File size: 63,958 Bytes
aee77fd 75775c4 a6cf941 75775c4 d6f5eba aee77fd 75775c4 a6cf941 aee77fd 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 aee77fd 75775c4 a6cf941 75775c4 aee77fd 75775c4 a6cf941 75775c4 a6cf941 75775c4 aee77fd 75775c4 a6cf941 aee77fd 75775c4 aee77fd 75775c4 aee77fd 75775c4 a6cf941 75775c4 aee77fd 75775c4 d6f5eba 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 aee77fd a6cf941 75775c4 aee77fd 75775c4 993126d 75775c4 993126d 75775c4 a6cf941 75775c4 a6cf941 75775c4 aee77fd a6cf941 aee77fd d6f5eba aee77fd a6cf941 aee77fd d6f5eba a6cf941 d6f5eba a6cf941 aee77fd d6f5eba aee77fd 75775c4 a6cf941 d6f5eba 75775c4 aee77fd 75775c4 d6f5eba aee77fd d6f5eba a6cf941 d6f5eba a6cf941 d6f5eba 75775c4 d6f5eba 75775c4 d6f5eba a6cf941 d6f5eba a6cf941 d6f5eba aee77fd d6f5eba 75775c4 aee77fd a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 aee77fd 75775c4 d6f5eba aee77fd 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 2bc1f40 75775c4 a6cf941 75775c4 aee77fd a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 aee77fd 75775c4 aee77fd 75775c4 aee77fd 75775c4 aee77fd 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 aee77fd a6cf941 aee77fd 75775c4 a6cf941 d6f5eba 75775c4 a6cf941 75775c4 a6cf941 aee77fd 75775c4 aee77fd d6f5eba a6cf941 75775c4 d6f5eba 75775c4 a6cf941 d6f5eba a6cf941 d6f5eba a6cf941 d6f5eba 75775c4 aee77fd 75775c4 d6f5eba 75775c4 d6f5eba 75775c4 a6cf941 75775c4 d6f5eba 75775c4 a6cf941 d6f5eba a6cf941 d6f5eba a6cf941 75775c4 d6f5eba 75775c4 d6f5eba 75775c4 a6cf941 75775c4 d6f5eba 75775c4 d6f5eba 75775c4 d6f5eba 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 a6cf941 d6f5eba a6cf941 75775c4 d6f5eba 75775c4 d6f5eba 75775c4 d6f5eba a6cf941 75775c4 aee77fd 75775c4 d6f5eba a6cf941 75775c4 a6cf941 75775c4 a6cf941 75775c4 aee77fd 75775c4 aee77fd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 |
from openai import OpenAI
from pydantic import BaseModel
from typing import List, Optional
import gradio as gr
import os
import logging
from logging.handlers import RotatingFileHandler
import sys
from functools import lru_cache
from tenacity import (
retry,
stop_after_attempt,
wait_exponential,
retry_if_exception_type,
)
import hashlib
import genanki
import random
import json
import tempfile
from pathlib import Path
import pandas as pd
import requests
from bs4 import BeautifulSoup
class Step(BaseModel):
explanation: str
output: str
class Subtopics(BaseModel):
steps: List[Step]
result: List[str]
class Topics(BaseModel):
result: List[Subtopics]
class CardFront(BaseModel):
question: Optional[str] = None
class CardBack(BaseModel):
answer: Optional[str] = None
explanation: str
example: str
class Card(BaseModel):
front: CardFront
back: CardBack
metadata: Optional[dict] = None
card_type: str = "basic" # Add card_type, default to basic
class CardList(BaseModel):
topic: str
cards: List[Card]
class ConceptBreakdown(BaseModel):
main_concept: str
prerequisites: List[str]
learning_outcomes: List[str]
common_misconceptions: List[str]
difficulty_level: str # "beginner", "intermediate", "advanced"
class CardGeneration(BaseModel):
concept: str
thought_process: str
verification_steps: List[str]
card: Card
class LearningSequence(BaseModel):
topic: str
concepts: List[ConceptBreakdown]
cards: List[CardGeneration]
suggested_study_order: List[str]
review_recommendations: List[str]
def setup_logging():
"""Configure logging to both file and console"""
logger = logging.getLogger("ankigen")
logger.setLevel(logging.DEBUG)
# Create formatters
detailed_formatter = logging.Formatter(
"%(asctime)s - %(name)s - %(levelname)s - %(message)s"
)
simple_formatter = logging.Formatter("%(levelname)s: %(message)s")
# File handler (detailed logging)
file_handler = RotatingFileHandler(
"ankigen.log",
maxBytes=1024 * 1024, # 1MB
backupCount=5,
)
file_handler.setLevel(logging.DEBUG)
file_handler.setFormatter(detailed_formatter)
# Console handler (info and above)
console_handler = logging.StreamHandler(sys.stdout)
console_handler.setLevel(logging.INFO)
console_handler.setFormatter(simple_formatter)
# Add handlers to logger
logger.addHandler(file_handler)
logger.addHandler(console_handler)
return logger
# Initialize logger
logger = setup_logging()
# Replace the caching implementation with a proper cache dictionary
_response_cache = {} # Global cache dictionary
@lru_cache(maxsize=100)
def get_cached_response(cache_key: str):
"""Get response from cache"""
return _response_cache.get(cache_key)
def set_cached_response(cache_key: str, response):
"""Set response in cache"""
_response_cache[cache_key] = response
def create_cache_key(prompt: str, model: str) -> str:
"""Create a unique cache key for the API request"""
return hashlib.md5(f"{model}:{prompt}".encode()).hexdigest()
# Add retry decorator for API calls
@retry(
stop=stop_after_attempt(3),
wait=wait_exponential(multiplier=1, min=4, max=10),
retry=retry_if_exception_type(Exception),
before_sleep=lambda retry_state: logger.warning(
f"Retrying API call (attempt {retry_state.attempt_number})"
),
)
def structured_output_completion(
client, model, response_format, system_prompt, user_prompt
):
"""Make API call with retry logic and caching"""
cache_key = create_cache_key(f"{system_prompt}:{user_prompt}", model)
cached_response = get_cached_response(cache_key)
if cached_response is not None:
logger.info("Using cached response")
return cached_response
try:
logger.debug(f"Making API call with model {model}")
# Add JSON instruction to system prompt
system_prompt = f"{system_prompt}\nProvide your response as a JSON object matching the specified schema."
completion = client.chat.completions.create(
model=model,
messages=[
{"role": "system", "content": system_prompt.strip()},
{"role": "user", "content": user_prompt.strip()},
],
response_format={"type": "json_object"},
temperature=0.7,
)
if not hasattr(completion, "choices") or not completion.choices:
logger.warning("No choices returned in the completion.")
return None
first_choice = completion.choices[0]
if not hasattr(first_choice, "message"):
logger.warning("No message found in the first choice.")
return None
# Parse the JSON response
result = json.loads(first_choice.message.content)
# Cache the successful response
set_cached_response(cache_key, result)
return result
except Exception as e:
logger.error(f"API call failed: {str(e)}", exc_info=True)
raise
def fetch_webpage_text(url: str) -> str:
"""Fetches and extracts main text content from a URL."""
try:
logger.info(f"Fetching content from URL: {url}")
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
}
response = requests.get(url, headers=headers, timeout=15) # Added timeout
response.raise_for_status() # Raise HTTPError for bad responses (4xx or 5xx)
logger.debug(f"Parsing HTML content for {url}")
# Use lxml for speed if available, fallback to html.parser
try:
soup = BeautifulSoup(response.text, "lxml")
except ImportError:
logger.warning("lxml not found, using html.parser instead.")
soup = BeautifulSoup(response.text, "html.parser")
# Remove script and style elements
for script_or_style in soup(["script", "style"]):
script_or_style.extract()
# Attempt to find main content tags
main_content = soup.find("main")
if not main_content:
main_content = soup.find("article")
# If specific tags found, use their text, otherwise fallback to body
if main_content:
text = main_content.get_text()
logger.debug(f"Extracted text from <{main_content.name}> tag.")
else:
body = soup.find("body")
if body:
text = body.get_text()
logger.debug("Extracted text from <body> tag (fallback).")
else:
text = "" # No body tag found?
logger.warning(f"Could not find <body> tag in {url}")
# Break into lines and remove leading/trailing space on each
lines = (line.strip() for line in text.splitlines())
# Break multi-headlines into a line each
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
# Drop blank lines
text = "\n".join(chunk for chunk in chunks if chunk)
if not text:
logger.warning(f"Could not extract meaningful text from {url}")
raise ValueError("Could not extract text content from the URL.")
logger.info(
f"Successfully extracted text from {url} (Length: {len(text)} chars)"
)
return text
except requests.exceptions.RequestException as e:
logger.error(f"Network error fetching URL {url}: {e}")
raise ConnectionError(f"Could not fetch URL: {e}")
except Exception as e:
logger.error(f"Error processing URL {url}: {e}", exc_info=True)
# Re-raise specific internal errors or a general one
if isinstance(e, (ValueError, ConnectionError)):
raise e
else:
raise RuntimeError(
f"An unexpected error occurred while processing the URL: {e}"
)
def generate_cards_batch(
client, model, topic, num_cards, system_prompt, generate_cloze=False, batch_size=3
):
"""Generate a batch of cards for a topic, potentially including cloze deletions"""
cloze_instruction = ""
if generate_cloze:
cloze_instruction = """
Where appropriate, generate Cloze deletion cards.
- For Cloze cards, set "card_type" to "cloze".
- Format the question field using Anki's cloze syntax (e.g., "The capital of France is {{c1::Paris}}.").
- The "answer" field should contain the full, non-cloze text or specific context for the cloze.
- For standard question/answer cards, set "card_type" to "basic".
"""
cards_prompt = f"""
Generate {num_cards} flashcards for the topic: {topic}
{cloze_instruction}
Return your response as a JSON object with the following structure:
{{
"cards": [
{{
"card_type": "basic or cloze",
"front": {{
"question": "question text (potentially with {{c1::cloze syntax}})"
}},
"back": {{
"answer": "concise answer or full text for cloze",
"explanation": "detailed explanation",
"example": "practical example"
}},
"metadata": {{
"prerequisites": ["list", "of", "prerequisites"],
"learning_outcomes": ["list", "of", "outcomes"],
"misconceptions": ["list", "of", "misconceptions"],
"difficulty": "beginner/intermediate/advanced"
}}
}}
// ... more cards
]
}}
"""
try:
logger.info(
f"Generating card batch for {topic}, Cloze enabled: {generate_cloze}"
)
response = structured_output_completion(
client, model, {"type": "json_object"}, system_prompt, cards_prompt
)
if not response or "cards" not in response:
logger.error("Invalid cards response format")
raise ValueError("Failed to generate cards. Please try again.")
# Convert the JSON response into Card objects
cards = []
for card_data in response["cards"]:
# Ensure required fields are present before creating Card object
if "front" not in card_data or "back" not in card_data:
logger.warning(
f"Skipping card due to missing front/back data: {card_data}"
)
continue
if "question" not in card_data["front"]:
logger.warning(f"Skipping card due to missing question: {card_data}")
continue
if (
"answer" not in card_data["back"]
or "explanation" not in card_data["back"]
or "example" not in card_data["back"]
):
logger.warning(
f"Skipping card due to missing answer/explanation/example: {card_data}"
)
continue
card = Card(
card_type=card_data.get("card_type", "basic"),
front=CardFront(**card_data["front"]),
back=CardBack(**card_data["back"]),
metadata=card_data.get("metadata", {}),
)
cards.append(card)
return cards
except Exception as e:
logger.error(
f"Failed to generate cards batch for {topic}: {str(e)}", exc_info=True
)
raise
# Add near the top with other constants
AVAILABLE_MODELS = [
{
"value": "gpt-4.1", # Corrected model name
"label": "gpt-4.1 (Best Quality)", # Corrected label
"description": "Highest quality, slower generation", # Corrected description
},
{
"value": "gpt-4.1-nano",
"label": "gpt-4.1 Nano (Fast & Efficient)",
"description": "Optimized for speed and lower cost",
},
]
GENERATION_MODES = [
{
"value": "subject",
"label": "Single Subject",
"description": "Generate cards for a specific topic",
},
{
"value": "path",
"label": "Learning Path",
"description": "Break down a job description or learning goal into subjects",
},
]
def generate_cards(
api_key_input,
subject,
generation_mode,
source_text,
url_input,
model_name="gpt-4.1-nano",
topic_number=1,
cards_per_topic=2,
preference_prompt="assume I'm a beginner",
generate_cloze=False,
):
logger.info(f"Starting card generation in {generation_mode} mode")
logger.debug(
f"Parameters: mode={generation_mode}, topics={topic_number}, cards_per_topic={cards_per_topic}, cloze={generate_cloze}"
)
# --- Common Setup ---
if not api_key_input:
logger.warning("No API key provided")
raise gr.Error("OpenAI API key is required")
if not api_key_input.startswith("sk-"):
logger.warning("Invalid API key format")
raise gr.Error("Invalid API key format. OpenAI keys should start with 'sk-'")
# Moved client initialization up
try:
logger.debug("Initializing OpenAI client")
client = OpenAI(api_key=api_key_input)
except Exception as e:
logger.error(f"Failed to initialize OpenAI client: {str(e)}", exc_info=True)
raise gr.Error(f"Failed to initialize OpenAI client: {str(e)}")
model = model_name
flattened_data = []
total = 0
progress_tracker = gr.Progress(track_tqdm=True)
# ---------------------
try:
page_text_for_generation = "" # Initialize variable to hold text for AI
# --- Web Mode --- (Fetch text first)
if generation_mode == "web":
logger.info("Generation mode: Web")
if not url_input or not url_input.strip():
logger.warning("No URL provided for web generation mode.")
raise gr.Error("URL is required for 'From Web' mode.")
gr.Info(f"🕸️ Fetching content from {url_input}...")
try:
page_text_for_generation = fetch_webpage_text(url_input)
gr.Info(
f"✅ Successfully fetched text (approx. {len(page_text_for_generation)} chars). Starting AI generation..."
)
except (ConnectionError, ValueError, RuntimeError) as e:
logger.error(f"Failed to fetch or process URL {url_input}: {e}")
raise gr.Error(
f"Failed to get content from URL: {e}"
) # Display fetch error to user
except Exception as e: # Catch any other unexpected errors during fetch
logger.error(
f"Unexpected error fetching URL {url_input}: {e}", exc_info=True
)
raise gr.Error(f"An unexpected error occurred fetching the URL.")
# --- Text Mode --- (Use provided text)
elif generation_mode == "text":
logger.info("Generation mode: Text Input")
if not source_text or not source_text.strip():
logger.warning("No source text provided for text generation mode.")
raise gr.Error("Source text is required for 'From Text' mode.")
page_text_for_generation = source_text # Use the input text directly
gr.Info("🚀 Starting card generation from text...")
# --- Generation from Text/Web Content ---
if generation_mode == "text" or generation_mode == "web":
# Shared logic for generating cards from fetched/provided text
text_system_prompt = f"""
You are an expert educator specializing in extracting key information and creating flashcards from provided text.
Your goal is to generate clear, concise, and accurate flashcards based *only* on the text given by the user.
Focus on the most important concepts, definitions, facts, or processes mentioned.
Generate {cards_per_topic} cards.
Adhere to the user's learning preferences: {preference_prompt}
Use the specified JSON output format.
For explanations and examples:
- Keep explanations in plain text
- Format code examples with triple backticks (```)
- Separate conceptual examples from code examples
- Use clear, concise language
"""
json_structure_prompt = """
Return your response as a JSON object with the following structure:
{
"cards": [
{
"card_type": "basic or cloze",
"front": {
"question": "question text (potentially with {{c1::cloze syntax}})"
},
"back": {
"answer": "concise answer or full text for cloze",
"explanation": "detailed explanation",
"example": "practical example"
},
"metadata": {
"prerequisites": ["list", "of", "prerequisites"],
"learning_outcomes": ["list", "of", "outcomes"],
"misconceptions": ["list", "of", "misconceptions"],
"difficulty": "beginner/intermediate/advanced"
}
}
// ... more cards
]
}
"""
cloze_instruction = ""
if generate_cloze:
cloze_instruction = """
Where appropriate, generate Cloze deletion cards.
- For Cloze cards, set "card_type" to "cloze".
- Format the question field using Anki's cloze syntax (e.g., "The capital of France is {{{{c1::Paris}}}}.").
- The "answer" field should contain the full, non-cloze text or specific context for the cloze.
- For standard question/answer cards, set "card_type" to "basic".
"""
text_user_prompt = f"""
Generate {cards_per_topic} flashcards based *only* on the following text:
--- TEXT START ---
{page_text_for_generation}
--- TEXT END ---
{cloze_instruction}
{json_structure_prompt}
"""
response = structured_output_completion(
client,
model,
{"type": "json_object"},
text_system_prompt,
text_user_prompt,
)
if not response or "cards" not in response:
logger.error("Invalid cards response format from text generation.")
raise gr.Error("Failed to generate cards from text. Please try again.")
# Process the cards (similar to generate_cards_batch processing)
cards_data = response["cards"]
topic_name = "From Web" if generation_mode == "web" else "From Text"
for card_index, card_data in enumerate(cards_data, start=1):
if "front" not in card_data or "back" not in card_data:
logger.warning(
f"Skipping card due to missing front/back data: {card_data}"
)
continue
if "question" not in card_data["front"]:
logger.warning(
f"Skipping card due to missing question: {card_data}"
)
continue
if (
"answer" not in card_data["back"]
or "explanation" not in card_data["back"]
or "example" not in card_data["back"]
):
logger.warning(
f"Skipping card due to missing answer/explanation/example: {card_data}"
)
continue
card = Card(
card_type=card_data.get("card_type", "basic"),
front=CardFront(**card_data["front"]),
back=CardBack(**card_data["back"]),
metadata=card_data.get("metadata", {}),
)
metadata = card.metadata or {}
row = [
f"1.{card_index}",
topic_name, # Use dynamic topic name
card.card_type,
card.front.question,
card.back.answer,
card.back.explanation,
card.back.example,
metadata.get("prerequisites", []),
metadata.get("learning_outcomes", []),
metadata.get("misconceptions", []),
metadata.get("difficulty", "beginner"),
]
flattened_data.append(row)
total += 1
gr.Info(f"✅ Generated {total} cards from the provided content.")
# --- Subject Mode --- (Existing logic)
elif generation_mode == "subject":
logger.info(f"Generating cards for subject: {subject}")
if not subject or not subject.strip():
logger.warning("No subject provided for subject generation mode.")
raise gr.Error("Subject is required for 'Single Subject' mode.")
gr.Info("🚀 Starting card generation for subject...")
# Note: system_prompt uses subject variable
system_prompt = f"""
You are an expert educator in {subject}, creating an optimized learning sequence.
Your goal is to:
1. Break down the subject into logical concepts
2. Identify prerequisites and learning outcomes
3. Generate cards that build upon each other
4. Address and correct common misconceptions
5. Include verification steps to minimize hallucinations
6. Provide a recommended study order
For explanations and examples:
- Keep explanations in plain text
- Format code examples with triple backticks (```)
- Separate conceptual examples from code examples
- Use clear, concise language
Keep in mind the user's preferences: {preference_prompt}
"""
topic_prompt = f"""
Generate the top {topic_number} important subjects to know about {subject} in
order of ascending difficulty. Return your response as a JSON object with the following structure:
{{
"topics": [
{{
"name": "topic name",
"difficulty": "beginner/intermediate/advanced",
"description": "brief description"
}}
]
}}
"""
logger.info("Generating topics...")
topics_response = structured_output_completion(
client, model, {"type": "json_object"}, system_prompt, topic_prompt
)
if not topics_response or "topics" not in topics_response:
logger.error("Invalid topics response format")
raise gr.Error("Failed to generate topics. Please try again.")
topics = topics_response["topics"]
gr.Info(f"✨ Generated {len(topics)} topics successfully!")
# Generate cards for each topic
for i, topic in enumerate(
progress_tracker.tqdm(topics, desc="Generating cards")
):
try:
# Re-use the system_prompt defined above for topic generation
cards = generate_cards_batch(
client,
model,
topic["name"],
cards_per_topic,
system_prompt, # Use the same system prompt
generate_cloze=generate_cloze,
batch_size=3,
)
if cards:
for card_index, card in enumerate(cards, start=1):
index = f"{i + 1}.{card_index}"
metadata = card.metadata or {}
row = [
index,
topic["name"],
card.card_type,
card.front.question,
card.back.answer,
card.back.explanation,
card.back.example,
metadata.get("prerequisites", []),
metadata.get("learning_outcomes", []),
metadata.get("misconceptions", []),
metadata.get("difficulty", "beginner"),
]
flattened_data.append(row)
total += 1
gr.Info(f"✅ Generated {len(cards)} cards for {topic['name']}")
except Exception as e:
logger.error(
f"Failed to generate cards for topic {topic['name']}: {str(e)}"
)
gr.Warning(f"Failed to generate cards for '{topic['name']}'")
continue
else:
# Handle other modes or invalid mode if necessary
logger.error(f"Invalid generation mode: {generation_mode}")
raise gr.Error(f"Unsupported generation mode: {generation_mode}")
# --- Common Completion Logic ---
final_html = f"""
<div style="text-align: center">
<p>✅ Generation complete!</p>
<p>Total cards generated: {total}</p>
</div>
"""
df = pd.DataFrame(
flattened_data,
columns=[
"Index",
"Topic",
"Card_Type",
"Question",
"Answer",
"Explanation",
"Example",
"Prerequisites",
"Learning_Outcomes",
"Common_Misconceptions",
"Difficulty",
],
)
return df, final_html, total
except Exception as e:
logger.error(f"Card generation failed: {str(e)}", exc_info=True)
# Check if e is already a gr.Error
if isinstance(e, gr.Error):
raise e
else:
raise gr.Error(f"Card generation failed: {str(e)}")
# Update the BASIC_MODEL definition with enhanced CSS/HTML
BASIC_MODEL = genanki.Model(
random.randrange(1 << 30, 1 << 31),
"AnkiGen Enhanced",
fields=[
{"name": "Question"},
{"name": "Answer"},
{"name": "Explanation"},
{"name": "Example"},
{"name": "Prerequisites"},
{"name": "Learning_Outcomes"},
{"name": "Common_Misconceptions"},
{"name": "Difficulty"},
],
templates=[
{
"name": "Card 1",
"qfmt": """
<div class="card question-side">
<div class="difficulty-indicator {{Difficulty}}"></div>
<div class="content">
<div class="question">{{Question}}</div>
<div class="prerequisites" onclick="event.stopPropagation();">
<div class="prerequisites-toggle">Show Prerequisites</div>
<div class="prerequisites-content">{{Prerequisites}}</div>
</div>
</div>
</div>
<script>
document.querySelector('.prerequisites-toggle').addEventListener('click', function(e) {
e.stopPropagation();
this.parentElement.classList.toggle('show');
});
</script>
""",
"afmt": """
<div class="card answer-side">
<div class="content">
<div class="question-section">
<div class="question">{{Question}}</div>
<div class="prerequisites">
<strong>Prerequisites:</strong> {{Prerequisites}}
</div>
</div>
<hr>
<div class="answer-section">
<h3>Answer</h3>
<div class="answer">{{Answer}}</div>
</div>
<div class="explanation-section">
<h3>Explanation</h3>
<div class="explanation-text">{{Explanation}}</div>
</div>
<div class="example-section">
<h3>Example</h3>
<div class="example-text"></div>
<pre><code>{{Example}}</code></pre>
</div>
<div class="metadata-section">
<div class="learning-outcomes">
<h3>Learning Outcomes</h3>
<div>{{Learning_Outcomes}}</div>
</div>
<div class="misconceptions">
<h3>Common Misconceptions - Debunked</h3>
<div>{{Common_Misconceptions}}</div>
</div>
<div class="difficulty">
<h3>Difficulty Level</h3>
<div>{{Difficulty}}</div>
</div>
</div>
</div>
</div>
""",
}
],
css="""
/* Base styles */
.card {
font-family: 'Inter', system-ui, -apple-system, sans-serif;
font-size: 16px;
line-height: 1.6;
color: #1a1a1a;
max-width: 800px;
margin: 0 auto;
padding: 20px;
background: #ffffff;
}
@media (max-width: 768px) {
.card {
font-size: 14px;
padding: 15px;
}
}
/* Question side */
.question-side {
position: relative;
min-height: 200px;
}
.difficulty-indicator {
position: absolute;
top: 10px;
right: 10px;
width: 10px;
height: 10px;
border-radius: 50%;
}
.difficulty-indicator.beginner { background: #4ade80; }
.difficulty-indicator.intermediate { background: #fbbf24; }
.difficulty-indicator.advanced { background: #ef4444; }
.question {
font-size: 1.3em;
font-weight: 600;
color: #2563eb;
margin-bottom: 1.5em;
}
.prerequisites {
margin-top: 1em;
font-size: 0.9em;
color: #666;
}
.prerequisites-toggle {
color: #2563eb;
cursor: pointer;
text-decoration: underline;
}
.prerequisites-content {
display: none;
margin-top: 0.5em;
padding: 0.5em;
background: #f8fafc;
border-radius: 4px;
}
.prerequisites.show .prerequisites-content {
display: block;
}
/* Answer side */
.answer-section,
.explanation-section,
.example-section {
margin: 1.5em 0;
padding: 1.2em;
border-radius: 8px;
box-shadow: 0 2px 4px rgba(0,0,0,0.05);
}
.answer-section {
background: #f0f9ff;
border-left: 4px solid #2563eb;
}
.explanation-section {
background: #f0fdf4;
border-left: 4px solid #4ade80;
}
.example-section {
background: #fff7ed;
border-left: 4px solid #f97316;
}
/* Code blocks */
pre code {
display: block;
padding: 1em;
background: #1e293b;
color: #e2e8f0;
border-radius: 6px;
overflow-x: auto;
font-family: 'Fira Code', 'Consolas', monospace;
font-size: 0.9em;
}
/* Metadata tabs */
.metadata-tabs {
margin-top: 2em;
border: 1px solid #e5e7eb;
border-radius: 8px;
overflow: hidden;
}
.tab-buttons {
display: flex;
background: #f8fafc;
border-bottom: 1px solid #e5e7eb;
}
.tab-btn {
flex: 1;
padding: 0.8em;
border: none;
background: none;
cursor: pointer;
font-weight: 500;
color: #64748b;
transition: all 0.2s;
}
.tab-btn:hover {
background: #f1f5f9;
}
.tab-btn.active {
color: #2563eb;
background: #fff;
border-bottom: 2px solid #2563eb;
}
.tab-content {
display: none;
padding: 1.2em;
}
.tab-content.active {
display: block;
}
/* Responsive design */
@media (max-width: 640px) {
.tab-buttons {
flex-direction: column;
}
.tab-btn {
width: 100%;
text-align: left;
padding: 0.6em;
}
.answer-section,
.explanation-section,
.example-section {
padding: 1em;
margin: 1em 0;
}
}
/* Animations */
@keyframes fadeIn {
from { opacity: 0; }
to { opacity: 1; }
}
.card {
animation: fadeIn 0.3s ease-in-out;
}
.tab-content.active {
animation: fadeIn 0.2s ease-in-out;
}
""",
)
# Define the Cloze Model (based on Anki's default Cloze type)
CLOZE_MODEL = genanki.Model(
random.randrange(1 << 30, 1 << 31), # Needs a unique ID
"AnkiGen Cloze Enhanced",
model_type=genanki.Model.CLOZE, # Specify model type as CLOZE
fields=[
{"name": "Text"}, # Field for the text containing the cloze deletion
{"name": "Extra"}, # Field for additional info shown on the back
{"name": "Difficulty"}, # Keep metadata
{"name": "SourceTopic"}, # Add topic info
],
templates=[
{
"name": "Cloze Card",
"qfmt": "{{cloze:Text}}",
"afmt": """
{{cloze:Text}}
<hr>
<div class="extra-info">{{Extra}}</div>
<div class="metadata-footer">Difficulty: {{Difficulty}} | Topic: {{SourceTopic}}</div>
""",
}
],
css="""
.card {
font-family: 'Inter', system-ui, -apple-system, sans-serif;
font-size: 16px; line-height: 1.6; color: #1a1a1a;
max-width: 800px; margin: 0 auto; padding: 20px;
background: #ffffff;
}
.cloze {
font-weight: bold; color: #2563eb;
}
.extra-info {
margin-top: 1em; padding-top: 1em;
border-top: 1px solid #e5e7eb;
font-size: 0.95em; color: #333;
background: #f8fafc; padding: 1em; border-radius: 6px;
}
.extra-info h3 { margin-top: 0.5em; font-size: 1.1em; color: #1e293b; }
.extra-info pre code {
display: block; padding: 1em; background: #1e293b;
color: #e2e8f0; border-radius: 6px; overflow-x: auto;
font-family: 'Fira Code', 'Consolas', monospace; font-size: 0.9em;
margin-top: 0.5em;
}
.metadata-footer {
margin-top: 1.5em; font-size: 0.85em; color: #64748b; text-align: right;
}
""",
)
# Split the export functions
def export_csv(data):
"""Export the generated cards as a CSV file"""
if data is None:
raise gr.Error("No data to export. Please generate cards first.")
if len(data) < 2: # Minimum 2 cards
raise gr.Error("Need at least 2 cards to export.")
try:
gr.Info("💾 Exporting to CSV...")
csv_path = "anki_cards.csv"
data.to_csv(csv_path, index=False)
gr.Info("✅ CSV export complete!")
return gr.File(value=csv_path, visible=True)
except Exception as e:
logger.error(f"Failed to export CSV: {str(e)}", exc_info=True)
raise gr.Error(f"Failed to export CSV: {str(e)}")
def export_deck(data, subject):
"""Export the generated cards as an Anki deck with pedagogical metadata"""
if data is None:
raise gr.Error("No data to export. Please generate cards first.")
if len(data) < 2: # Minimum 2 cards
raise gr.Error("Need at least 2 cards to export.")
try:
gr.Info("💾 Creating Anki deck...")
deck_id = random.randrange(1 << 30, 1 << 31)
deck = genanki.Deck(deck_id, f"AnkiGen - {subject}")
records = data.to_dict("records")
# Ensure both models are added to the deck package
deck.add_model(BASIC_MODEL)
deck.add_model(CLOZE_MODEL)
# Add notes to the deck
for record in records:
card_type = record.get("Card_Type", "basic").lower()
if card_type == "cloze":
# Create Cloze note
extra_content = f"""
<h3>Explanation:</h3>
<div>{record["Explanation"]}</div>
<h3>Example:</h3>
<pre><code>{record["Example"]}</code></pre>
<h3>Prerequisites:</h3>
<div>{record["Prerequisites"]}</div>
<h3>Learning Outcomes:</h3>
<div>{record["Learning_Outcomes"]}</div>
<h3>Watch out for:</h3>
<div>{record["Common_Misconceptions"]}</div>
"""
note = genanki.Note(
model=CLOZE_MODEL,
fields=[
str(record["Question"]), # Contains {{c1::...}}
extra_content, # All other info goes here
str(record["Difficulty"]),
str(record["Topic"]),
],
)
else: # Default to basic card
# Create Basic note (existing logic)
note = genanki.Note(
model=BASIC_MODEL,
fields=[
str(record["Question"]),
str(record["Answer"]),
str(record["Explanation"]),
str(record["Example"]),
str(record["Prerequisites"]),
str(record["Learning_Outcomes"]),
str(record["Common_Misconceptions"]),
str(record["Difficulty"]),
],
)
deck.add_note(note)
# Create a temporary directory for the package
with tempfile.TemporaryDirectory() as temp_dir:
output_path = Path(temp_dir) / "anki_deck.apkg"
package = genanki.Package(deck)
package.write_to_file(output_path)
# Copy to a more permanent location
final_path = "anki_deck.apkg"
with open(output_path, "rb") as src, open(final_path, "wb") as dst:
dst.write(src.read())
gr.Info("✅ Anki deck export complete!")
return gr.File(value=final_path, visible=True)
except Exception as e:
logger.error(f"Failed to export Anki deck: {str(e)}", exc_info=True)
raise gr.Error(f"Failed to export Anki deck: {str(e)}")
# Add this near the top where we define our CSS
js_storage = """
async () => {
// Load decks from localStorage
const loadDecks = () => {
const decks = localStorage.getItem('ankigen_decks');
return decks ? JSON.parse(decks) : [];
};
// Save decks to localStorage
const saveDecks = (decks) => {
localStorage.setItem('ankigen_decks', JSON.stringify(decks));
};
// Add methods to window for Gradio to access
window.loadStoredDecks = loadDecks;
window.saveStoredDecks = saveDecks;
// Initial load
return loadDecks();
}
"""
# Create a custom theme
custom_theme = gr.themes.Soft().set(
body_background_fill="*background_fill_secondary",
block_background_fill="*background_fill_primary",
block_border_width="0",
button_primary_background_fill="*primary_500",
button_primary_text_color="white",
)
def analyze_learning_path(api_key, description, model):
"""Analyze a job description or learning goal to create a structured learning path"""
try:
client = OpenAI(api_key=api_key)
except Exception as e:
logger.error(f"Failed to initialize OpenAI client: {str(e)}")
raise gr.Error(f"Failed to initialize OpenAI client: {str(e)}")
system_prompt = """You are an expert curriculum designer and educational consultant.
Your task is to analyze learning goals and create structured, achievable learning paths.
Break down complex topics into manageable subjects, identify prerequisites,
and suggest practical projects that reinforce learning.
Focus on creating a logical progression that builds upon previous knowledge."""
path_prompt = f"""
Analyze this description and create a structured learning path.
Return your analysis as a JSON object with the following structure:
{{
"subjects": [
{{
"Subject": "name of the subject",
"Prerequisites": "required prior knowledge",
"Time Estimate": "estimated time to learn"
}}
],
"learning_order": "recommended sequence of study",
"projects": "suggested practical projects"
}}
Description to analyze:
{description}
"""
try:
response = structured_output_completion(
client, model, {"type": "json_object"}, system_prompt, path_prompt
)
if (
not response
or "subjects" not in response
or "learning_order" not in response
or "projects" not in response
):
logger.error("Invalid response format from API")
raise gr.Error("Failed to analyze learning path. Please try again.")
subjects_df = pd.DataFrame(response["subjects"])
learning_order_text = (
f"### Recommended Learning Order\n{response['learning_order']}"
)
projects_text = f"### Suggested Projects\n{response['projects']}"
return subjects_df, learning_order_text, projects_text
except Exception as e:
logger.error(f"Failed to analyze learning path: {str(e)}")
raise gr.Error(f"Failed to analyze learning path: {str(e)}")
# --- Example Data for Initialization ---
example_data = pd.DataFrame(
[
[
"1.1",
"SQL Basics",
"basic",
"What is a SELECT statement used for?",
"Retrieving data from one or more database tables.",
"The SELECT statement is the most common command in SQL. It allows you to specify which columns and rows you want to retrieve from a table based on certain conditions.",
"```sql\\nSELECT column1, column2 FROM my_table WHERE condition;\\n```",
["Understanding of database tables"],
["Retrieve specific data", "Filter results"],
["❌ SELECT * is always efficient (Reality: Can be slow for large tables)"],
"beginner",
],
[
"2.1",
"Python Fundamentals",
"cloze",
"The primary keyword to define a function in Python is {{c1::def}}.",
"def",
"Functions are defined using the `def` keyword, followed by the function name, parentheses for arguments, and a colon. The indented block below defines the function body.",
# Use a raw triple-quoted string for the code block to avoid escaping issues
r"""```python
def greet(name):
print(f"Hello, {name}!")
```""",
["Basic programming concepts"],
["Define reusable blocks of code"],
["❌ Forgetting the colon (:) after the definition"],
"beginner",
],
],
columns=[
"Index",
"Topic",
"Card_Type",
"Question",
"Answer",
"Explanation",
"Example",
"Prerequisites",
"Learning_Outcomes",
"Common_Misconceptions",
"Difficulty",
],
)
# -------------------------------------
with gr.Blocks(
theme=custom_theme,
title="AnkiGen",
css="""
#footer {display:none !important}
.tall-dataframe {min-height: 500px !important}
.contain {max-width: 100% !important; margin: auto;}
.output-cards {border-radius: 8px; box-shadow: 0 4px 6px -1px rgba(0,0,0,0.1);}
.hint-text {font-size: 0.9em; color: #666; margin-top: 4px;}
.export-group > .gradio-group { margin-bottom: 0 !important; padding-bottom: 5px !important; }
""",
js=js_storage,
) as ankigen:
with gr.Column(elem_classes="contain"):
gr.Markdown("# 📚 AnkiGen - Advanced Anki Card Generator")
gr.Markdown("""
#### Generate comprehensive Anki flashcards using AI.
""")
# Configuration Section in an Accordion
with gr.Accordion("Configuration Settings", open=True):
# Create a row to hold two columns for settings
with gr.Row():
# Column 1: Basic settings
with gr.Column(scale=1):
# Add mode selection
generation_mode = gr.Radio(
choices=[
("Single Subject", "subject"),
("Learning Path", "path"),
("From Text", "text"),
("From Web", "web"),
],
value="subject",
label="Generation Mode",
info="Choose how you want to generate content",
)
# Create containers for different modes
with gr.Group() as subject_mode:
subject = gr.Textbox(
label="Subject",
placeholder="Enter the subject, e.g., 'Basic SQL Concepts'",
info="The topic you want to generate flashcards for",
)
with gr.Group(visible=False) as path_mode:
description = gr.Textbox(
label="Learning Goal",
placeholder="Paste a job description or describe what you want to learn...",
info="We'll break this down into learnable subjects",
lines=5,
)
analyze_button = gr.Button(
"Analyze & Break Down", variant="secondary"
)
# Add group for text input mode
with gr.Group(visible=False) as text_mode:
source_text = gr.Textbox(
label="Source Text",
placeholder="Paste the text you want to generate cards from here...",
info="The AI will extract key information from this text to create cards.",
lines=15,
)
# Add group for web input mode
with gr.Group(visible=False) as web_mode:
url_input = gr.Textbox(
label="Web Page URL",
placeholder="Paste the URL of the page you want to generate cards from...",
info="The AI will attempt to extract content from this URL.",
)
# Common settings moved inside the accordion, in column 1
api_key_input = gr.Textbox(
label="OpenAI API Key",
type="password",
placeholder="Enter your OpenAI API key",
value=os.getenv("OPENAI_API_KEY", ""),
info="Your OpenAI API key starting with 'sk-'",
)
# Column 2: Advanced settings accordion
with gr.Column(scale=1):
# Advanced Settings Accordion moved inside the main accordion, in column 2
with gr.Accordion("Advanced Settings", open=False):
model_choice = gr.Dropdown(
choices=["gpt-4.1", "gpt-4.1-nano"], # Corrected choices
value="gpt-4.1-nano", # Changed default to nano as it's faster/cheaper
label="Model Selection",
info="Select the AI model to use for generation",
)
# Add tooltip/description for models
model_info = gr.Markdown(
"""
**Model Information:**
- **gpt-4.1**: Highest quality, slower generation
- **gpt-4.1-nano**: Optimized for speed and lower cost
""" # Corrected descriptions
)
topic_number = gr.Slider(
label="Number of Topics",
minimum=2,
maximum=20,
step=1,
value=2,
info="How many distinct topics to cover within the subject",
)
cards_per_topic = gr.Slider(
label="Cards per Topic",
minimum=2,
maximum=30,
step=1,
value=3,
info="How many flashcards to generate for each topic",
)
preference_prompt = gr.Textbox(
label="Learning Preferences",
placeholder="e.g., 'Assume I'm a beginner' or 'Focus on practical examples'",
info="Customize how the content is presented",
lines=3,
)
generate_cloze_checkbox = gr.Checkbox(
label="Generate Cloze Cards (Experimental)",
value=False,
info="Allow the AI to generate fill-in-the-blank style cards where appropriate.",
)
# End of Advanced Settings Accordion
# End of Row containing settings columns
# End of Configuration Settings Accordion
# Generation Button moved outside the Accordion
generate_button = gr.Button("Generate Cards", variant="primary")
# Output Area remains below the button
with gr.Group(
visible=False
) as path_results: # Initial visibility controlled by mode
gr.Markdown("### Learning Path Analysis")
subjects_list = gr.Dataframe(
headers=["Subject", "Prerequisites", "Time Estimate"],
label="Recommended Subjects",
interactive=False,
)
learning_order = gr.Markdown("### Recommended Learning Order")
projects = gr.Markdown("### Suggested Projects")
use_subjects = gr.Button(
"Use These Subjects ℹ️",
variant="primary",
)
gr.Markdown(
"*Click to copy subjects to main input for card generation*",
elem_classes="hint-text",
)
with gr.Group() as cards_output: # Initial visibility controlled by mode
gr.Markdown("### Generated Cards")
# Output Format Documentation (can stay here)
with gr.Accordion("Output Format", open=False):
gr.Markdown("""
The generated cards include:
* **Index**: Unique identifier for each card
* **Topic**: The specific subtopic within your subject
* **Card_Type**: Type of card (basic or cloze)
* **Question**: Clear, focused question for the flashcard front
* **Answer**: Concise core answer
* **Explanation**: Detailed conceptual explanation
* **Example**: Practical implementation or code example
* **Prerequisites**: Required knowledge for this concept
* **Learning Outcomes**: What you should understand after mastering this card
* **Common Misconceptions**: Incorrect assumptions debunked with explanations
* **Difficulty**: Concept complexity level for optimal study sequencing
Export options:
- **CSV**: Raw data for custom processing
- **Anki Deck**: Ready-to-use deck with formatted cards and metadata
""")
with gr.Accordion("Example Card Format", open=False):
gr.Code(
label="Example Card",
value="""
{
"front": {
"question": "What is a PRIMARY KEY constraint in SQL?"
},
"back": {
"answer": "A PRIMARY KEY constraint uniquely identifies each record in a table",
"explanation": "A primary key serves as a unique identifier for each row in a database table. It enforces data integrity by ensuring that:\n1. Each value is unique\n2. No null values are allowed\n3. The value remains stable over time\n\nThis is fundamental for:\n- Establishing relationships between tables\n- Maintaining data consistency\n- Efficient data retrieval",
"example": "-- Creating a table with a primary key\nCREATE TABLE Users (\n user_id INT PRIMARY KEY,\n username VARCHAR(50) NOT NULL,\n email VARCHAR(100) UNIQUE\n);"
},
"metadata": {
"prerequisites": ["Basic SQL table concepts", "Understanding of data types"],
"learning_outcomes": ["Understand the purpose and importance of primary keys", "Know how to create and use primary keys"],
"common_misconceptions": [
"❌ Misconception: Primary keys must always be single columns\n✓ Reality: Primary keys can be composite (multiple columns)",
"❌ Misconception: Primary keys must be integers\n✓ Reality: Any data type that ensures uniqueness can be used"
],
"difficulty": "beginner"
}
}
""",
language="json",
)
output = gr.Dataframe(
value=example_data,
headers=[
"Index",
"Topic",
"Card_Type",
"Question",
"Answer",
"Explanation",
"Example",
"Prerequisites",
"Learning_Outcomes",
"Common_Misconceptions",
"Difficulty",
],
interactive=True,
elem_classes="tall-dataframe",
wrap=True,
column_widths=[
50,
100,
80,
200,
200,
250,
200,
150,
150,
150,
100,
],
)
with gr.Group(elem_classes="export-group"):
gr.Markdown("#### Export Generated Cards")
with gr.Row():
export_csv_button = gr.Button("Export to CSV", variant="secondary")
export_anki_button = gr.Button(
"Export to Anki Deck (.apkg)", variant="secondary"
)
with gr.Row(): # Row containing File components is now visible
download_csv = gr.File(label="Download CSV", interactive=False)
download_anki = gr.File(
label="Download Anki Deck",
interactive=False,
)
# Add near the top of the Blocks
with gr.Row():
progress = gr.HTML(visible=False)
total_cards = gr.Number(
label="Total Cards Generated", value=0, visible=False
)
# Adjust JavaScript handler for mode switching
def update_mode_visibility(mode):
is_subject = mode == "subject"
is_path = mode == "path"
is_text = mode == "text"
is_web = mode == "web"
subject_val = subject.value if is_subject else ""
description_val = description.value if is_path else ""
text_val = source_text.value if is_text else ""
url_val = url_input.value if is_web else ""
return {
subject_mode: gr.update(visible=is_subject),
path_mode: gr.update(visible=is_path),
text_mode: gr.update(visible=is_text),
web_mode: gr.update(visible=is_web),
path_results: gr.update(visible=is_path),
cards_output: gr.update(visible=is_subject or is_text or is_web),
subject: gr.update(value=subject_val),
description: gr.update(value=description_val),
source_text: gr.update(value=text_val),
url_input: gr.update(value=url_val),
output: gr.update(value=None),
subjects_list: gr.update(value=None),
learning_order: gr.update(value=""),
projects: gr.update(value=""),
progress: gr.update(value="", visible=False),
total_cards: gr.update(value=0, visible=False),
}
generation_mode.change(
fn=update_mode_visibility,
inputs=[generation_mode],
outputs=[
subject_mode,
path_mode,
text_mode,
web_mode,
path_results,
cards_output,
subject,
description,
source_text,
url_input,
output,
subjects_list,
learning_order,
projects,
progress,
total_cards,
],
)
analyze_button.click(
fn=analyze_learning_path,
inputs=[api_key_input, description, model_choice],
outputs=[subjects_list, learning_order, projects],
)
def use_selected_subjects(subjects_df):
if subjects_df is None or subjects_df.empty:
gr.Warning("No subjects available to copy from Learning Path analysis.")
return (
gr.update(),
gr.update(),
gr.update(),
gr.update(),
gr.update(),
gr.update(),
gr.update(),
gr.update(),
gr.update(),
gr.update(),
gr.update(),
gr.update(),
gr.update(),
gr.update(),
gr.update(),
)
subjects = subjects_df["Subject"].tolist()
combined_subject = ", ".join(subjects)
suggested_topics = min(len(subjects) + 1, 20)
return {
generation_mode: "subject",
subject_mode: gr.update(visible=True),
path_mode: gr.update(visible=False),
text_mode: gr.update(visible=False),
web_mode: gr.update(visible=False),
path_results: gr.update(visible=False),
cards_output: gr.update(visible=True),
subject: combined_subject,
description: "",
source_text: "",
url_input: "",
topic_number: suggested_topics,
preference_prompt: "Focus on connections between these subjects and their practical applications.",
output: example_data,
subjects_list: subjects_df,
learning_order: gr.update(),
projects: gr.update(),
progress: gr.update(visible=False),
total_cards: gr.update(visible=False),
}
use_subjects.click(
fn=use_selected_subjects,
inputs=[subjects_list],
outputs=[
generation_mode,
subject_mode,
path_mode,
text_mode,
web_mode,
path_results,
cards_output,
subject,
description,
source_text,
url_input,
topic_number,
preference_prompt,
output,
subjects_list,
learning_order,
projects,
progress,
total_cards,
],
)
generate_button.click(
fn=generate_cards,
inputs=[
api_key_input,
subject,
generation_mode,
source_text,
url_input,
model_choice,
topic_number,
cards_per_topic,
preference_prompt,
generate_cloze_checkbox,
],
outputs=[output, progress, total_cards],
show_progress="full",
)
export_csv_button.click(
fn=export_csv,
inputs=[output],
outputs=download_csv,
show_progress="full",
)
export_anki_button.click(
fn=export_deck,
inputs=[output, subject],
outputs=download_anki,
show_progress="full",
)
if __name__ == "__main__":
logger.info("Starting AnkiGen application")
ankigen.launch(share=False, favicon_path="./favicon.ico")
|