File size: 108,786 Bytes
167596f | 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 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 | """
This module contains all document-related routes for the LightRAG API.
"""
import asyncio
from lightrag.utils import logger, get_pinyin_sort_key
import aiofiles
import shutil
import traceback
import pipmaster as pm
from datetime import datetime, timezone
from pathlib import Path
from typing import Dict, List, Optional, Any, Literal
from fastapi import (
APIRouter,
BackgroundTasks,
Depends,
File,
HTTPException,
UploadFile,
)
from pydantic import BaseModel, Field, field_validator
from lightrag import LightRAG
from lightrag.base import DeletionResult, DocProcessingStatus, DocStatus
from lightrag.utils import generate_track_id
from lightrag.api.utils_api import get_combined_auth_dependency
from ..config import global_args
# Function to format datetime to ISO format string with timezone information
def format_datetime(dt: Any) -> Optional[str]:
"""Format datetime to ISO format string with timezone information
Args:
dt: Datetime object, string, or None
Returns:
ISO format string with timezone information, or None if input is None
"""
if dt is None:
return None
if isinstance(dt, str):
return dt
# Check if datetime object has timezone information
if isinstance(dt, datetime):
# If datetime object has no timezone info (naive datetime), add UTC timezone
if dt.tzinfo is None:
dt = dt.replace(tzinfo=timezone.utc)
# Return ISO format string with timezone information
return dt.isoformat()
router = APIRouter(
prefix="/documents",
tags=["documents"],
)
# Temporary file prefix
temp_prefix = "__tmp__"
def sanitize_filename(filename: str, input_dir: Path) -> str:
"""
Sanitize uploaded filename to prevent Path Traversal attacks.
Args:
filename: The original filename from the upload
input_dir: The target input directory
Returns:
str: Sanitized filename that is safe to use
Raises:
HTTPException: If the filename is unsafe or invalid
"""
# Basic validation
if not filename or not filename.strip():
raise HTTPException(status_code=400, detail="Filename cannot be empty")
# Remove path separators and traversal sequences
clean_name = filename.replace("/", "").replace("\\", "")
clean_name = clean_name.replace("..", "")
# Remove control characters and null bytes
clean_name = "".join(c for c in clean_name if ord(c) >= 32 and c != "\x7f")
# Remove leading/trailing whitespace and dots
clean_name = clean_name.strip().strip(".")
# Check if anything is left after sanitization
if not clean_name:
raise HTTPException(
status_code=400, detail="Invalid filename after sanitization"
)
# Verify the final path stays within the input directory
try:
final_path = (input_dir / clean_name).resolve()
if not final_path.is_relative_to(input_dir.resolve()):
raise HTTPException(status_code=400, detail="Unsafe filename detected")
except (OSError, ValueError):
raise HTTPException(status_code=400, detail="Invalid filename")
return clean_name
class ScanResponse(BaseModel):
"""Response model for document scanning operation
Attributes:
status: Status of the scanning operation
message: Optional message with additional details
track_id: Tracking ID for monitoring scanning progress
"""
status: Literal["scanning_started"] = Field(
description="Status of the scanning operation"
)
message: Optional[str] = Field(
default=None, description="Additional details about the scanning operation"
)
track_id: str = Field(description="Tracking ID for monitoring scanning progress")
class Config:
json_schema_extra = {
"example": {
"status": "scanning_started",
"message": "Scanning process has been initiated in the background",
"track_id": "scan_20250729_170612_abc123",
}
}
class InsertTextRequest(BaseModel):
"""Request model for inserting a single text document
Attributes:
text: The text content to be inserted into the RAG system
file_source: Source of the text (optional)
"""
text: str = Field(
min_length=1,
description="The text to insert",
)
file_source: str = Field(default=None, min_length=0, description="File Source")
@field_validator("text", mode="after")
@classmethod
def strip_text_after(cls, text: str) -> str:
return text.strip()
@field_validator("file_source", mode="after")
@classmethod
def strip_source_after(cls, file_source: str) -> str:
return file_source.strip()
class Config:
json_schema_extra = {
"example": {
"text": "This is a sample text to be inserted into the RAG system.",
"file_source": "Source of the text (optional)",
}
}
class InsertTextsRequest(BaseModel):
"""Request model for inserting multiple text documents
Attributes:
texts: List of text contents to be inserted into the RAG system
file_sources: Sources of the texts (optional)
"""
texts: list[str] = Field(
min_length=1,
description="The texts to insert",
)
file_sources: list[str] = Field(
default=None, min_length=0, description="Sources of the texts"
)
@field_validator("texts", mode="after")
@classmethod
def strip_texts_after(cls, texts: list[str]) -> list[str]:
return [text.strip() for text in texts]
@field_validator("file_sources", mode="after")
@classmethod
def strip_sources_after(cls, file_sources: list[str]) -> list[str]:
return [file_source.strip() for file_source in file_sources]
class Config:
json_schema_extra = {
"example": {
"texts": [
"This is the first text to be inserted.",
"This is the second text to be inserted.",
],
"file_sources": [
"First file source (optional)",
],
}
}
class InsertResponse(BaseModel):
"""Response model for document insertion operations
Attributes:
status: Status of the operation (success, duplicated, partial_success, failure)
message: Detailed message describing the operation result
track_id: Tracking ID for monitoring processing status
"""
status: Literal["success", "duplicated", "partial_success", "failure"] = Field(
description="Status of the operation"
)
message: str = Field(description="Message describing the operation result")
track_id: str = Field(description="Tracking ID for monitoring processing status")
class Config:
json_schema_extra = {
"example": {
"status": "success",
"message": "File 'document.pdf' uploaded successfully. Processing will continue in background.",
"track_id": "upload_20250729_170612_abc123",
}
}
class ClearDocumentsResponse(BaseModel):
"""Response model for document clearing operation
Attributes:
status: Status of the clear operation
message: Detailed message describing the operation result
"""
status: Literal["success", "partial_success", "busy", "fail"] = Field(
description="Status of the clear operation"
)
message: str = Field(description="Message describing the operation result")
class Config:
json_schema_extra = {
"example": {
"status": "success",
"message": "All documents cleared successfully. Deleted 15 files.",
}
}
class ClearCacheRequest(BaseModel):
"""Request model for clearing cache
This model is kept for API compatibility but no longer accepts any parameters.
All cache will be cleared regardless of the request content.
"""
class Config:
json_schema_extra = {"example": {}}
class ClearCacheResponse(BaseModel):
"""Response model for cache clearing operation
Attributes:
status: Status of the clear operation
message: Detailed message describing the operation result
"""
status: Literal["success", "fail"] = Field(
description="Status of the clear operation"
)
message: str = Field(description="Message describing the operation result")
class Config:
json_schema_extra = {
"example": {
"status": "success",
"message": "Successfully cleared cache for modes: ['default', 'naive']",
}
}
"""Response model for document status
Attributes:
id: Document identifier
content_summary: Summary of document content
content_length: Length of document content
status: Current processing status
created_at: Creation timestamp (ISO format string)
updated_at: Last update timestamp (ISO format string)
chunks_count: Number of chunks (optional)
error: Error message if any (optional)
metadata: Additional metadata (optional)
file_path: Path to the document file
"""
class DeleteDocRequest(BaseModel):
doc_ids: List[str] = Field(..., description="The IDs of the documents to delete.")
delete_file: bool = Field(
default=False,
description="Whether to delete the corresponding file in the upload directory.",
)
@field_validator("doc_ids", mode="after")
@classmethod
def validate_doc_ids(cls, doc_ids: List[str]) -> List[str]:
if not doc_ids:
raise ValueError("Document IDs list cannot be empty")
validated_ids = []
for doc_id in doc_ids:
if not doc_id or not doc_id.strip():
raise ValueError("Document ID cannot be empty")
validated_ids.append(doc_id.strip())
# Check for duplicates
if len(validated_ids) != len(set(validated_ids)):
raise ValueError("Document IDs must be unique")
return validated_ids
class DeleteEntityRequest(BaseModel):
entity_name: str = Field(..., description="The name of the entity to delete.")
@field_validator("entity_name", mode="after")
@classmethod
def validate_entity_name(cls, entity_name: str) -> str:
if not entity_name or not entity_name.strip():
raise ValueError("Entity name cannot be empty")
return entity_name.strip()
class DeleteRelationRequest(BaseModel):
source_entity: str = Field(..., description="The name of the source entity.")
target_entity: str = Field(..., description="The name of the target entity.")
@field_validator("source_entity", "target_entity", mode="after")
@classmethod
def validate_entity_names(cls, entity_name: str) -> str:
if not entity_name or not entity_name.strip():
raise ValueError("Entity name cannot be empty")
return entity_name.strip()
class DocStatusResponse(BaseModel):
id: str = Field(description="Document identifier")
content_summary: str = Field(description="Summary of document content")
content_length: int = Field(description="Length of document content in characters")
status: DocStatus = Field(description="Current processing status")
created_at: str = Field(description="Creation timestamp (ISO format string)")
updated_at: str = Field(description="Last update timestamp (ISO format string)")
track_id: Optional[str] = Field(
default=None, description="Tracking ID for monitoring progress"
)
chunks_count: Optional[int] = Field(
default=None, description="Number of chunks the document was split into"
)
error_msg: Optional[str] = Field(
default=None, description="Error message if processing failed"
)
metadata: Optional[dict[str, Any]] = Field(
default=None, description="Additional metadata about the document"
)
file_path: str = Field(description="Path to the document file")
class Config:
json_schema_extra = {
"example": {
"id": "doc_123456",
"content_summary": "Research paper on machine learning",
"content_length": 15240,
"status": "PROCESSED",
"created_at": "2025-03-31T12:34:56",
"updated_at": "2025-03-31T12:35:30",
"track_id": "upload_20250729_170612_abc123",
"chunks_count": 12,
"error": None,
"metadata": {"author": "John Doe", "year": 2025},
"file_path": "research_paper.pdf",
}
}
class DocsStatusesResponse(BaseModel):
"""Response model for document statuses
Attributes:
statuses: Dictionary mapping document status to lists of document status responses
"""
statuses: Dict[DocStatus, List[DocStatusResponse]] = Field(
default_factory=dict,
description="Dictionary mapping document status to lists of document status responses",
)
class Config:
json_schema_extra = {
"example": {
"statuses": {
"PENDING": [
{
"id": "doc_123",
"content_summary": "Pending document",
"content_length": 5000,
"status": "PENDING",
"created_at": "2025-03-31T10:00:00",
"updated_at": "2025-03-31T10:00:00",
"track_id": "upload_20250331_100000_abc123",
"chunks_count": None,
"error": None,
"metadata": None,
"file_path": "pending_doc.pdf",
}
],
"PROCESSED": [
{
"id": "doc_456",
"content_summary": "Processed document",
"content_length": 8000,
"status": "PROCESSED",
"created_at": "2025-03-31T09:00:00",
"updated_at": "2025-03-31T09:05:00",
"track_id": "insert_20250331_090000_def456",
"chunks_count": 8,
"error": None,
"metadata": {"author": "John Doe"},
"file_path": "processed_doc.pdf",
}
],
}
}
}
class TrackStatusResponse(BaseModel):
"""Response model for tracking document processing status by track_id
Attributes:
track_id: The tracking ID
documents: List of documents associated with this track_id
total_count: Total number of documents for this track_id
status_summary: Count of documents by status
"""
track_id: str = Field(description="The tracking ID")
documents: List[DocStatusResponse] = Field(
description="List of documents associated with this track_id"
)
total_count: int = Field(description="Total number of documents for this track_id")
status_summary: Dict[str, int] = Field(description="Count of documents by status")
class Config:
json_schema_extra = {
"example": {
"track_id": "upload_20250729_170612_abc123",
"documents": [
{
"id": "doc_123456",
"content_summary": "Research paper on machine learning",
"content_length": 15240,
"status": "PROCESSED",
"created_at": "2025-03-31T12:34:56",
"updated_at": "2025-03-31T12:35:30",
"track_id": "upload_20250729_170612_abc123",
"chunks_count": 12,
"error": None,
"metadata": {"author": "John Doe", "year": 2025},
"file_path": "research_paper.pdf",
}
],
"total_count": 1,
"status_summary": {"PROCESSED": 1},
}
}
class DocumentsRequest(BaseModel):
"""Request model for paginated document queries
Attributes:
status_filter: Filter by document status, None for all statuses
page: Page number (1-based)
page_size: Number of documents per page (10-200)
sort_field: Field to sort by ('created_at', 'updated_at', 'id', 'file_path')
sort_direction: Sort direction ('asc' or 'desc')
"""
status_filter: Optional[DocStatus] = Field(
default=None, description="Filter by document status, None for all statuses"
)
page: int = Field(default=1, ge=1, description="Page number (1-based)")
page_size: int = Field(
default=50, ge=10, le=200, description="Number of documents per page (10-200)"
)
sort_field: Literal["created_at", "updated_at", "id", "file_path"] = Field(
default="updated_at", description="Field to sort by"
)
sort_direction: Literal["asc", "desc"] = Field(
default="desc", description="Sort direction"
)
class Config:
json_schema_extra = {
"example": {
"status_filter": "PROCESSED",
"page": 1,
"page_size": 50,
"sort_field": "updated_at",
"sort_direction": "desc",
}
}
class PaginationInfo(BaseModel):
"""Pagination information
Attributes:
page: Current page number
page_size: Number of items per page
total_count: Total number of items
total_pages: Total number of pages
has_next: Whether there is a next page
has_prev: Whether there is a previous page
"""
page: int = Field(description="Current page number")
page_size: int = Field(description="Number of items per page")
total_count: int = Field(description="Total number of items")
total_pages: int = Field(description="Total number of pages")
has_next: bool = Field(description="Whether there is a next page")
has_prev: bool = Field(description="Whether there is a previous page")
class Config:
json_schema_extra = {
"example": {
"page": 1,
"page_size": 50,
"total_count": 150,
"total_pages": 3,
"has_next": True,
"has_prev": False,
}
}
class PaginatedDocsResponse(BaseModel):
"""Response model for paginated document queries
Attributes:
documents: List of documents for the current page
pagination: Pagination information
status_counts: Count of documents by status for all documents
"""
documents: List[DocStatusResponse] = Field(
description="List of documents for the current page"
)
pagination: PaginationInfo = Field(description="Pagination information")
status_counts: Dict[str, int] = Field(
description="Count of documents by status for all documents"
)
class Config:
json_schema_extra = {
"example": {
"documents": [
{
"id": "doc_123456",
"content_summary": "Research paper on machine learning",
"content_length": 15240,
"status": "PROCESSED",
"created_at": "2025-03-31T12:34:56",
"updated_at": "2025-03-31T12:35:30",
"track_id": "upload_20250729_170612_abc123",
"chunks_count": 12,
"error_msg": None,
"metadata": {"author": "John Doe", "year": 2025},
"file_path": "research_paper.pdf",
}
],
"pagination": {
"page": 1,
"page_size": 50,
"total_count": 150,
"total_pages": 3,
"has_next": True,
"has_prev": False,
},
"status_counts": {
"PENDING": 10,
"PROCESSING": 5,
"PROCESSED": 130,
"FAILED": 5,
},
}
}
class StatusCountsResponse(BaseModel):
"""Response model for document status counts
Attributes:
status_counts: Count of documents by status
"""
status_counts: Dict[str, int] = Field(description="Count of documents by status")
class Config:
json_schema_extra = {
"example": {
"status_counts": {
"PENDING": 10,
"PROCESSING": 5,
"PROCESSED": 130,
"FAILED": 5,
}
}
}
class PipelineStatusResponse(BaseModel):
"""Response model for pipeline status
Attributes:
autoscanned: Whether auto-scan has started
busy: Whether the pipeline is currently busy
job_name: Current job name (e.g., indexing files/indexing texts)
job_start: Job start time as ISO format string with timezone (optional)
docs: Total number of documents to be indexed
batchs: Number of batches for processing documents
cur_batch: Current processing batch
request_pending: Flag for pending request for processing
latest_message: Latest message from pipeline processing
history_messages: List of history messages
update_status: Status of update flags for all namespaces
"""
autoscanned: bool = False
busy: bool = False
job_name: str = "Default Job"
job_start: Optional[str] = None
docs: int = 0
batchs: int = 0
cur_batch: int = 0
request_pending: bool = False
latest_message: str = ""
history_messages: Optional[List[str]] = None
update_status: Optional[dict] = None
@field_validator("job_start", mode="before")
@classmethod
def parse_job_start(cls, value):
"""Process datetime and return as ISO format string with timezone"""
return format_datetime(value)
class Config:
extra = "allow" # Allow additional fields from the pipeline status
class DocumentManager:
def __init__(
self,
input_dir: str,
workspace: str = "", # New parameter for workspace isolation
supported_extensions: tuple = (
".txt",
".md",
".pdf",
".docx",
".pptx",
".xlsx",
".rtf", # Rich Text Format
".odt", # OpenDocument Text
".tex", # LaTeX
".epub", # Electronic Publication
".html", # HyperText Markup Language
".htm", # HyperText Markup Language
".csv", # Comma-Separated Values
".json", # JavaScript Object Notation
".xml", # eXtensible Markup Language
".yaml", # YAML Ain't Markup Language
".yml", # YAML
".log", # Log files
".conf", # Configuration files
".ini", # Initialization files
".properties", # Java properties files
".sql", # SQL scripts
".bat", # Batch files
".sh", # Shell scripts
".c", # C source code
".cpp", # C++ source code
".py", # Python source code
".java", # Java source code
".js", # JavaScript source code
".ts", # TypeScript source code
".swift", # Swift source code
".go", # Go source code
".rb", # Ruby source code
".php", # PHP source code
".css", # Cascading Style Sheets
".scss", # Sassy CSS
".less", # LESS CSS
),
):
# Store the base input directory and workspace
self.base_input_dir = Path(input_dir)
self.workspace = workspace
self.supported_extensions = supported_extensions
self.indexed_files = set()
# Create workspace-specific input directory
# If workspace is provided, create a subdirectory for data isolation
if workspace:
self.input_dir = self.base_input_dir / workspace
else:
self.input_dir = self.base_input_dir
# Create input directory if it doesn't exist
self.input_dir.mkdir(parents=True, exist_ok=True)
def scan_directory_for_new_files(self) -> List[Path]:
"""Scan input directory for new files"""
new_files = []
for ext in self.supported_extensions:
logger.debug(f"Scanning for {ext} files in {self.input_dir}")
for file_path in self.input_dir.glob(f"*{ext}"):
if file_path not in self.indexed_files:
new_files.append(file_path)
return new_files
def mark_as_indexed(self, file_path: Path):
self.indexed_files.add(file_path)
def is_supported_file(self, filename: str) -> bool:
return any(filename.lower().endswith(ext) for ext in self.supported_extensions)
def validate_file_path_security(file_path_str: str, base_dir: Path) -> Optional[Path]:
"""
Validate file path security to prevent Path Traversal attacks.
Args:
file_path_str: The file path string to validate
base_dir: The base directory that the file must be within
Returns:
Path: Safe file path if valid, None if unsafe or invalid
"""
if not file_path_str or not file_path_str.strip():
return None
try:
# Clean the file path string
clean_path_str = file_path_str.strip()
# Check for obvious path traversal patterns before processing
# This catches both Unix (..) and Windows (..\) style traversals
if ".." in clean_path_str:
# Additional check for Windows-style backslash traversal
if (
"\\..\\" in clean_path_str
or clean_path_str.startswith("..\\")
or clean_path_str.endswith("\\..")
):
# logger.warning(
# f"Security violation: Windows path traversal attempt detected - {file_path_str}"
# )
return None
# Normalize path separators (convert backslashes to forward slashes)
# This helps handle Windows-style paths on Unix systems
normalized_path = clean_path_str.replace("\\", "/")
# Create path object and resolve it (handles symlinks and relative paths)
candidate_path = (base_dir / normalized_path).resolve()
base_dir_resolved = base_dir.resolve()
# Check if the resolved path is within the base directory
if not candidate_path.is_relative_to(base_dir_resolved):
# logger.warning(
# f"Security violation: Path traversal attempt detected - {file_path_str}"
# )
return None
return candidate_path
except (OSError, ValueError, Exception) as e:
logger.warning(f"Invalid file path detected: {file_path_str} - {str(e)}")
return None
def get_unique_filename_in_enqueued(target_dir: Path, original_name: str) -> str:
"""Generate a unique filename in the target directory by adding numeric suffixes if needed
Args:
target_dir: Target directory path
original_name: Original filename
Returns:
str: Unique filename (may have numeric suffix added)
"""
from pathlib import Path
import time
original_path = Path(original_name)
base_name = original_path.stem
extension = original_path.suffix
# Try original name first
if not (target_dir / original_name).exists():
return original_name
# Try with numeric suffixes 001-999
for i in range(1, 1000):
suffix = f"{i:03d}"
new_name = f"{base_name}_{suffix}{extension}"
if not (target_dir / new_name).exists():
return new_name
# Fallback with timestamp if all 999 slots are taken
timestamp = int(time.time())
return f"{base_name}_{timestamp}{extension}"
async def pipeline_enqueue_file(
rag: LightRAG, file_path: Path, track_id: str = None
) -> tuple[bool, str]:
"""Add a file to the queue for processing
Args:
rag: LightRAG instance
file_path: Path to the saved file
track_id: Optional tracking ID, if not provided will be generated
Returns:
tuple: (success: bool, track_id: str)
"""
# Generate track_id if not provided
if track_id is None:
track_id = generate_track_id("unknown")
try:
content = ""
ext = file_path.suffix.lower()
file_size = 0
# Get file size for error reporting
try:
file_size = file_path.stat().st_size
except Exception:
file_size = 0
file = None
try:
async with aiofiles.open(file_path, "rb") as f:
file = await f.read()
except PermissionError as e:
error_files = [
{
"file_path": str(file_path.name),
"error_description": "[File Extraction]Permission denied - cannot read file",
"original_error": str(e),
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(error_files, track_id)
logger.error(
f"[File Extraction]Permission denied reading file: {file_path.name}"
)
return False, track_id
except FileNotFoundError as e:
error_files = [
{
"file_path": str(file_path.name),
"error_description": "[File Extraction]File not found",
"original_error": str(e),
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(error_files, track_id)
logger.error(f"[File Extraction]File not found: {file_path.name}")
return False, track_id
except Exception as e:
error_files = [
{
"file_path": str(file_path.name),
"error_description": "[File Extraction]File reading error",
"original_error": str(e),
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(error_files, track_id)
logger.error(
f"[File Extraction]Error reading file {file_path.name}: {str(e)}"
)
return False, track_id
# Process based on file type
try:
match ext:
case (
".txt"
| ".md"
| ".html"
| ".htm"
| ".tex"
| ".json"
| ".xml"
| ".yaml"
| ".yml"
| ".rtf"
| ".odt"
| ".epub"
| ".csv"
| ".log"
| ".conf"
| ".ini"
| ".properties"
| ".sql"
| ".bat"
| ".sh"
| ".c"
| ".cpp"
| ".py"
| ".java"
| ".js"
| ".ts"
| ".swift"
| ".go"
| ".rb"
| ".php"
| ".css"
| ".scss"
| ".less"
):
try:
# Try to decode as UTF-8
content = file.decode("utf-8")
# Validate content
if not content or len(content.strip()) == 0:
error_files = [
{
"file_path": str(file_path.name),
"error_description": "[File Extraction]Empty file content",
"original_error": "File contains no content or only whitespace",
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(
error_files, track_id
)
logger.error(
f"[File Extraction]Empty content in file: {file_path.name}"
)
return False, track_id
# Check if content looks like binary data string representation
if content.startswith("b'") or content.startswith('b"'):
error_files = [
{
"file_path": str(file_path.name),
"error_description": "[File Extraction]Binary data in text file",
"original_error": "File appears to contain binary data representation instead of text",
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(
error_files, track_id
)
logger.error(
f"[File Extraction]File {file_path.name} appears to contain binary data representation instead of text"
)
return False, track_id
except UnicodeDecodeError as e:
error_files = [
{
"file_path": str(file_path.name),
"error_description": "[File Extraction]UTF-8 encoding error, please convert it to UTF-8 before processing",
"original_error": f"File is not valid UTF-8 encoded text: {str(e)}",
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(
error_files, track_id
)
logger.error(
f"[File Extraction]File {file_path.name} is not valid UTF-8 encoded text. Please convert it to UTF-8 before processing."
)
return False, track_id
case ".pdf":
try:
if global_args.document_loading_engine == "DOCLING":
if not pm.is_installed("docling"): # type: ignore
pm.install("docling")
from docling.document_converter import DocumentConverter # type: ignore
converter = DocumentConverter()
result = converter.convert(file_path)
content = result.document.export_to_markdown()
else:
if not pm.is_installed("pypdf2"): # type: ignore
pm.install("pypdf2")
from PyPDF2 import PdfReader # type: ignore
from io import BytesIO
pdf_file = BytesIO(file)
reader = PdfReader(pdf_file)
for page in reader.pages:
content += page.extract_text() + "\n"
except Exception as e:
error_files = [
{
"file_path": str(file_path.name),
"error_description": "[File Extraction]PDF processing error",
"original_error": f"Failed to extract text from PDF: {str(e)}",
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(
error_files, track_id
)
logger.error(
f"[File Extraction]Error processing PDF {file_path.name}: {str(e)}"
)
return False, track_id
case ".docx":
try:
if global_args.document_loading_engine == "DOCLING":
if not pm.is_installed("docling"): # type: ignore
pm.install("docling")
from docling.document_converter import DocumentConverter # type: ignore
converter = DocumentConverter()
result = converter.convert(file_path)
content = result.document.export_to_markdown()
else:
if not pm.is_installed("python-docx"): # type: ignore
try:
pm.install("python-docx")
except Exception:
pm.install("docx")
from docx import Document # type: ignore
from io import BytesIO
docx_file = BytesIO(file)
doc = Document(docx_file)
content = "\n".join(
[paragraph.text for paragraph in doc.paragraphs]
)
except Exception as e:
error_files = [
{
"file_path": str(file_path.name),
"error_description": "[File Extraction]DOCX processing error",
"original_error": f"Failed to extract text from DOCX: {str(e)}",
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(
error_files, track_id
)
logger.error(
f"[File Extraction]Error processing DOCX {file_path.name}: {str(e)}"
)
return False, track_id
case ".pptx":
try:
if global_args.document_loading_engine == "DOCLING":
if not pm.is_installed("docling"): # type: ignore
pm.install("docling")
from docling.document_converter import DocumentConverter # type: ignore
converter = DocumentConverter()
result = converter.convert(file_path)
content = result.document.export_to_markdown()
else:
if not pm.is_installed("python-pptx"): # type: ignore
pm.install("pptx")
from pptx import Presentation # type: ignore
from io import BytesIO
pptx_file = BytesIO(file)
prs = Presentation(pptx_file)
for slide in prs.slides:
for shape in slide.shapes:
if hasattr(shape, "text"):
content += shape.text + "\n"
except Exception as e:
error_files = [
{
"file_path": str(file_path.name),
"error_description": "[File Extraction]PPTX processing error",
"original_error": f"Failed to extract text from PPTX: {str(e)}",
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(
error_files, track_id
)
logger.error(
f"[File Extraction]Error processing PPTX {file_path.name}: {str(e)}"
)
return False, track_id
case ".xlsx":
try:
if global_args.document_loading_engine == "DOCLING":
if not pm.is_installed("docling"): # type: ignore
pm.install("docling")
from docling.document_converter import DocumentConverter # type: ignore
converter = DocumentConverter()
result = converter.convert(file_path)
content = result.document.export_to_markdown()
else:
if not pm.is_installed("openpyxl"): # type: ignore
pm.install("openpyxl")
from openpyxl import load_workbook # type: ignore
from io import BytesIO
xlsx_file = BytesIO(file)
wb = load_workbook(xlsx_file)
for sheet in wb:
content += f"Sheet: {sheet.title}\n"
for row in sheet.iter_rows(values_only=True):
content += (
"\t".join(
str(cell) if cell is not None else ""
for cell in row
)
+ "\n"
)
content += "\n"
except Exception as e:
error_files = [
{
"file_path": str(file_path.name),
"error_description": "[File Extraction]XLSX processing error",
"original_error": f"Failed to extract text from XLSX: {str(e)}",
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(
error_files, track_id
)
logger.error(
f"[File Extraction]Error processing XLSX {file_path.name}: {str(e)}"
)
return False, track_id
case _:
error_files = [
{
"file_path": str(file_path.name),
"error_description": f"[File Extraction]Unsupported file type: {ext}",
"original_error": f"File extension {ext} is not supported",
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(error_files, track_id)
logger.error(
f"[File Extraction]Unsupported file type: {file_path.name} (extension {ext})"
)
return False, track_id
except Exception as e:
error_files = [
{
"file_path": str(file_path.name),
"error_description": "[File Extraction]File format processing error",
"original_error": f"Unexpected error during file extracting: {str(e)}",
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(error_files, track_id)
logger.error(
f"[File Extraction]Unexpected error during {file_path.name} extracting: {str(e)}"
)
return False, track_id
# Insert into the RAG queue
if content:
# Check if content contains only whitespace characters
if not content.strip():
error_files = [
{
"file_path": str(file_path.name),
"error_description": "[File Extraction]File contains only whitespace",
"original_error": "File content contains only whitespace characters",
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(error_files, track_id)
logger.warning(
f"[File Extraction]File contains only whitespace characters: {file_path.name}"
)
return False, track_id
try:
await rag.apipeline_enqueue_documents(
content, file_paths=file_path.name, track_id=track_id
)
logger.info(
f"Successfully extracted and enqueued file: {file_path.name}"
)
# Move file to __enqueued__ directory after enqueuing
try:
enqueued_dir = file_path.parent / "__enqueued__"
enqueued_dir.mkdir(exist_ok=True)
# Generate unique filename to avoid conflicts
unique_filename = get_unique_filename_in_enqueued(
enqueued_dir, file_path.name
)
target_path = enqueued_dir / unique_filename
# Move the file
file_path.rename(target_path)
logger.debug(
f"Moved file to enqueued directory: {file_path.name} -> {unique_filename}"
)
except Exception as move_error:
logger.error(
f"Failed to move file {file_path.name} to __enqueued__ directory: {move_error}"
)
# Don't affect the main function's success status
return True, track_id
except Exception as e:
error_files = [
{
"file_path": str(file_path.name),
"error_description": "Document enqueue error",
"original_error": f"Failed to enqueue document: {str(e)}",
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(error_files, track_id)
logger.error(f"Error enqueueing document {file_path.name}: {str(e)}")
return False, track_id
else:
error_files = [
{
"file_path": str(file_path.name),
"error_description": "No content extracted",
"original_error": "No content could be extracted from file",
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(error_files, track_id)
logger.error(f"No content extracted from file: {file_path.name}")
return False, track_id
except Exception as e:
# Catch-all for any unexpected errors
try:
file_size = file_path.stat().st_size if file_path.exists() else 0
except Exception:
file_size = 0
error_files = [
{
"file_path": str(file_path.name),
"error_description": "Unexpected processing error",
"original_error": f"Unexpected error: {str(e)}",
"file_size": file_size,
}
]
await rag.apipeline_enqueue_error_documents(error_files, track_id)
logger.error(f"Enqueuing file {file_path.name} error: {str(e)}")
logger.error(traceback.format_exc())
return False, track_id
finally:
if file_path.name.startswith(temp_prefix):
try:
file_path.unlink()
except Exception as e:
logger.error(f"Error deleting file {file_path}: {str(e)}")
async def pipeline_index_file(rag: LightRAG, file_path: Path, track_id: str = None):
"""Index a file with track_id
Args:
rag: LightRAG instance
file_path: Path to the saved file
track_id: Optional tracking ID
"""
try:
success, returned_track_id = await pipeline_enqueue_file(
rag, file_path, track_id
)
if success:
await rag.apipeline_process_enqueue_documents()
except Exception as e:
logger.error(f"Error indexing file {file_path.name}: {str(e)}")
logger.error(traceback.format_exc())
async def pipeline_index_files(
rag: LightRAG, file_paths: List[Path], track_id: str = None
):
"""Index multiple files sequentially to avoid high CPU load
Args:
rag: LightRAG instance
file_paths: Paths to the files to index
track_id: Optional tracking ID to pass to all files
"""
if not file_paths:
return
try:
enqueued = False
# Use get_pinyin_sort_key for Chinese pinyin sorting
sorted_file_paths = sorted(
file_paths, key=lambda p: get_pinyin_sort_key(str(p))
)
# Process files sequentially with track_id
for file_path in sorted_file_paths:
success, _ = await pipeline_enqueue_file(rag, file_path, track_id)
if success:
enqueued = True
# Process the queue only if at least one file was successfully enqueued
if enqueued:
await rag.apipeline_process_enqueue_documents()
except Exception as e:
logger.error(f"Error indexing files: {str(e)}")
logger.error(traceback.format_exc())
async def pipeline_index_texts(
rag: LightRAG,
texts: List[str],
file_sources: List[str] = None,
track_id: str = None,
):
"""Index a list of texts with track_id
Args:
rag: LightRAG instance
texts: The texts to index
file_sources: Sources of the texts
track_id: Optional tracking ID
"""
if not texts:
return
if file_sources is not None:
if len(file_sources) != 0 and len(file_sources) != len(texts):
[
file_sources.append("unknown_source")
for _ in range(len(file_sources), len(texts))
]
await rag.apipeline_enqueue_documents(
input=texts, file_paths=file_sources, track_id=track_id
)
await rag.apipeline_process_enqueue_documents()
async def run_scanning_process(
rag: LightRAG, doc_manager: DocumentManager, track_id: str = None
):
"""Background task to scan and index documents
Args:
rag: LightRAG instance
doc_manager: DocumentManager instance
track_id: Optional tracking ID to pass to all scanned files
"""
try:
new_files = doc_manager.scan_directory_for_new_files()
total_files = len(new_files)
logger.info(f"Found {total_files} files to index.")
if new_files:
# Check for files with PROCESSED status and filter them out
valid_files = []
processed_files = []
for file_path in new_files:
filename = file_path.name
existing_doc_data = await rag.doc_status.get_doc_by_file_path(filename)
if existing_doc_data and existing_doc_data.get("status") == "processed":
# File is already PROCESSED, skip it with warning
processed_files.append(filename)
logger.warning(f"Skipping already processed file: {filename}")
else:
# File is new or in non-PROCESSED status, add to processing list
valid_files.append(file_path)
# Process valid files (new files + non-PROCESSED status files)
if valid_files:
await pipeline_index_files(rag, valid_files, track_id)
if processed_files:
logger.info(
f"Scanning process completed: {len(valid_files)} files Processed {len(processed_files)} skipped."
)
else:
logger.info(
f"Scanning process completed: {len(valid_files)} files Processed."
)
else:
logger.info(
"No files to process after filtering already processed files."
)
else:
# No new files to index, check if there are any documents in the queue
logger.info(
"No upload file found, check if there are any documents in the queue..."
)
await rag.apipeline_process_enqueue_documents()
except Exception as e:
logger.error(f"Error during scanning process: {str(e)}")
logger.error(traceback.format_exc())
async def background_delete_documents(
rag: LightRAG,
doc_manager: DocumentManager,
doc_ids: List[str],
delete_file: bool = False,
):
"""Background task to delete multiple documents"""
from lightrag.kg.shared_storage import (
get_namespace_data,
get_pipeline_status_lock,
)
pipeline_status = await get_namespace_data("pipeline_status")
pipeline_status_lock = get_pipeline_status_lock()
total_docs = len(doc_ids)
successful_deletions = []
failed_deletions = []
# Double-check pipeline status before proceeding
async with pipeline_status_lock:
if pipeline_status.get("busy", False):
logger.warning("Error: Unexpected pipeline busy state, aborting deletion.")
return # Abort deletion operation
# Set pipeline status to busy for deletion
pipeline_status.update(
{
"busy": True,
"job_name": f"Deleting {total_docs} Documents",
"job_start": datetime.now().isoformat(),
"docs": total_docs,
"batchs": total_docs,
"cur_batch": 0,
"latest_message": "Starting document deletion process",
}
)
# Use slice assignment to clear the list in place
pipeline_status["history_messages"][:] = ["Starting document deletion process"]
try:
# Loop through each document ID and delete them one by one
for i, doc_id in enumerate(doc_ids, 1):
async with pipeline_status_lock:
start_msg = f"Deleting document {i}/{total_docs}: {doc_id}"
logger.info(start_msg)
pipeline_status["cur_batch"] = i
pipeline_status["latest_message"] = start_msg
pipeline_status["history_messages"].append(start_msg)
file_path = "#"
try:
result = await rag.adelete_by_doc_id(doc_id)
file_path = (
getattr(result, "file_path", "-") if "result" in locals() else "-"
)
if result.status == "success":
successful_deletions.append(doc_id)
success_msg = (
f"Document deleted {i}/{total_docs}: {doc_id}[{file_path}]"
)
logger.info(success_msg)
async with pipeline_status_lock:
pipeline_status["history_messages"].append(success_msg)
# Handle file deletion if requested and file_path is available
if (
delete_file
and result.file_path
and result.file_path != "unknown_source"
):
try:
deleted_files = []
# SECURITY FIX: Use secure path validation to prevent arbitrary file deletion
safe_file_path = validate_file_path_security(
result.file_path, doc_manager.input_dir
)
if safe_file_path is None:
# Security violation detected - log and skip file deletion
security_msg = f"Security violation: Unsafe file path detected for deletion - {result.file_path}"
logger.warning(security_msg)
async with pipeline_status_lock:
pipeline_status["latest_message"] = security_msg
pipeline_status["history_messages"].append(
security_msg
)
else:
# check and delete files from input_dir directory
if safe_file_path.exists():
try:
safe_file_path.unlink()
deleted_files.append(safe_file_path.name)
file_delete_msg = f"Successfully deleted input_dir file: {result.file_path}"
logger.info(file_delete_msg)
async with pipeline_status_lock:
pipeline_status["latest_message"] = (
file_delete_msg
)
pipeline_status["history_messages"].append(
file_delete_msg
)
except Exception as file_error:
file_error_msg = f"Failed to delete input_dir file {result.file_path}: {str(file_error)}"
logger.debug(file_error_msg)
async with pipeline_status_lock:
pipeline_status["latest_message"] = (
file_error_msg
)
pipeline_status["history_messages"].append(
file_error_msg
)
# Also check and delete files from __enqueued__ directory
enqueued_dir = doc_manager.input_dir / "__enqueued__"
if enqueued_dir.exists():
# SECURITY FIX: Validate that the file path is safe before processing
# Only proceed if the original path validation passed
base_name = Path(result.file_path).stem
extension = Path(result.file_path).suffix
# Search for exact match and files with numeric suffixes
for enqueued_file in enqueued_dir.glob(
f"{base_name}*{extension}"
):
# Additional security check: ensure enqueued file is within enqueued directory
safe_enqueued_path = (
validate_file_path_security(
enqueued_file.name, enqueued_dir
)
)
if safe_enqueued_path is not None:
try:
enqueued_file.unlink()
deleted_files.append(enqueued_file.name)
logger.info(
f"Successfully deleted enqueued file: {enqueued_file.name}"
)
except Exception as enqueued_error:
file_error_msg = f"Failed to delete enqueued file {enqueued_file.name}: {str(enqueued_error)}"
logger.debug(file_error_msg)
async with pipeline_status_lock:
pipeline_status[
"latest_message"
] = file_error_msg
pipeline_status[
"history_messages"
].append(file_error_msg)
else:
security_msg = f"Security violation: Unsafe enqueued file path detected - {enqueued_file.name}"
logger.warning(security_msg)
if deleted_files == []:
file_error_msg = f"File deletion skipped, missing or unsafe file: {result.file_path}"
logger.warning(file_error_msg)
async with pipeline_status_lock:
pipeline_status["latest_message"] = file_error_msg
pipeline_status["history_messages"].append(
file_error_msg
)
except Exception as file_error:
file_error_msg = f"Failed to delete file {result.file_path}: {str(file_error)}"
logger.error(file_error_msg)
async with pipeline_status_lock:
pipeline_status["latest_message"] = file_error_msg
pipeline_status["history_messages"].append(
file_error_msg
)
elif delete_file:
no_file_msg = (
f"File deletion skipped, missing file path: {doc_id}"
)
logger.warning(no_file_msg)
async with pipeline_status_lock:
pipeline_status["latest_message"] = no_file_msg
pipeline_status["history_messages"].append(no_file_msg)
else:
failed_deletions.append(doc_id)
error_msg = f"Failed to delete {i}/{total_docs}: {doc_id}[{file_path}] - {result.message}"
logger.error(error_msg)
async with pipeline_status_lock:
pipeline_status["latest_message"] = error_msg
pipeline_status["history_messages"].append(error_msg)
except Exception as e:
failed_deletions.append(doc_id)
error_msg = f"Error deleting document {i}/{total_docs}: {doc_id}[{file_path}] - {str(e)}"
logger.error(error_msg)
logger.error(traceback.format_exc())
async with pipeline_status_lock:
pipeline_status["latest_message"] = error_msg
pipeline_status["history_messages"].append(error_msg)
except Exception as e:
error_msg = f"Critical error during batch deletion: {str(e)}"
logger.error(error_msg)
logger.error(traceback.format_exc())
async with pipeline_status_lock:
pipeline_status["history_messages"].append(error_msg)
finally:
# Final summary and check for pending requests
async with pipeline_status_lock:
pipeline_status["busy"] = False
completion_msg = f"Deletion completed: {len(successful_deletions)} successful, {len(failed_deletions)} failed"
pipeline_status["latest_message"] = completion_msg
pipeline_status["history_messages"].append(completion_msg)
# Check if there are pending document indexing requests
has_pending_request = pipeline_status.get("request_pending", False)
# If there are pending requests, start document processing pipeline
if has_pending_request:
try:
logger.info(
"Processing pending document indexing requests after deletion"
)
await rag.apipeline_process_enqueue_documents()
except Exception as e:
logger.error(f"Error processing pending documents after deletion: {e}")
def create_document_routes(
rag: LightRAG, doc_manager: DocumentManager, api_key: Optional[str] = None
):
# Create combined auth dependency for document routes
combined_auth = get_combined_auth_dependency(api_key)
@router.post(
"/scan", response_model=ScanResponse, dependencies=[Depends(combined_auth)]
)
async def scan_for_new_documents(background_tasks: BackgroundTasks):
"""
Trigger the scanning process for new documents.
This endpoint initiates a background task that scans the input directory for new documents
and processes them. If a scanning process is already running, it returns a status indicating
that fact.
Returns:
ScanResponse: A response object containing the scanning status and track_id
"""
# Generate track_id with "scan" prefix for scanning operation
track_id = generate_track_id("scan")
# Start the scanning process in the background with track_id
background_tasks.add_task(run_scanning_process, rag, doc_manager, track_id)
return ScanResponse(
status="scanning_started",
message="Scanning process has been initiated in the background",
track_id=track_id,
)
@router.post(
"/upload", response_model=InsertResponse, dependencies=[Depends(combined_auth)]
)
async def upload_to_input_dir(
background_tasks: BackgroundTasks, file: UploadFile = File(...)
):
"""
Upload a file to the input directory and index it.
This API endpoint accepts a file through an HTTP POST request, checks if the
uploaded file is of a supported type, saves it in the specified input directory,
indexes it for retrieval, and returns a success status with relevant details.
Args:
background_tasks: FastAPI BackgroundTasks for async processing
file (UploadFile): The file to be uploaded. It must have an allowed extension.
Returns:
InsertResponse: A response object containing the upload status and a message.
status can be "success", "duplicated", or error is thrown.
Raises:
HTTPException: If the file type is not supported (400) or other errors occur (500).
"""
try:
# Sanitize filename to prevent Path Traversal attacks
safe_filename = sanitize_filename(file.filename, doc_manager.input_dir)
if not doc_manager.is_supported_file(safe_filename):
raise HTTPException(
status_code=400,
detail=f"Unsupported file type. Supported types: {doc_manager.supported_extensions}",
)
# Check if filename already exists in doc_status storage
existing_doc_data = await rag.doc_status.get_doc_by_file_path(safe_filename)
if existing_doc_data:
# Get document status information for error message
status = existing_doc_data.get("status", "unknown")
return InsertResponse(
status="duplicated",
message=f"File '{safe_filename}' already exists in document storage (Status: {status}).",
track_id="",
)
file_path = doc_manager.input_dir / safe_filename
# Check if file already exists in file system
if file_path.exists():
return InsertResponse(
status="duplicated",
message=f"File '{safe_filename}' already exists in the input directory.",
track_id="",
)
with open(file_path, "wb") as buffer:
shutil.copyfileobj(file.file, buffer)
track_id = generate_track_id("upload")
# Add to background tasks and get track_id
background_tasks.add_task(pipeline_index_file, rag, file_path, track_id)
return InsertResponse(
status="success",
message=f"File '{safe_filename}' uploaded successfully. Processing will continue in background.",
track_id=track_id,
)
except Exception as e:
logger.error(f"Error /documents/upload: {file.filename}: {str(e)}")
logger.error(traceback.format_exc())
raise HTTPException(status_code=500, detail=str(e))
@router.post(
"/text", response_model=InsertResponse, dependencies=[Depends(combined_auth)]
)
async def insert_text(
request: InsertTextRequest, background_tasks: BackgroundTasks
):
"""
Insert text into the RAG system.
This endpoint allows you to insert text data into the RAG system for later retrieval
and use in generating responses.
Args:
request (InsertTextRequest): The request body containing the text to be inserted.
background_tasks: FastAPI BackgroundTasks for async processing
Returns:
InsertResponse: A response object containing the status of the operation.
Raises:
HTTPException: If an error occurs during text processing (500).
"""
try:
# Check if file_source already exists in doc_status storage
if (
request.file_source
and request.file_source.strip()
and request.file_source != "unknown_source"
):
existing_doc_data = await rag.doc_status.get_doc_by_file_path(
request.file_source
)
if existing_doc_data:
# Get document status information for error message
status = existing_doc_data.get("status", "unknown")
return InsertResponse(
status="duplicated",
message=f"File source '{request.file_source}' already exists in document storage (Status: {status}).",
track_id="",
)
# Generate track_id for text insertion
track_id = generate_track_id("insert")
background_tasks.add_task(
pipeline_index_texts,
rag,
[request.text],
file_sources=[request.file_source],
track_id=track_id,
)
return InsertResponse(
status="success",
message="Text successfully received. Processing will continue in background.",
track_id=track_id,
)
except Exception as e:
logger.error(f"Error /documents/text: {str(e)}")
logger.error(traceback.format_exc())
raise HTTPException(status_code=500, detail=str(e))
@router.post(
"/texts",
response_model=InsertResponse,
dependencies=[Depends(combined_auth)],
)
async def insert_texts(
request: InsertTextsRequest, background_tasks: BackgroundTasks
):
"""
Insert multiple texts into the RAG system.
This endpoint allows you to insert multiple text entries into the RAG system
in a single request.
Args:
request (InsertTextsRequest): The request body containing the list of texts.
background_tasks: FastAPI BackgroundTasks for async processing
Returns:
InsertResponse: A response object containing the status of the operation.
Raises:
HTTPException: If an error occurs during text processing (500).
"""
try:
# Check if any file_sources already exist in doc_status storage
if request.file_sources:
for file_source in request.file_sources:
if (
file_source
and file_source.strip()
and file_source != "unknown_source"
):
existing_doc_data = await rag.doc_status.get_doc_by_file_path(
file_source
)
if existing_doc_data:
# Get document status information for error message
status = existing_doc_data.get("status", "unknown")
return InsertResponse(
status="duplicated",
message=f"File source '{file_source}' already exists in document storage (Status: {status}).",
track_id="",
)
# Generate track_id for texts insertion
track_id = generate_track_id("insert")
background_tasks.add_task(
pipeline_index_texts,
rag,
request.texts,
file_sources=request.file_sources,
track_id=track_id,
)
return InsertResponse(
status="success",
message="Texts successfully received. Processing will continue in background.",
track_id=track_id,
)
except Exception as e:
logger.error(f"Error /documents/texts: {str(e)}")
logger.error(traceback.format_exc())
raise HTTPException(status_code=500, detail=str(e))
@router.delete(
"", response_model=ClearDocumentsResponse, dependencies=[Depends(combined_auth)]
)
async def clear_documents():
"""
Clear all documents from the RAG system.
This endpoint deletes all documents, entities, relationships, and files from the system.
It uses the storage drop methods to properly clean up all data and removes all files
from the input directory.
Returns:
ClearDocumentsResponse: A response object containing the status and message.
- status="success": All documents and files were successfully cleared.
- status="partial_success": Document clear job exit with some errors.
- status="busy": Operation could not be completed because the pipeline is busy.
- status="fail": All storage drop operations failed, with message
- message: Detailed information about the operation results, including counts
of deleted files and any errors encountered.
Raises:
HTTPException: Raised when a serious error occurs during the clearing process,
with status code 500 and error details in the detail field.
"""
from lightrag.kg.shared_storage import (
get_namespace_data,
get_pipeline_status_lock,
)
# Get pipeline status and lock
pipeline_status = await get_namespace_data("pipeline_status")
pipeline_status_lock = get_pipeline_status_lock()
# Check and set status with lock
async with pipeline_status_lock:
if pipeline_status.get("busy", False):
return ClearDocumentsResponse(
status="busy",
message="Cannot clear documents while pipeline is busy",
)
# Set busy to true
pipeline_status.update(
{
"busy": True,
"job_name": "Clearing Documents",
"job_start": datetime.now().isoformat(),
"docs": 0,
"batchs": 0,
"cur_batch": 0,
"request_pending": False, # Clear any previous request
"latest_message": "Starting document clearing process",
}
)
# Cleaning history_messages without breaking it as a shared list object
del pipeline_status["history_messages"][:]
pipeline_status["history_messages"].append(
"Starting document clearing process"
)
try:
# Use drop method to clear all data
drop_tasks = []
storages = [
rag.text_chunks,
rag.full_docs,
rag.full_entities,
rag.full_relations,
rag.entities_vdb,
rag.relationships_vdb,
rag.chunks_vdb,
rag.chunk_entity_relation_graph,
rag.doc_status,
]
# Log storage drop start
if "history_messages" in pipeline_status:
pipeline_status["history_messages"].append(
"Starting to drop storage components"
)
for storage in storages:
if storage is not None:
drop_tasks.append(storage.drop())
# Wait for all drop tasks to complete
drop_results = await asyncio.gather(*drop_tasks, return_exceptions=True)
# Check for errors and log results
errors = []
storage_success_count = 0
storage_error_count = 0
for i, result in enumerate(drop_results):
storage_name = storages[i].__class__.__name__
if isinstance(result, Exception):
error_msg = f"Error dropping {storage_name}: {str(result)}"
errors.append(error_msg)
logger.error(error_msg)
storage_error_count += 1
else:
namespace = storages[i].namespace
workspace = storages[i].workspace
logger.info(
f"Successfully dropped {storage_name}: {workspace}/{namespace}"
)
storage_success_count += 1
# Log storage drop results
if "history_messages" in pipeline_status:
if storage_error_count > 0:
pipeline_status["history_messages"].append(
f"Dropped {storage_success_count} storage components with {storage_error_count} errors"
)
else:
pipeline_status["history_messages"].append(
f"Successfully dropped all {storage_success_count} storage components"
)
# If all storage operations failed, return error status and don't proceed with file deletion
if storage_success_count == 0 and storage_error_count > 0:
error_message = "All storage drop operations failed. Aborting document clearing process."
logger.error(error_message)
if "history_messages" in pipeline_status:
pipeline_status["history_messages"].append(error_message)
return ClearDocumentsResponse(status="fail", message=error_message)
# Log file deletion start
if "history_messages" in pipeline_status:
pipeline_status["history_messages"].append(
"Starting to delete files in input directory"
)
# Delete only files in the current directory, preserve files in subdirectories
deleted_files_count = 0
file_errors_count = 0
for file_path in doc_manager.input_dir.glob("*"):
if file_path.is_file():
try:
file_path.unlink()
deleted_files_count += 1
except Exception as e:
logger.error(f"Error deleting file {file_path}: {str(e)}")
file_errors_count += 1
# Log file deletion results
if "history_messages" in pipeline_status:
if file_errors_count > 0:
pipeline_status["history_messages"].append(
f"Deleted {deleted_files_count} files with {file_errors_count} errors"
)
errors.append(f"Failed to delete {file_errors_count} files")
else:
pipeline_status["history_messages"].append(
f"Successfully deleted {deleted_files_count} files"
)
# Prepare final result message
final_message = ""
if errors:
final_message = f"Cleared documents with some errors. Deleted {deleted_files_count} files."
status = "partial_success"
else:
final_message = f"All documents cleared successfully. Deleted {deleted_files_count} files."
status = "success"
# Log final result
if "history_messages" in pipeline_status:
pipeline_status["history_messages"].append(final_message)
# Return response based on results
return ClearDocumentsResponse(status=status, message=final_message)
except Exception as e:
error_msg = f"Error clearing documents: {str(e)}"
logger.error(error_msg)
logger.error(traceback.format_exc())
if "history_messages" in pipeline_status:
pipeline_status["history_messages"].append(error_msg)
raise HTTPException(status_code=500, detail=str(e))
finally:
# Reset busy status after completion
async with pipeline_status_lock:
pipeline_status["busy"] = False
completion_msg = "Document clearing process completed"
pipeline_status["latest_message"] = completion_msg
if "history_messages" in pipeline_status:
pipeline_status["history_messages"].append(completion_msg)
@router.get(
"/pipeline_status",
dependencies=[Depends(combined_auth)],
response_model=PipelineStatusResponse,
)
async def get_pipeline_status() -> PipelineStatusResponse:
"""
Get the current status of the document indexing pipeline.
This endpoint returns information about the current state of the document processing pipeline,
including the processing status, progress information, and history messages.
Returns:
PipelineStatusResponse: A response object containing:
- autoscanned (bool): Whether auto-scan has started
- busy (bool): Whether the pipeline is currently busy
- job_name (str): Current job name (e.g., indexing files/indexing texts)
- job_start (str, optional): Job start time as ISO format string
- docs (int): Total number of documents to be indexed
- batchs (int): Number of batches for processing documents
- cur_batch (int): Current processing batch
- request_pending (bool): Flag for pending request for processing
- latest_message (str): Latest message from pipeline processing
- history_messages (List[str], optional): List of history messages (limited to latest 1000 entries,
with truncation message if more than 1000 messages exist)
Raises:
HTTPException: If an error occurs while retrieving pipeline status (500)
"""
try:
from lightrag.kg.shared_storage import (
get_namespace_data,
get_all_update_flags_status,
)
pipeline_status = await get_namespace_data("pipeline_status")
# Get update flags status for all namespaces
update_status = await get_all_update_flags_status()
# Convert MutableBoolean objects to regular boolean values
processed_update_status = {}
for namespace, flags in update_status.items():
processed_flags = []
for flag in flags:
# Handle both multiprocess and single process cases
if hasattr(flag, "value"):
processed_flags.append(bool(flag.value))
else:
processed_flags.append(bool(flag))
processed_update_status[namespace] = processed_flags
# Convert to regular dict if it's a Manager.dict
status_dict = dict(pipeline_status)
# Add processed update_status to the status dictionary
status_dict["update_status"] = processed_update_status
# Convert history_messages to a regular list if it's a Manager.list
# and limit to latest 1000 entries with truncation message if needed
if "history_messages" in status_dict:
history_list = list(status_dict["history_messages"])
total_count = len(history_list)
if total_count > 1000:
# Calculate truncated message count
truncated_count = total_count - 1000
# Take only the latest 1000 messages
latest_messages = history_list[-1000:]
# Add truncation message at the beginning
truncation_message = (
f"[Truncated history messages: {truncated_count}/{total_count}]"
)
status_dict["history_messages"] = [
truncation_message
] + latest_messages
else:
# No truncation needed, return all messages
status_dict["history_messages"] = history_list
# Ensure job_start is properly formatted as a string with timezone information
if "job_start" in status_dict and status_dict["job_start"]:
# Use format_datetime to ensure consistent formatting
status_dict["job_start"] = format_datetime(status_dict["job_start"])
return PipelineStatusResponse(**status_dict)
except Exception as e:
logger.error(f"Error getting pipeline status: {str(e)}")
logger.error(traceback.format_exc())
raise HTTPException(status_code=500, detail=str(e))
# TODO: Deprecated
@router.get(
"", response_model=DocsStatusesResponse, dependencies=[Depends(combined_auth)]
)
async def documents() -> DocsStatusesResponse:
"""
Get the status of all documents in the system. This endpoint is deprecated; use /documents/paginated instead.
To prevent excessive resource consumption, a maximum of 1,000 records is returned.
This endpoint retrieves the current status of all documents, grouped by their
processing status (PENDING, PROCESSING, PROCESSED, FAILED). The results are
limited to 1000 total documents with fair distribution across all statuses.
Returns:
DocsStatusesResponse: A response object containing a dictionary where keys are
DocStatus values and values are lists of DocStatusResponse
objects representing documents in each status category.
Maximum 1000 documents total will be returned.
Raises:
HTTPException: If an error occurs while retrieving document statuses (500).
"""
try:
statuses = (
DocStatus.PENDING,
DocStatus.PROCESSING,
DocStatus.PROCESSED,
DocStatus.FAILED,
)
tasks = [rag.get_docs_by_status(status) for status in statuses]
results: List[Dict[str, DocProcessingStatus]] = await asyncio.gather(*tasks)
response = DocsStatusesResponse()
total_documents = 0
max_documents = 1000
# Convert results to lists for easier processing
status_documents = []
for idx, result in enumerate(results):
status = statuses[idx]
docs_list = []
for doc_id, doc_status in result.items():
docs_list.append((doc_id, doc_status))
status_documents.append((status, docs_list))
# Fair distribution: round-robin across statuses
status_indices = [0] * len(
status_documents
) # Track current index for each status
current_status_idx = 0
while total_documents < max_documents:
# Check if we have any documents left to process
has_remaining = False
for status_idx, (status, docs_list) in enumerate(status_documents):
if status_indices[status_idx] < len(docs_list):
has_remaining = True
break
if not has_remaining:
break
# Try to get a document from the current status
status, docs_list = status_documents[current_status_idx]
current_index = status_indices[current_status_idx]
if current_index < len(docs_list):
doc_id, doc_status = docs_list[current_index]
if status not in response.statuses:
response.statuses[status] = []
response.statuses[status].append(
DocStatusResponse(
id=doc_id,
content_summary=doc_status.content_summary,
content_length=doc_status.content_length,
status=doc_status.status,
created_at=format_datetime(doc_status.created_at),
updated_at=format_datetime(doc_status.updated_at),
track_id=doc_status.track_id,
chunks_count=doc_status.chunks_count,
error_msg=doc_status.error_msg,
metadata=doc_status.metadata,
file_path=doc_status.file_path,
)
)
status_indices[current_status_idx] += 1
total_documents += 1
# Move to next status (round-robin)
current_status_idx = (current_status_idx + 1) % len(status_documents)
return response
except Exception as e:
logger.error(f"Error GET /documents: {str(e)}")
logger.error(traceback.format_exc())
raise HTTPException(status_code=500, detail=str(e))
class DeleteDocByIdResponse(BaseModel):
"""Response model for single document deletion operation."""
status: Literal["deletion_started", "busy", "not_allowed"] = Field(
description="Status of the deletion operation"
)
message: str = Field(description="Message describing the operation result")
doc_id: str = Field(description="The ID of the document to delete")
@router.delete(
"/delete_document",
response_model=DeleteDocByIdResponse,
dependencies=[Depends(combined_auth)],
summary="Delete a document and all its associated data by its ID.",
)
async def delete_document(
delete_request: DeleteDocRequest,
background_tasks: BackgroundTasks,
) -> DeleteDocByIdResponse:
"""
Delete documents and all their associated data by their IDs using background processing.
Deletes specific documents and all their associated data, including their status,
text chunks, vector embeddings, and any related graph data.
The deletion process runs in the background to avoid blocking the client connection.
It is disabled when llm cache for entity extraction is disabled.
This operation is irreversible and will interact with the pipeline status.
Args:
delete_request (DeleteDocRequest): The request containing the document IDs and delete_file options.
background_tasks: FastAPI BackgroundTasks for async processing
Returns:
DeleteDocByIdResponse: The result of the deletion operation.
- status="deletion_started": The document deletion has been initiated in the background.
- status="busy": The pipeline is busy with another operation.
- status="not_allowed": Operation not allowed when LLM cache for entity extraction is disabled.
Raises:
HTTPException:
- 500: If an unexpected internal error occurs during initialization.
"""
doc_ids = delete_request.doc_ids
# The rag object is initialized from the server startup args,
# so we can access its properties here.
if not rag.enable_llm_cache_for_entity_extract:
return DeleteDocByIdResponse(
status="not_allowed",
message="Operation not allowed when LLM cache for entity extraction is disabled.",
doc_id=", ".join(delete_request.doc_ids),
)
try:
from lightrag.kg.shared_storage import get_namespace_data
pipeline_status = await get_namespace_data("pipeline_status")
# Check if pipeline is busy
if pipeline_status.get("busy", False):
return DeleteDocByIdResponse(
status="busy",
message="Cannot delete documents while pipeline is busy",
doc_id=", ".join(doc_ids),
)
# Add deletion task to background tasks
background_tasks.add_task(
background_delete_documents,
rag,
doc_manager,
doc_ids,
delete_request.delete_file,
)
return DeleteDocByIdResponse(
status="deletion_started",
message=f"Document deletion for {len(doc_ids)} documents has been initiated. Processing will continue in background.",
doc_id=", ".join(doc_ids),
)
except Exception as e:
error_msg = f"Error initiating document deletion for {delete_request.doc_ids}: {str(e)}"
logger.error(error_msg)
logger.error(traceback.format_exc())
raise HTTPException(status_code=500, detail=error_msg)
@router.post(
"/clear_cache",
response_model=ClearCacheResponse,
dependencies=[Depends(combined_auth)],
)
async def clear_cache(request: ClearCacheRequest):
"""
Clear all cache data from the LLM response cache storage.
This endpoint clears all cached LLM responses regardless of mode.
The request body is accepted for API compatibility but is ignored.
Args:
request (ClearCacheRequest): The request body (ignored for compatibility).
Returns:
ClearCacheResponse: A response object containing the status and message.
Raises:
HTTPException: If an error occurs during cache clearing (500).
"""
try:
# Call the aclear_cache method (no modes parameter)
await rag.aclear_cache()
# Prepare success message
message = "Successfully cleared all cache"
return ClearCacheResponse(status="success", message=message)
except Exception as e:
logger.error(f"Error clearing cache: {str(e)}")
logger.error(traceback.format_exc())
raise HTTPException(status_code=500, detail=str(e))
@router.delete(
"/delete_entity",
response_model=DeletionResult,
dependencies=[Depends(combined_auth)],
)
async def delete_entity(request: DeleteEntityRequest):
"""
Delete an entity and all its relationships from the knowledge graph.
Args:
request (DeleteEntityRequest): The request body containing the entity name.
Returns:
DeletionResult: An object containing the outcome of the deletion process.
Raises:
HTTPException: If the entity is not found (404) or an error occurs (500).
"""
try:
result = await rag.adelete_by_entity(entity_name=request.entity_name)
if result.status == "not_found":
raise HTTPException(status_code=404, detail=result.message)
if result.status == "fail":
raise HTTPException(status_code=500, detail=result.message)
# Set doc_id to empty string since this is an entity operation, not document
result.doc_id = ""
return result
except HTTPException:
raise
except Exception as e:
error_msg = f"Error deleting entity '{request.entity_name}': {str(e)}"
logger.error(error_msg)
logger.error(traceback.format_exc())
raise HTTPException(status_code=500, detail=error_msg)
@router.delete(
"/delete_relation",
response_model=DeletionResult,
dependencies=[Depends(combined_auth)],
)
async def delete_relation(request: DeleteRelationRequest):
"""
Delete a relationship between two entities from the knowledge graph.
Args:
request (DeleteRelationRequest): The request body containing the source and target entity names.
Returns:
DeletionResult: An object containing the outcome of the deletion process.
Raises:
HTTPException: If the relation is not found (404) or an error occurs (500).
"""
try:
result = await rag.adelete_by_relation(
source_entity=request.source_entity,
target_entity=request.target_entity,
)
if result.status == "not_found":
raise HTTPException(status_code=404, detail=result.message)
if result.status == "fail":
raise HTTPException(status_code=500, detail=result.message)
# Set doc_id to empty string since this is a relation operation, not document
result.doc_id = ""
return result
except HTTPException:
raise
except Exception as e:
error_msg = f"Error deleting relation from '{request.source_entity}' to '{request.target_entity}': {str(e)}"
logger.error(error_msg)
logger.error(traceback.format_exc())
raise HTTPException(status_code=500, detail=error_msg)
@router.get(
"/track_status/{track_id}",
response_model=TrackStatusResponse,
dependencies=[Depends(combined_auth)],
)
async def get_track_status(track_id: str) -> TrackStatusResponse:
"""
Get the processing status of documents by tracking ID.
This endpoint retrieves all documents associated with a specific tracking ID,
allowing users to monitor the processing progress of their uploaded files or inserted texts.
Args:
track_id (str): The tracking ID returned from upload, text, or texts endpoints
Returns:
TrackStatusResponse: A response object containing:
- track_id: The tracking ID
- documents: List of documents associated with this track_id
- total_count: Total number of documents for this track_id
Raises:
HTTPException: If track_id is invalid (400) or an error occurs (500).
"""
try:
# Validate track_id
if not track_id or not track_id.strip():
raise HTTPException(status_code=400, detail="Track ID cannot be empty")
track_id = track_id.strip()
# Get documents by track_id
docs_by_track_id = await rag.aget_docs_by_track_id(track_id)
# Convert to response format
documents = []
status_summary = {}
for doc_id, doc_status in docs_by_track_id.items():
documents.append(
DocStatusResponse(
id=doc_id,
content_summary=doc_status.content_summary,
content_length=doc_status.content_length,
status=doc_status.status,
created_at=format_datetime(doc_status.created_at),
updated_at=format_datetime(doc_status.updated_at),
track_id=doc_status.track_id,
chunks_count=doc_status.chunks_count,
error_msg=doc_status.error_msg,
metadata=doc_status.metadata,
file_path=doc_status.file_path,
)
)
# Build status summary
# Handle both DocStatus enum and string cases for robust deserialization
status_key = str(doc_status.status)
status_summary[status_key] = status_summary.get(status_key, 0) + 1
return TrackStatusResponse(
track_id=track_id,
documents=documents,
total_count=len(documents),
status_summary=status_summary,
)
except HTTPException:
raise
except Exception as e:
logger.error(f"Error getting track status for {track_id}: {str(e)}")
logger.error(traceback.format_exc())
raise HTTPException(status_code=500, detail=str(e))
@router.post(
"/paginated",
response_model=PaginatedDocsResponse,
dependencies=[Depends(combined_auth)],
)
async def get_documents_paginated(
request: DocumentsRequest,
) -> PaginatedDocsResponse:
"""
Get documents with pagination support.
This endpoint retrieves documents with pagination, filtering, and sorting capabilities.
It provides better performance for large document collections by loading only the
requested page of data.
Args:
request (DocumentsRequest): The request body containing pagination parameters
Returns:
PaginatedDocsResponse: A response object containing:
- documents: List of documents for the current page
- pagination: Pagination information (page, total_count, etc.)
- status_counts: Count of documents by status for all documents
Raises:
HTTPException: If an error occurs while retrieving documents (500).
"""
try:
# Get paginated documents and status counts in parallel
docs_task = rag.doc_status.get_docs_paginated(
status_filter=request.status_filter,
page=request.page,
page_size=request.page_size,
sort_field=request.sort_field,
sort_direction=request.sort_direction,
)
status_counts_task = rag.doc_status.get_all_status_counts()
# Execute both queries in parallel
(documents_with_ids, total_count), status_counts = await asyncio.gather(
docs_task, status_counts_task
)
# Convert documents to response format
doc_responses = []
for doc_id, doc in documents_with_ids:
doc_responses.append(
DocStatusResponse(
id=doc_id,
content_summary=doc.content_summary,
content_length=doc.content_length,
status=doc.status,
created_at=format_datetime(doc.created_at),
updated_at=format_datetime(doc.updated_at),
track_id=doc.track_id,
chunks_count=doc.chunks_count,
error_msg=doc.error_msg,
metadata=doc.metadata,
file_path=doc.file_path,
)
)
# Calculate pagination info
total_pages = (total_count + request.page_size - 1) // request.page_size
has_next = request.page < total_pages
has_prev = request.page > 1
pagination = PaginationInfo(
page=request.page,
page_size=request.page_size,
total_count=total_count,
total_pages=total_pages,
has_next=has_next,
has_prev=has_prev,
)
return PaginatedDocsResponse(
documents=doc_responses,
pagination=pagination,
status_counts=status_counts,
)
except Exception as e:
logger.error(f"Error getting paginated documents: {str(e)}")
logger.error(traceback.format_exc())
raise HTTPException(status_code=500, detail=str(e))
@router.get(
"/status_counts",
response_model=StatusCountsResponse,
dependencies=[Depends(combined_auth)],
)
async def get_document_status_counts() -> StatusCountsResponse:
"""
Get counts of documents by status.
This endpoint retrieves the count of documents in each processing status
(PENDING, PROCESSING, PROCESSED, FAILED) for all documents in the system.
Returns:
StatusCountsResponse: A response object containing status counts
Raises:
HTTPException: If an error occurs while retrieving status counts (500).
"""
try:
status_counts = await rag.doc_status.get_all_status_counts()
return StatusCountsResponse(status_counts=status_counts)
except Exception as e:
logger.error(f"Error getting document status counts: {str(e)}")
logger.error(traceback.format_exc())
raise HTTPException(status_code=500, detail=str(e))
return router
|