country that corresponds to the current geographic location of collection; capitalize first letter of each word; use the entire location name even if an abbreviation is given"
},
"State": {
"format": "[Adm. Division 1]",
"null_value": "",
"description": "Administrative division 1 that corresponds to the current geographic location of collection; capitalize first letter of each word"
},
"County": {
"format": "[Adm. Division 2]",
"null_value": "",
"description": "Administrative division 2 that corresponds to the current geographic location of collection; capitalize first letter of each word"
},
"Locality Name": {
"format": "verbatim, if no geographic info: 'no data provided on label of catalog no: [######]', or if illegible: 'locality present but illegible/not translated for catalog no: #######', or if no named locality: 'no named locality for catalog no: #######'",
"description": "Description of geographic location or landscape"
},
"Min Elevation": {
"format": "elevation integer",
"null_value": "",
"description": "Elevation or altitude in meters, convert from feet to meters if 'm' or 'meters' is not in the text and round to integer, default field for elevation if a range is not given"
},
"Max Elevation": {
"format": "elevation integer",
"null_value": "",
"description": "Elevation or altitude in meters, convert from feet to meters if 'm' or 'meters' is not in the text and round to integer, maximum elevation if there are two elevations listed but '' otherwise"
},
"Elevation Units": {
"format": "m",
"null_value": "",
"description": "'m' only if an elevation is present"
},
"Verbatim Coordinates": {
"format": "[Lat, Long | UTM | TRS]",
"null_value": "",
"description": "Verbatim coordinates as they appear on the label, fix typos to match standardized GPS coordinate format"
},
"Datum": {
"format": "[WGS84, NAD23 etc.]",
"null_value": "",
"description": "GPS Datum of coordinates on label; empty string "" if GPS coordinates are not in OCR"
},
"Cultivated": {
"format": "yes",
"null_value": "",
"description": "Indicates if specimen was grown in cultivation"
},
"Habitat": {
"format": "verbatim",
"null_value": "",
"description": "Description of habitat or location where specimen was collected, ignore descriptions of the plant itself"
},
"Collectors": {
"format": "[Collector]",
"null_value": "not present",
"description": "Full name of person (i.e., agent) who collected the specimen; if more than one person then separate the names with commas"
},
"Collector Number": {
"format": "[Collector No.]",
"null_value": "s.n.",
"description": "Sequential number assigned to collection, associated with the collector"
},
"Verbatim Date": {
"format": "verbatim",
"null_value": "s.d.",
"description": "Date of collection exactly as it appears on the label"
},
"Date": {
"format": "[yyyy-mm-dd]",
"null_value": "",
"description": "Date of collection formatted as year, month, and day; zeros may be used for unknown values i.e., 0000-00-00 if no date, YYYY-00-00 if only year, YYYY-MM-00 if no day"
},
"End Date": {
"format": "[yyyy-mm-dd]",
"null_value": "",
"description": "If date range is listed, later date of collection range"
}
}"""
structure = """{"Dictionary":
{
"Catalog Number": [Catalog Number],
"Genus": [Genus],
"Species": [species],
"subspecies": [subspecies],
"variety": [variety],
"forma": [forma],
"Country": [Country],
"State": [State],
"County": [County],
"Locality Name": [Locality Name],
"Min Elevation": [Min Elevation],
"Max Elevation": [Max Elevation],
"Elevation Units": [Elevation Units],
"Verbatim Coordinates": [Verbatim Coordinates],
"Datum": [Datum],
"Cultivated": [Cultivated],
"Habitat": [Habitat],
"Collectors": [Collectors],
"Collector Number": [Collector Number],
"Verbatim Date": [Verbatim Date],
"Date": [Date],
"End Date": [End Date]
},
"SpeciesName": {"taxonomy": [Genus_species]}}"""
prompt = f"""I'm providing you with a set of rules, an unstructured OCR text, and a reference dictionary (domain knowledge). Your task is to convert the OCR text into a structured dictionary that matches the structure of the reference dictionary. Please follow the rules strictly.
The rules are as follows:
{set_rules}
The unstructured OCR text is:
{self.OCR}
The reference dictionary, which provides an example of the output structure and has an embedding distance of {self.similarity} to the OCR, is:
{self.domain_knowledge_example}
Some dictionary fields have special requirements. These requirements specify the format for each field, and are given below:
{umich_all_asia_rules}
Please refactor the OCR text into a dictionary, following the rules and the reference structure:
{structure}
"""
xlsx_headers = ["Catalog Number","Genus","Species","subspecies","variety","forma","Country","State","County","Locality Name","Min Elevation","Max Elevation","Elevation Units","Verbatim Coordinates","Datum","Cultivated","Habitat","Collectors","Collector Number","Verbatim Date","Date","End Date"]
return prompt, self.n_fields, xlsx_headers
def prompt_v1_verbose_noDomainKnowledge(self, OCR=None):
self.OCR = OCR or self.OCR
self.n_fields = 22 or self.n_fields
set_rules = """
Please note that your task is to generate a dictionary, following the below rules:
1. Refactor the unstructured OCR text into a dictionary based on the reference dictionary structure (ref_dict).
2. Each field of OCR corresponds to a column of the ref_dict. You should correctly map the values from OCR to the respective fields in ref_dict.
3. If the OCR is mostly empty and contains substantially less text than the ref_dict examples, then only return "None".
4. If there is a field in the ref_dict that does not have a corresponding value in the OCR text, fill it based on your knowledge but don't generate new information.
5. Do not use any text from the ref_dict values in the new dict, but you must use the headers from ref_dict.
6. Duplicate dictionary fields are not allowed.
7. Only return the new dictionary. You should not explain your answer.
8. Your output should be a Python dictionary represented as a JSON string.
"""
umich_all_asia_rules = """{
"Catalog Number": {
"format": "[Catalog Number]",
"null_value": "",
"description": "The barcode identifier, typically a number with at least 6 digits, but fewer than 30 digits"
},
"Genus": {
"format": "[Genus] or '[Family] indet' if no genus",
"null_value": "",
"description": "Taxonomic determination to genus, do capitalize genus"
},
"Species": {
"format": "[species] or 'indet' if no species",
"null_value": "",
"description": "Taxonomic determination to species, do not capitalize species"
},
"subspecies": {
"format": "[subspecies]",
"null_value": "",
"description": "Taxonomic determination to subspecies (subsp.)"
},
"variety": {
"format": "[variety]",
"null_value": "",
"description": "Taxonomic determination to variety (var)"
},
"forma": {
"format": "[form]",
"null_value": "",
"description": "Taxonomic determination to form (f.)"
},
"Country": {
"format": "[Country]",
"null_value": "",
"description": "Country that corresponds to the current geographic location of collection; capitalize first letter of each word; use the entire location name even if an abbreviation is given"
},
"State": {
"format": "[Adm. Division 1]",
"null_value": "",
"description": "Administrative division 1 that corresponds to the current geographic location of collection; capitalize first letter of each word"
},
"County": {
"format": "[Adm. Division 2]",
"null_value": "",
"description": "Administrative division 2 that corresponds to the current geographic location of collection; capitalize first letter of each word"
},
"Locality Name": {
"format": "verbatim, if no geographic info: 'no data provided on label of catalog no: [######]', or if illegible: 'locality present but illegible/not translated for catalog no: #######', or if no named locality: 'no named locality for catalog no: #######'",
"description": "Description of geographic location or landscape"
},
"Min Elevation": {
"format": "elevation integer",
"null_value": "",
"description": "Elevation or altitude in meters, convert from feet to meters if 'm' or 'meters' is not in the text and round to integer, default field for elevation if a range is not given"
},
"Max Elevation": {
"format": "elevation integer",
"null_value": "",
"description": "Elevation or altitude in meters, convert from feet to meters if 'm' or 'meters' is not in the text and round to integer, maximum elevation if there are two elevations listed but '' otherwise"
},
"Elevation Units": {
"format": "m",
"null_value": "",
"description": "'m' only if an elevation is present"
},
"Verbatim Coordinates": {
"format": "[Lat, Long | UTM | TRS]",
"null_value": "",
"description": "Verbatim coordinates as they appear on the label, fix typos to match standardized GPS coordinate format"
},
"Datum": {
"format": "[WGS84, NAD23 etc.]",
"null_value": "",
"description": "GPS Datum of coordinates on label; empty string "" if GPS coordinates are not in OCR"
},
"Cultivated": {
"format": "yes",
"null_value": "",
"description": "Indicates if specimen was grown in cultivation"
},
"Habitat": {
"format": "verbatim",
"null_value": "",
"description": "Description of habitat or location where specimen was collected, ignore descriptions of the plant itself"
},
"Collectors": {
"format": "[Collector]",
"null_value": "not present",
"description": "Full name of person (i.e., agent) who collected the specimen; if more than one person then separate the names with commas"
},
"Collector Number": {
"format": "[Collector No.]",
"null_value": "s.n.",
"description": "Sequential number assigned to collection, associated with the collector"
},
"Verbatim Date": {
"format": "verbatim",
"null_value": "s.d.",
"description": "Date of collection exactly as it appears on the label"
},
"Date": {
"format": "[yyyy-mm-dd]",
"null_value": "",
"description": "Date of collection formatted as year, month, and day; zeros may be used for unknown values i.e., 0000-00-00 if no date, YYYY-00-00 if only year, YYYY-MM-00 if no day"
},
"End Date": {
"format": "[yyyy-mm-dd]",
"null_value": "",
"description": "If date range is listed, later date of collection range"
}
}"""
structure = """{"Dictionary":
{
"Catalog Number": [Catalog Number],
"Genus": [Genus],
"Species": [species],
"subspecies": [subspecies],
"variety": [variety],
"forma": [forma],
"Country": [Country],
"State": [State],
"County": [County],
"Locality Name": [Locality Name],
"Min Elevation": [Min Elevation],
"Max Elevation": [Max Elevation],
"Elevation Units": [Elevation Units],
"Verbatim Coordinates": [Verbatim Coordinates],
"Datum": [Datum],
"Cultivated": [Cultivated],
"Habitat": [Habitat],
"Collectors": [Collectors],
"Collector Number": [Collector Number],
"Verbatim Date": [Verbatim Date],
"Date": [Date],
"End Date": [End Date]
},
"SpeciesName": {"taxonomy": [Genus_species]}}"""
prompt = f"""I'm providing you with a set of rules, an unstructured OCR text, and a reference dictionary (domain knowledge). Your task is to convert the OCR text into a structured dictionary that matches the structure of the reference dictionary. Please follow the rules strictly.
The rules are as follows:
{set_rules}
The unstructured OCR text is:
{self.OCR}
Some dictionary fields have special requirements. These requirements specify the format for each field, and are given below:
{umich_all_asia_rules}
Please refactor the OCR text into a dictionary, following the rules and the reference structure:
{structure}
"""
xlsx_headers = ["Catalog Number","Genus","Species","subspecies","variety","forma","Country","State","County","Locality Name","Min Elevation","Max Elevation","Elevation Units","Verbatim Coordinates","Datum","Cultivated","Habitat","Collectors","Collector Number","Verbatim Date","Date","End Date"]
return prompt, self.n_fields, xlsx_headers
def prompt_v2_json_rules(self, OCR=None):
self.OCR = OCR or self.OCR
self.n_fields = 26 or self.n_fields
set_rules = """
1. Refactor the unstructured OCR text into a dictionary based on the JSON structure outlined below.
2. You should map the unstructured OCR text to the appropriate JSON key and then populate the field based on its rules.
3. Some JSON key fields are permitted to remain empty if the corresponding information is not found in the unstructured OCR text.
4. Ignore any information in the OCR text that doesn't fit into the defined JSON structure.
5. Duplicate dictionary fields are not allowed.
6. Ensure that all JSON keys are in lowercase.
7. Ensure that new JSON field values follow sentence case capitalization.
7. Ensure all key-value pairs in the JSON dictionary strictly adhere to the format and data types specified in the template.
8. Ensure the output JSON string is valid JSON format. It should not have trailing commas or unquoted keys.
9. Only return a JSON dictionary represented as a string. You should not explain your answer.
"""
dictionary_field_format_descriptions = """
The next section of instructions outlines how to format the JSON dictionary. The keys are the same as those of the final formatted JSON object.
For each key there is a format requirement that specifies how to transcribe the information for that key.
The possible formatting options are:
1. "verbatim transcription" - field is populated with verbatim text from the unformatted OCR.
2. "spell check transcription" - field is populated with spelling corrected text from the unformatted OCR.
3. "boolean yes no" - field is populated with only yes or no.
4. "integer" - field is populated with only an integer.
5. "[list]" - field is populated from one of the values in the list.
6. "yyyy-mm-dd" - field is populated with a date in the format year-month-day.
The desired null value is also given. Populate the field with the null value of the information for that key is not present in the unformatted OCR text.
"""
json_template_rules = """
{"Dictionary":{
"catalog_number": {
"format": "verbatim transcription",
"null_value": "",
"description": "The barcode identifier, typically a number with at least 6 digits, but fewer than 30 digits."
},
"genus": {
"format": "verbatim transcription",
"null_value": "",
"description": "Taxonomic determination to genus. Genus must be capitalized. If genus is not present use the taxonomic family name followed by the word 'indet'."
},
"species": {
"format": "verbatim transcription",
"null_value": "",
"description": "Taxonomic determination to species, do not capitalize species."
},
"subspecies": {
"format": "verbatim transcription",
"null_value": "",
"description": "Taxonomic determination to subspecies (subsp.)."
},
"variety": {
"format": "verbatim transcription",
"null_value": "",
"description": "Taxonomic determination to variety (var)."
},
"forma": {
"format": "verbatim transcription",
"null_value": "",
"description": "Taxonomic determination to form (f.)."
},
"country": {
"format": "spell check transcription",
"null_value": "",
"description": "Country that corresponds to the current geographic location of collection. Capitalize first letter of each word. If abbreviation is given populate field with the full spelling of the country's name."
},
"state": {
"format": "spell check transcription",
"null_value": "",
"description": "Administrative division 1 that corresponds to the current geographic location of collection. Capitalize first letter of each word. Administrative division 1 is equivalent to a U.S. State."
},
"county": {
"format": "spell check transcription",
"null_value": "",
"description": "Administrative division 2 that corresponds to the current geographic location of collection; capitalize first letter of each word. Administrative division 2 is equivalent to a U.S. county, parish, borough."
},
"locality_name": {
"format": "verbatim transcription",
"null_value": "",
"description": "Description of geographic location, landscape, landmarks, regional features, nearby places, or any contextual information aiding in pinpointing the exact origin or site of the specimen."
},
"min_elevation": {
"format": "integer",
"null_value": "",
"description": "Minimum elevation or altitude in meters. Only if units are explicit then convert from feet ('ft' or 'ft.' or 'feet') to meters ('m' or 'm.' or 'meters'). Round to integer."
},
"max_elevation": {
"format": "integer",
"null_value": "",
"description": "Maximum elevation or altitude in meters. If only one elevation is present, then max_elevation should be set to the null_value. Only if units are explicit then convert from feet ('ft' or 'ft.' or 'feet') to meters ('m' or 'm.' or 'meters'). Round to integer."
},
"elevation_units": {
"format": "spell check transcription",
"null_value": "",
"description": "Elevation units must be meters. If min_elevation field is populated, then elevation_units: 'm'. Otherwise elevation_units: ''."
},
"verbatim_coordinates": {
"format": "verbatim transcription",
"null_value": "",
"description": "Verbatim location coordinates as they appear on the label. Do not convert formats. Possible coordinate types are one of [Lat, Long, UTM, TRS]."
},
"decimal_coordinates": {
"format": "spell check transcription",
"null_value": "",
"description": "Correct and convert the verbatim location coordinates to conform with the decimal degrees GPS coordinate format."
},
"datum": {
"format": "[WGS84, WGS72, WGS66, WGS60, NAD83, NAD27, OSGB36, ETRS89, ED50, GDA94, JGD2011, Tokyo97, KGD2002, TWD67, TWD97, BJS54, XAS80, GCJ-02, BD-09, PZ-90.11, GTRF, CGCS2000, ITRF88, ITRF89, ITRF90, ITRF91, ITRF92, ITRF93, ITRF94, ITRF96, ITRF97, ITRF2000, ITRF2005, ITRF2008, ITRF2014, Hong Kong Principal Datum, SAD69]",
"null_value": "",
"description": "Datum of location coordinates. Possible values are include in the format list. Leave field blank if unclear."
},
"cultivated": {
"format": "boolean yes no",
"null_value": "",
"description": "Cultivated plants are intentionally grown by humans. In text descriptions, look for planting dates, garden locations, ornamental, cultivar names, garden, or farm to indicate cultivated plant."
},
"habitat": {
"format": "verbatim transcription",
"null_value": "",
"description": "Description of a plant's habitat or the location where the specimen was collected. Ignore descriptions of the plant itself."
},
"plant_description": {
"format": "verbatim transcription",
"null_value": "",
"description": "Description of plant features such as leaf shape, size, color, stem texture, height, flower structure, scent, fruit or seed characteristics, root system type, overall growth habit and form, any notable aroma or secretions, presence of hairs or bristles, and any other distinguishing morphological or physiological characteristics."
},
"collectors": {
"format": "verbatim transcription",
"null_value": "not present",
"description": "Full name(s) of the individual(s) responsible for collecting the specimen. When multiple collectors are involved, their names should be separated by commas."
},
"collector_number": {
"format": "verbatim transcription",
"null_value": "s.n.",
"description": "Unique identifier or number that denotes the specific collecting event and associated with the collector."
},
"determined_by": {
"format": "verbatim transcription",
"null_value": "",
"description": "Full name of the individual responsible for determining the taxanomic name of the specimen. Sometimes the name will be near to the characters 'det' to denote determination. This name may be isolated from other names in the unformatted OCR text."
},
"multiple_names": {
"format": "boolean yes no",
"null_value": "",
"description": "Indicate whether multiple people or collector names are present in the unformatted OCR text. If you see more than one person's name the value is 'yes'; otherwise the value is 'no'."
},
"verbatim_date": {
"format": "verbatim transcription",
"null_value": "s.d.",
"description": "Date of collection exactly as it appears on the label. Do not change the format or correct typos."
},
"date": {
"format": "yyyy-mm-dd",
"null_value": "",
"description": "Date the specimen was collected formatted as year-month-day. If specific components of the date are unknown, they should be replaced with zeros. Examples: '0000-00-00' if the entire date is unknown, 'YYYY-00-00' if only the year is known, and 'YYYY-MM-00' if year and month are known but day is not."
},
"end_date": {
"format": "yyyy-mm-dd",
"null_value": "",
"description": "If a date range is provided, this represents the later or ending date of the collection period, formatted as year-month-day. If specific components of the date are unknown, they should be replaced with zeros. Examples: '0000-00-00' if the entire end date is unknown, 'YYYY-00-00' if only the year of the end date is known, and 'YYYY-MM-00' if year and month of the end date are known but the day is not."
},
},
"SpeciesName": {
"taxonomy": [Genus_species]}
}"""
structure = """{"Dictionary":
{
"catalog_number": "",
"genus": "",
"species": "",
"subspecies": "",
"variety": "",
"forma": "",
"country": "",
"state": "",
"county": "",
"locality_name": "",
"min_elevation": "",
"max_elevation": "",
"elevation_units": "",
"verbatim_coordinates": "",
"decimal_coordinates": "",
"datum": "",
"cultivated": "",
"habitat": "",
"plant_description": "",
"collectors": "",
"collector_number": "",
"determined_by": "",
"multiple_names": "",
"verbatim_date":"" ,
"date": "",
"end_date": ""
},
"SpeciesName": {"taxonomy": ""}}"""
prompt = f"""Please help me complete this text parsing task given the following rules and unstructured OCR text. Your task is to refactor the OCR text into a structured JSON dictionary that matches the structure specified in the following rules. Please follow the rules strictly.
The rules are:
{set_rules}
The unstructured OCR text is:
{self.OCR}
{dictionary_field_format_descriptions}
This is the JSON template that includes instructions for each key:
{json_template_rules}
Please populate the following JSON dictionary based on the rules and the unformatted OCR text:
{structure}
"""
xlsx_headers = ["catalog_number","genus","species","subspecies","variety","forma","country","state","county","locality_name","min_elevation","max_elevation","elevation_units","verbatim_coordinates","decimal_coordinates","datum","cultivated","habitat","plant_description","collectors","collector_number","determined_by","multiple_names","verbatim_date","date","end_date"]
return prompt, self.n_fields, xlsx_headers
#############################################################################################
#############################################################################################
#############################################################################################
#############################################################################################
# These are for dynamically creating your own prompts with n-columns
def prompt_SLTP(self, rules_config_path, OCR=None, is_palm=False):
self.OCR = OCR
self.rules_config_path = rules_config_path
self.rules_config = self.load_rules_config()
self.instructions = self.rules_config['instructions']
self.json_formatting_instructions = self.rules_config['json_formatting_instructions']
self.rules_list = self.rules_config['rules']
self.n_fields = len(self.rules_config['rules'])
# Set the rules for processing OCR into JSON format
self.rules = self.create_rules(is_palm)
self.structure, self.dictionary_structure = self.create_structure(is_palm)
''' between instructions and json_formatting_instructions. Made the prompt too long. Better performance without it
The unstructured OCR text is:
{self.OCR}
'''
if is_palm:
prompt = f"""Please help me complete this text parsing task given the following rules and unstructured OCR text. Your task is to refactor the OCR text into a structured JSON dictionary that matches the structure specified in the following rules. Please follow the rules strictly.
The rules are:
{self.instructions}
{self.json_formatting_instructions}
This is the JSON template that includes instructions for each key:
{self.rules}
The unstructured OCR text is:
{self.OCR}
Please populate the following JSON dictionary based on the rules and the unformatted OCR text:
{self.structure}
{self.structure}
{self.structure}
"""
else:
prompt = f"""Please help me complete this text parsing task given the following rules and unstructured OCR text. Your task is to refactor the OCR text into a structured JSON dictionary that matches the structure specified in the following rules. Please follow the rules strictly.
The rules are:
{self.instructions}
{self.json_formatting_instructions}
This is the JSON template that includes instructions for each key:
{self.rules}
The unstructured OCR text is:
{self.OCR}
Please populate the following JSON dictionary based on the rules and the unformatted OCR text:
{self.structure}
"""
# xlsx_headers = self.generate_xlsx_headers(is_palm)
# return prompt, self.PromptJSONModel, self.n_fields, xlsx_headers
return prompt, self.dictionary_structure
def load_rules_config(self):
with open(self.rules_config_path, 'r') as stream:
try:
return yaml.safe_load(stream)
except yaml.YAMLError as exc:
print(exc)
return None
def create_rules(self, is_palm=False):
dictionary_structure = {key: value for key, value in self.rules_list.items()}
# Convert the structure to a JSON string without indentation
structure_json_str = json.dumps(dictionary_structure, sort_keys=False)
return structure_json_str
def create_structure(self, is_palm=False):
# Create fields for the Pydantic model dynamically
fields = {key: (str, Field(default=value, description=value)) for key, value in self.rules_list.items()}
# Dynamically create the Pydantic model
DynamicJSONParsingModel = create_model('SLTPvA', **fields)
DynamicJSONParsingModel_use = DynamicJSONParsingModel()
# Define the structure for the "Dictionary" section
dictionary_fields = {key: (str, Field(default='', description="")) for key in self.rules_list.keys()}
# Dynamically create the "Dictionary" Pydantic model
PromptJSONModel = create_model('PromptJSONModel', **dictionary_fields)
# Convert the model to JSON string (for demonstration)
dictionary_structure = PromptJSONModel().dict()
structure_json_str = json.dumps(dictionary_structure, sort_keys=False, indent=4)
return structure_json_str, dictionary_structure
def generate_xlsx_headers(self, is_palm):
# Extract headers from the 'Dictionary' keys in the JSON template rules
if is_palm:
xlsx_headers = list(self.rules_list.keys())
return xlsx_headers
else:
xlsx_headers = list(self.rules_list.keys())
return xlsx_headers
def prompt_v2_custom_redo(self, incorrect_json, is_palm):
# Load the existing rules and structure
self.rules_config = self.load_rules_config()
# self.rules = self.create_rules(is_palm)
self.structure, self.dictionary_structure = self.create_structure(is_palm)
# Generate the prompt using the loaded rules and structure
if is_palm:
prompt = f"""The incorrectly formatted JSON dictionary below is not valid. It contains an error that prevents it from loading with the Python command json.loads().
The incorrectly formatted JSON dictionary below is the literal string returned by a previous function and the error may be caused by markdown formatting.
You need to return coorect JSON for the following dictionary. Most likely, a quotation mark inside of a field value has not been escaped properly with a backslash.
Given the input, please generate a JSON response. Please note that the response should not contain any special characters, including quotation marks (single ' or double \"), within the JSON values.
Escape all JSON control characters that appear in input including ampersand (&) and other control characters.
Ensure all key-value pairs in the JSON dictionary strictly adhere to the format and data types specified in the template.
Ensure the output JSON string is valid JSON format. It should not have trailing commas or unquoted keys.
The incorrectly formatted JSON dictionary: {incorrect_json}
The output JSON structure: {self.structure}
The output JSON structure: {self.structure}
The output JSON structure: {self.structure}
Please reformat the incorrectly formatted JSON dictionary given the output JSON structure: """
else:
prompt = f"""The incorrectly formatted JSON dictionary below is not valid. It contains an error that prevents it from loading with the Python command json.loads().
The incorrectly formatted JSON dictionary below is the literal string returned by a previous function and the error may be caused by markdown formatting.
You need to return coorect JSON for the following dictionary. Most likely, a quotation mark inside of a field value has not been escaped properly with a backslash.
Given the input, please generate a JSON response. Please note that the response should not contain any special characters, including quotation marks (single ' or double \"), within the JSON values.
Escape all JSON control characters that appear in input including ampersand (&) and other control characters.
Ensure all key-value pairs in the JSON dictionary strictly adhere to the format and data types specified in the template.
Ensure the output JSON string is valid JSON format. It should not have trailing commas or unquoted keys.
The incorrectly formatted JSON dictionary: {incorrect_json}
The output JSON structure: {self.structure}
Please reformat the incorrectly formatted JSON dictionary given the output JSON structure: """
return prompt
#############################################################################################
#############################################################################################
#############################################################################################
#############################################################################################
def prompt_gpt_redo_v1(self, incorrect_json):
structure = """Below is the correct JSON formatting. Modify the text to conform to the following format, fixing the incorrect JSON:
{"Dictionary":
{
"Catalog Number": [Catalog Number],
"Genus": [Genus],
"Species": [species],
"subspecies": [subspecies],
"variety": [variety],
"forma": [forma],
"Country": [Country],
"State": [State],
"County": [County],
"Locality Name": [Locality Name],
"Min Elevation": [Min Elevation],
"Max Elevation": [Max Elevation],
"Elevation Units": [Elevation Units],
"Verbatim Coordinates": [Verbatim Coordinates],
"Datum": [Datum],
"Cultivated": [Cultivated],
"Habitat": [Habitat],
"Collectors": [Collectors],
"Collector Number": [Collector Number],
"Verbatim Date": [Verbatim Date],
"Date": [Date],
"End Date": [End Date]
},
"SpeciesName": {"taxonomy": [Genus_species]}}"""
prompt = f"""This text is supposed to be JSON, but it contains an error that prevents it from loading with the Python command json.loads().
You need to return coorect JSON for the following dictionary. Most likely, a quotation mark inside of a field value has not been escaped properly with a backslash.
Given the input, please generate a JSON response. Please note that the response should not contain any special characters, including quotation marks (single ' or double \"), within the JSON values.
Escape all JSON control characters that appear in input including ampersand (&) and other control characters.
Ensure all key-value pairs in the JSON dictionary strictly adhere to the format and data types specified in the template.
Ensure the output JSON string is valid JSON format. It should not have trailing commas or unquoted keys.
The incorrectly formatted JSON dictionary: {incorrect_json}
The output JSON structure: {structure}
The refactored JSON disctionary: """
return prompt
def prompt_gpt_redo_v2(self, incorrect_json):
structure = """
{"Dictionary":{
"catalog_number": "",
"genus": "",
"species": "".
"subspecies": "",
"variety": "",
"forma":"",
"country": "",
"state": "",
"county": "",
"locality_name": "",
"min_elevation": "",
"max_elevation": "",
"elevation_units": "',
"verbatim_coordinates": "",
"decimal_coordinates": "",
"datum": "",
"cultivated": "",
"habitat": "",
"plant_description": "",
"collectors": "",
"collector_number": "",
"determined_by": "",
"multiple_names": "',
"verbatim_date": "",
"date": "",
"end_date": "",
},
"SpeciesName": {"taxonomy": [Genus_species]}}"""
prompt = f"""This text is supposed to be JSON, but it contains an error that prevents it from loading with the Python command json.loads().
You need to return coorect JSON for the following dictionary. Most likely, a quotation mark inside of a field value has not been escaped properly with a backslash.
Given the input, please generate a JSON response. Please note that the response should not contain any special characters, including quotation marks (single ' or double \"), within the JSON values.
Escape all JSON control characters that appear in input including ampersand (&) and other control characters.
Ensure all key-value pairs in the JSON dictionary strictly adhere to the format and data types specified in the template.
Ensure the output JSON string is valid JSON format. It should not have trailing commas or unquoted keys.
The incorrectly formatted JSON dictionary: {incorrect_json}
The output JSON structure: {structure}
The refactored JSON disctionary: """
return prompt
#####################################################################################################################################
#####################################################################################################################################
def prompt_v1_palm2(self, in_list, out_list, OCR=None):
self.OCR = OCR or self.OCR
set_rules = """1. Your job is to return a new dict based on the structure of the reference dict ref_dict and these are your rules.
2. You must look at ref_dict and refactor the new text called OCR to match the same formatting.
3. OCR contains unstructured text inside of [], use your knowledge to put the OCR text into the correct ref_dict column.
4. If OCR is mostly empty and contains substantially less text than the ref_dict examples, then only return "None" and skip all other steps.
5. If there is a field that does not have a direct proxy in the OCR text, you can fill it in based on your knowledge, but you cannot generate new information.
6. Never put text from the ref_dict values into the new dict, but you must use the headers from ref_dict.
7. There cannot be duplicate dictionary fields.
8. Only return the new dict, do not explain your answer.
9. Do not include quotation marks in content, only use quotation marks to represent values in dictionaries.
10. For GPS coordinates only use Decimal Degrees (D.D°)
11. "Given the input text, please generate a JSON response. Please note that the response should not contain any special characters, including quotation marks (single ' or double \"), within the JSON values."""
umich_all_asia_rules = """
"Catalog Number" - {"format": "[barcode]", "null_value": "", "description": the barcode identifier, typically a number with at least 6 digits, but fewer than 30 digits}
"Genus" - {"format": "[Genus]" or "[Family] indet" if no genus", "null_value": "", "description": taxonomic determination to genus, do captalize genus}
"Species"- {"format": "[species]" or "indet" if no species, "null_value": "", "description": taxonomic determination to species, do not captalize species}
"subspecies" - {"format": "[subspecies]", "null_value": "", "description": taxonomic determination to subspecies (subsp.)}
"variety" - {"format": "[variety]", "null_value": "", "description": taxonomic determination to variety (var)}
"forma" - {"format": "[form]", "null_value": "", "description": taxonomic determination to form (f.)}
"Country" - {"format": "[Country]", "null_value": "no data", "description": Country that corresponds to the current geographic location of collection; capitalize first letter of each word; use the entire location name even if an abreviation is given}
"State" - {"format": "[Adm. Division 1]", "null_value": "no data", "description": Administrative division 1 that corresponds to the current geographic location of collection; capitalize first letter of each word}
"County" - {"format": "[Adm. Division 2]", "null_value": "no data", "description": Administrative division 2 that corresponds to the current geographic location of collection; capitalize first letter of each word}
"Locality Name" - {"format": "verbatim", if no geographic info: "no data provided on label of catalog no: [######]", or if illegible: "locality present but illegible/not translated for catalog no: #######", or if no named locality: "no named locality for catalog no: #######", "description": "Description of geographic location or landscape"}
"Min Elevation" - {format: "elevation integer", "null_value": "","description": Elevation or altitude in meters, convert from feet to meters if 'm' or 'meters' is not in the text and round to integer, default field for elevation if a range is not given}
"Max Elevation" - {format: "elevation integer", "null_value": "","description": Elevation or altitude in meters, convert from feet to meters if 'm' or 'meters' is not in the text and round to integer, maximum elevation if there are two elevations listed but '' otherwise}
"Elevation Units" - {format: "m", "null_value": "","description": "m" only if an elevation is present}
"Verbatim Coordinates" - {"format": "[Lat, Long | UTM | TRS]", "null_value": "", "description": Convert coordinates to Decimal Degrees (D.D°) format, do not use Minutes, Seconds or quotation marks}
"Datum" - {"format": "[WGS84, NAD23 etc.]", "null_value": "not present", "description": Datum of coordinates on label; "" is GPS coordinates are not in OCR}
"Cultivated" - {"format": "yes", "null_value": "", "description": Indicates if specimen was grown in cultivation}
"Habitat" - {"format": "verbatim", "null_value": "", "description": Description of habitat or location where specimen was collected, ignore descriptions of the plant itself}
"Collectors" - {"format": "[Collector]", "null_value": "not present", "description": Full name of person (i.e., agent) who collected the specimen; if more than one person then separate the names with commas}
"Collector Number" - {"format": "[Collector No.]", "null_value": "s.n.", "description": Sequential number assigned to collection, associated with the collector}
"Verbatim Date" - {"format": "verbatim", "null_value": "s.d.", "description": Date of collection exactly as it appears on the label}
"Date" - {"format": "[yyyy-mm-dd]", "null_value": "", "description": Date of collection formatted as year, month, and day; zeros may be used for unknown values i.e. 0000-00-00 if no date, YYYY-00-00 if only year, YYYY-MM-00 if no day}
"End Date" - {"format": "[yyyy-mm-dd]", "null_value": "", "description": If date range is listed, later date of collection range}
"""
prompt = f"""Given the following set of rules:
set_rules = {set_rules}
Some dict fields have special requirements listed below. First is the column header. After the - is the format. Do not include the instructions with your response:
requirements = {umich_all_asia_rules}
Given the input, please generate a JSON response. Please note that the response should not contain any special characters, including quotation marks (single ' or double \"), within the JSON values.
input: {in_list[0]}
output: {out_list[0]}
input: {in_list[1]}
output: {out_list[1]}
input: {in_list[2]}
output: {out_list[2]}
input: {self.OCR}
output:"""
return prompt
def prompt_v1_palm2_noDomainKnowledge(self, OCR=None):
self.OCR = OCR or self.OCR
set_rules = """1. Your job is to return a new dict based on the structure of the reference dict ref_dict and these are your rules.
2. You must look at ref_dict and refactor the new text called OCR to match the same formatting.
3. OCR contains unstructured text inside of [], use your knowledge to put the OCR text into the correct ref_dict column.
4. If OCR is mostly empty and contains substantially less text than the ref_dict examples, then only return "None" and skip all other steps.
5. If there is a field that does not have a direct proxy in the OCR text, you can fill it in based on your knowledge, but you cannot generate new information.
6. Never put text from the ref_dict values into the new dict, but you must use the headers from ref_dict.
7. There cannot be duplicate dictionary fields.
8. Only return the new dict, do not explain your answer.
9. Do not include quotation marks in content, only use quotation marks to represent values in dictionaries.
10. For GPS coordinates only use Decimal Degrees (D.D°)
11. "Given the input text, please generate a JSON response. Please note that the response should not contain any special characters, including quotation marks (single ' or double \"), within the JSON values."""
umich_all_asia_rules = """
"Catalog Number" - {"format": "barcode", "null_value": "", "description": the barcode identifier, typically a number with at least 6 digits, but fewer than 30 digits}
"Genus" - {"format": "Genus" or "Family indet" if no genus", "null_value": "", "description": taxonomic determination to genus, do captalize genus}
"Species"- {"format": "species" or "indet" if no species, "null_value": "", "description": taxonomic determination to species, do not captalize species}
"subspecies" - {"format": "subspecies", "null_value": "", "description": taxonomic determination to subspecies (subsp.)}
"variety" - {"format": "variety", "null_value": "", "description": taxonomic determination to variety (var)}
"forma" - {"format": "form", "null_value": "", "description": taxonomic determination to form (f.)}
"Country" - {"format": "Country", "null_value": "no data", "description": Country that corresponds to the current geographic location of collection; capitalize first letter of each word; use the entire location name even if an abreviation is given}
"State" - {"format": "Adm. Division 1", "null_value": "no data", "description": Administrative division 1 that corresponds to the current geographic location of collection; capitalize first letter of each word}
"County" - {"format": "Adm. Division 2", "null_value": "no data", "description": Administrative division 2 that corresponds to the current geographic location of collection; capitalize first letter of each word}
"Locality Name" - {"format": "verbatim", if no geographic info: "no data provided on label of catalog no: ######", or if illegible: "locality present but illegible/not translated for catalog no: #######", or if no named locality: "no named locality for catalog no: #######", "description": "Description of geographic location or landscape"}
"Min Elevation" - {format: "elevation integer", "null_value": "","description": Elevation or altitude in meters, convert from feet to meters if 'm' or 'meters' is not in the text and round to integer, default field for elevation if a range is not given}
"Max Elevation" - {format: "elevation integer", "null_value": "","description": Elevation or altitude in meters, convert from feet to meters if 'm' or 'meters' is not in the text and round to integer, maximum elevation if there are two elevations listed but '' otherwise}
"Elevation Units" - {format: "m", "null_value": "","description": "m" only if an elevation is present}
"Verbatim Coordinates" - {"format": "Lat, Long, UTM, TRS", "null_value": "", "description": Convert coordinates to Decimal Degrees (D.D°) format, do not use Minutes, Seconds or quotation marks}
"Datum" - {"format": "WGS84, NAD23 etc.", "null_value": "not present", "description": Datum of coordinates on label; "" is GPS coordinates are not in OCR}
"Cultivated" - {"format": "yes", "null_value": "", "description": Indicates if specimen was grown in cultivation}
"Habitat" - {"format": "verbatim", "null_value": "", "description": Description of habitat or location where specimen was collected, ignore descriptions of the plant itself}
"Collectors" - {"format": "Collector", "null_value": "not present", "description": Full name of person (i.e., agent) who collected the specimen; if more than one person then separate the names with commas}
"Collector Number" - {"format": "Collector No.", "null_value": "s.n.", "description": Sequential number assigned to collection, associated with the collector}
"Verbatim Date" - {"format": "verbatim", "null_value": "s.d.", "description": Date of collection exactly as it appears on the label}
"Date" - {"format": "yyyy-mm-dd", "null_value": "", "description": Date of collection formatted as year, month, and day; zeros may be used for unknown values i.e. 0000-00-00 if no date, YYYY-00-00 if only year, YYYY-MM-00 if no day}
"End Date" - {"format": "yyyy-mm-dd", "null_value": "", "description": If date range is listed, later date of collection range}
"""
structure = """{
"Catalog Number": "",
"Genus": "",
"Species": "",
"subspecies": "",
"variety": "",
"forma": "",
"Country": "",
"State": "",
"County": "",
"Locality Name": "",
"Min Elevation": "",
"Max Elevation": "",
"Elevation Units": "",
"Verbatim Coordinates": "",
"Datum": "",
"Cultivated": "",
"Habitat": "",
"Collectors": "",
"Collector Number": "",
"Verbatim Date": "",
"Date": "",
"End Date": "",
}"""
# structure = """{
# "Catalog Number": [Catalog Number],
# "Genus": [Genus],
# "Species": [species],
# "subspecies": [subspecies],
# "variety": [variety],
# "forma": [forma],
# "Country": [Country],
# "State": [State],
# "County": [County],
# "Locality Name": [Locality Name],
# "Min Elevation": [Min Elevation],
# "Max Elevation": [Max Elevation],
# "Elevation Units": [Elevation Units],
# "Verbatim Coordinates": [Verbatim Coordinates],
# "Datum": [Datum],
# "Cultivated": [Cultivated],
# "Habitat": [Habitat],
# "Collectors": [Collectors],
# "Collector Number": [Collector Number],
# "Verbatim Date": [Verbatim Date],
# "Date": [Date],
# "End Date": [End Date]
# }"""
prompt = f"""Given the following set of rules:
set_rules = {set_rules}
Some dict fields have special requirements listed below. First is the column header. After the - is the format. Do not include the instructions with your response:
requirements = {umich_all_asia_rules}
Given the input, please generate a JSON response. Please note that the response should not contain any special characters, including quotation marks (single ' or double \"), within the JSON values.
The input unformatted OCR text: {self.OCR}
The output JSON structure: {structure}
The output JSON structure: {structure}
The output JSON structure: {structure}
The refactored JSON disctionary:"""
return prompt
def prompt_v2_palm2(self, OCR=None):
self.OCR = OCR or self.OCR
self.n_fields = 26 or self.n_fields
set_rules = """
1. Refactor the unstructured OCR text into a dictionary based on the JSON structure outlined below.
2. You should map the unstructured OCR text to the appropriate JSON key and then populate the field based on its rules.
3. Some JSON key fields are permitted to remain empty if the corresponding information is not found in the unstructured OCR text.
4. Ignore any information in the OCR text that doesn't fit into the defined JSON structure.
5. Duplicate dictionary fields are not allowed.
6. Ensure that all JSON keys are in lowercase.
7. Ensure that new JSON field values follow sentence case capitalization.
8. Ensure all key-value pairs in the JSON dictionary strictly adhere to the format and data types specified in the template.
9. Ensure the output JSON string is valid JSON format. It should not have trailing commas or unquoted keys.
10. Only return a JSON dictionary represented as a string. You should not explain your answer.
"""
dictionary_field_format_descriptions = """
The next section of instructions outlines how to format the JSON dictionary. The keys are the same as those of the final formatted JSON object.
For each key there is a format requirement that specifies how to transcribe the information for that key.
The possible formatting options are:
1. "verbatim transcription" - field is populated with verbatim text from the unformatted OCR.
2. "spell check transcription" - field is populated with spelling corrected text from the unformatted OCR.
3. "boolean yes no" - field is populated with only yes or no.
4. "integer" - field is populated with only an integer.
5. "[list]" - field is populated from one of the values in the list.
6. "yyyy-mm-dd" - field is populated with a date in the format year-month-day.
The desired null value is also given. Populate the field with the null value of the information for that key is not present in the unformatted OCR text.
"""
json_template_rules = """
{
"catalog_number": {
"format": "verbatim transcription",
"null_value": "",
"description": "The barcode identifier, typically a number with at least 6 digits, but fewer than 30 digits."
},
"genus": {
"format": "verbatim transcription",
"null_value": "",
"description": "Taxonomic determination to genus. Genus must be capitalized. If genus is not present use the taxonomic family name followed by the word 'indet'."
},
"species": {
"format": "verbatim transcription",
"null_value": "",
"description": "Taxonomic determination to species, do not capitalize species."
},
"subspecies": {
"format": "verbatim transcription",
"null_value": "",
"description": "Taxonomic determination to subspecies (subsp.)."
},
"variety": {
"format": "verbatim transcription",
"null_value": "",
"description": "Taxonomic determination to variety (var)."
},
"forma": {
"format": "verbatim transcription",
"null_value": "",
"description": "Taxonomic determination to form (f.)."
},
"country": {
"format": "spell check transcription",
"null_value": "",
"description": "Country that corresponds to the current geographic location of collection. Capitalize first letter of each word. If abbreviation is given populate field with the full spelling of the country's name. Use sentence-case to capitalize proper nouns."
},
"state": {
"format": "spell check transcription",
"null_value": "",
"description": "Administrative division 1 that corresponds to the current geographic location of collection. Capitalize first letter of each word. Administrative division 1 is equivalent to a U.S. State. Use sentence-case to capitalize proper nouns."
},
"county": {
"format": "spell check transcription",
"null_value": "",
"description": "Administrative division 2 that corresponds to the current geographic location of collection; capitalize first letter of each word. Administrative division 2 is equivalent to a U.S. county, parish, borough. Use sentence-case to capitalize proper nouns."
},
"locality_name": {
"format": "verbatim transcription",
"null_value": "",
"description": "Description of geographic location, landscape, landmarks, regional features, nearby places, or any contextual information aiding in pinpointing the exact origin or site of the specimen. Use sentence-case to capitalize proper nouns."
},
"min_elevation": {
"format": "integer",
"null_value": "",
"description": "Minimum elevation or altitude in meters. Only if units are explicit then convert from feet ('ft' or 'ft.' or 'feet') to meters ('m' or 'm.' or 'meters'). Round to integer."
},
"max_elevation": {
"format": "integer",
"null_value": "",
"description": "Maximum elevation or altitude in meters. If only one elevation is present, then max_elevation should be set to the null_value. Only if units are explicit then convert from feet ('ft' or 'ft.' or 'feet') to meters ('m' or 'm.' or 'meters'). Round to integer."
},
"elevation_units": {
"format": "spell check transcription",
"null_value": "",
"description": "Elevation units must be meters. If min_elevation field is populated, then elevation_units: 'm'. Otherwise elevation_units: ''"
},
"verbatim_coordinates": {
"format": "verbatim transcription",
"null_value": "",
"description": "Verbatim location coordinates as they appear on the label. Do not convert formats. Possible coordinate types are one of [Lat, Long, UTM, TRS]."
},
"decimal_coordinates": {
"format": "spell check transcription",
"null_value": "",
"description": "Correct and convert the verbatim location coordinates to conform with the decimal degrees GPS coordinate format."
},
"datum": {
"format": "[WGS84, WGS72, WGS66, WGS60, NAD83, NAD27, OSGB36, ETRS89, ED50, GDA94, JGD2011, Tokyo97, KGD2002, TWD67, TWD97, BJS54, XAS80, GCJ-02, BD-09, PZ-90.11, GTRF, CGCS2000, ITRF88, ITRF89, ITRF90, ITRF91, ITRF92, ITRF93, ITRF94, ITRF96, ITRF97, ITRF2000, ITRF2005, ITRF2008, ITRF2014, Hong Kong Principal Datum, SAD69]",
"null_value": "",
"description": "Datum of location coordinates. Possible values are include in the format list. Leave field blank if unclear."
},
"cultivated": {
"format": "boolean yes no",
"null_value": "",
"description": "Cultivated plants are intentionally grown by humans. In text descriptions, look for planting dates, garden locations, ornamental, cultivar names, garden, or farm to indicate cultivated plant."
},
"habitat": {
"format": "verbatim transcription",
"null_value": "",
"description": "Description of a plant's habitat or the location where the specimen was collected. Ignore descriptions of the plant itself. Use sentence-case to capitalize proper nouns."
},
"plant_description": {
"format": "verbatim transcription",
"null_value": "",
"description": "Description of plant features such as leaf shape, size, color, stem texture, height, flower structure, scent, fruit or seed characteristics, root system type, overall growth habit and form, any notable aroma or secretions, presence of hairs or bristles, and any other distinguishing morphological or physiological characteristics. Use sentence-case to capitalize proper nouns."
},
"collectors": {
"format": "verbatim transcription",
"null_value": "not present",
"description": "Full name(s) of the individual(s) responsible for collecting the specimen. Use sentence-case to capitalize proper nouns. When multiple collectors are involved, their names should be separated by commas."
},
"collector_number": {
"format": "verbatim transcription",
"null_value": "s.n.",
"description": "Unique identifier or number that denotes the specific collecting event and associated with the collector."
},
"determined_by": {
"format": "verbatim transcription",
"null_value": "",
"description": "Full name of the individual responsible for determining the taxanomic name of the specimen. Use sentence-case to capitalize proper nouns. Sometimes the name will be near to the characters 'det' to denote determination. This name may be isolated from other names in the unformatted OCR text."
},
"multiple_names": {
"format": "boolean yes no",
"null_value": "",
"description": "Indicate whether multiple people or collector names are present in the unformatted OCR text. Use sentence-case to capitalize proper nouns. If you see more than one person's name the value is 'yes'; otherwise the value is 'no'."
},
"verbatim_date": {
"format": "verbatim transcription",
"null_value": "s.d.",
"description": "Date of collection exactly as it appears on the label. Do not change the format or correct typos."
},
"date": {
"format": "yyyy-mm-dd",
"null_value": "",
"description": "Date the specimen was collected formatted as year-month-day. If specific components of the date are unknown, they should be replaced with zeros. Examples: '0000-00-00' if the entire date is unknown, 'YYYY-00-00' if only the year is known, and 'YYYY-MM-00' if year and month are known but day is not."
},
"end_date": {
"format": "yyyy-mm-dd",
"null_value": "",
"description": "If a date range is provided, this represents the later or ending date of the collection period, formatted as year-month-day. If specific components of the date are unknown, they should be replaced with zeros. Examples: '0000-00-00' if the entire end date is unknown, 'YYYY-00-00' if only the year of the end date is known, and 'YYYY-MM-00' if year and month of the end date are known but the day is not."
},
}"""
structure = """{"catalog_number": "",
"genus": "",
"species": "".
"subspecies": "",
"variety": "",
"forma":"",
"country": "",
"state": "",
"county": "",
"locality_name": "",
"min_elevation": "",
"max_elevation": "",
"elevation_units": "',
"verbatim_coordinates": "",
"decimal_coordinates": "",
"datum": "",
"cultivated": "",
"habitat": "",
"plant_description": "",
"collectors": "",
"collector_number": "",
"determined_by": "",
"multiple_names": "',
"verbatim_date": "",
"date": "",
"end_date": "",
}"""
# structure = """{"catalog_number": [Catalog Number],
# "genus": [Genus],
# "species": [species],
# "subspecies": [subspecies],
# "variety": [variety],
# "forma": [forma],
# "country": [Country],
# "state": [State],
# "county": [County],
# "locality_name": [Locality Name],
# "min_elevation": [Min Elevation],
# "max_elevation": [Max Elevation],
# "elevation_units": [Elevation Units],
# "verbatim_coordinates": [Verbatim Coordinates],
# "decimal_coordinates": [Decimal Coordinates],
# "datum": [Datum],
# "cultivated": [boolean yes no],
# "habitat": [Habitat Description],
# "plant_description": [Plant Description],
# "collectors": [Name(s) of Collectors],
# "collector_number": [Collector Number],
# "determined_by": [Name(s) of Taxonomist],
# "multiple_names": [boolean yes no],
# "verbatim_date": [Verbatim Date],
# "date": [yyyy-mm-dd],
# "end_date": [yyyy-mm-dd],
# }"""
prompt = f"""Please help me complete this text parsing task given the following rules and unstructured OCR text. Your task is to refactor the OCR text into a structured JSON dictionary that matches the structure specified in the following rules. Please follow the rules strictly.
The rules are:
{set_rules}
The unstructured OCR text is:
{self.OCR}
{dictionary_field_format_descriptions}
This is the JSON template that includes instructions for each key:
{json_template_rules}
Please populate the following JSON dictionary based on the rules and the unformatted OCR text. The square brackets denote the locations that you should place the new structured text:
{structure}
{structure}
{structure}
"""
return prompt
def prompt_palm_redo_v1(self, incorrect_json):
structure = """{
"Catalog Number": [Catalog Number],
"Genus": [Genus],
"Species": [species],
"subspecies": [subspecies],
"variety": [variety],
"forma": [forma],
"Country": [Country],
"State": [State],
"County": [County],
"Locality Name": [Locality Name],
"Min Elevation": [Min Elevation],
"Max Elevation": [Max Elevation],
"Elevation Units": [Elevation Units],
"Verbatim Coordinates": [Verbatim Coordinates],
"Datum": [Datum],
"Cultivated": [Cultivated],
"Habitat": [Habitat],
"Collectors": [Collectors],
"Collector Number": [Collector Number],
"Verbatim Date": [Verbatim Date],
"Date": [Date],
"End Date": [End Date]
}"""
prompt = f"""This text is supposed to be JSON, but it contains an error that prevents it from loading with the Python command json.loads().
You need to return coorect JSON for the following dictionary. Most likely, a quotation mark inside of a field value has not been escaped properly with a backslash.
Given the input, please generate a JSON response. Please note that the response should not contain any special characters, including quotation marks (single ' or double \"), within the JSON values.
Escape all JSON control characters that appear in input including ampersand (&) and other control characters.
Ensure all key-value pairs in the JSON dictionary strictly adhere to the format and data types specified in the template.
Ensure the output JSON string is valid JSON format. It should not have trailing commas or unquoted keys.
The incorrectly formatted JSON dictionary: {incorrect_json}
The output JSON structure: {structure}
The output JSON structure: {structure}
The output JSON structure: {structure}
The refactored JSON disctionary: """
return prompt
def prompt_palm_redo_v2(self, incorrect_json):
structure = """{"catalog_number": "",
"genus": "",
"species": "".
"subspecies": "",
"variety": "",
"forma":"",
"country": "",
"state": "",
"county": "",
"locality_name": "",
"min_elevation": "",
"max_elevation": "",
"elevation_units": "',
"verbatim_coordinates": "",
"decimal_coordinates": "",
"datum": "",
"cultivated": "",
"habitat": "",
"plant_description": "",
"collectors": "",
"collector_number": "",
"determined_by": "",
"multiple_names": "',
"verbatim_date": "",
"date": "",
"end_date": "",
}"""
prompt = f"""This text is supposed to be JSON, but it contains an error that prevents it from loading with the Python command json.loads().
You need to return coorect JSON for the following dictionary. Most likely, a quotation mark inside of a field value has not been escaped properly with a backslash.
Given the input, please generate a JSON response. Please note that the response should not contain any special characters, including quotation marks (single ' or double \"), within the JSON values.
Escape all JSON control characters that appear in input including ampersand (&) and other control characters.
Ensure all key-value pairs in the JSON dictionary strictly adhere to the format and data types specified in the template.
Ensure the output JSON string is valid JSON format. It should not have trailing commas or unquoted keys.
The incorrectly formatted JSON dictionary: {incorrect_json}
The output JSON structure: {structure}
The output JSON structure: {structure}
The output JSON structure: {structure}
The refactored JSON disctionary: """
return prompt |