File size: 99,503 Bytes
395201c |
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 |
# +-----------------------------------------------+
# | |
# | Give Feedback / Get Help |
# | https://github.com/BerriAI/litellm/issues/new |
# | |
# +-----------------------------------------------+
#
# Thank you ! We ❤️ you! - Krrish & Ishaan
import os, openai, sys, json, inspect, uuid, datetime, threading
from typing import Any
from functools import partial
import dotenv, traceback, random, asyncio, time, contextvars
from copy import deepcopy
import httpx
import litellm
from litellm import ( # type: ignore
client,
exception_type,
get_optional_params,
get_litellm_params,
Logging,
)
from litellm.utils import (
get_secret,
CustomStreamWrapper,
read_config_args,
completion_with_fallbacks,
get_llm_provider,
get_api_key,
mock_completion_streaming_obj,
convert_to_model_response_object,
token_counter,
Usage
)
from .llms import (
anthropic,
together_ai,
ai21,
sagemaker,
bedrock,
huggingface_restapi,
replicate,
aleph_alpha,
nlp_cloud,
baseten,
vllm,
ollama,
cohere,
petals,
oobabooga,
palm,
vertex_ai,
maritalk)
from .llms.openai import OpenAIChatCompletion, OpenAITextCompletion
from .llms.azure import AzureChatCompletion
from .llms.huggingface_restapi import Huggingface
from .llms.prompt_templates.factory import prompt_factory, custom_prompt, function_call_prompt
import tiktoken
from concurrent.futures import ThreadPoolExecutor
from typing import Callable, List, Optional, Dict, Union, Mapping
encoding = tiktoken.get_encoding("cl100k_base")
from litellm.utils import (
get_secret,
CustomStreamWrapper,
TextCompletionStreamWrapper,
ModelResponse,
TextCompletionResponse,
TextChoices,
EmbeddingResponse,
read_config_args,
Choices,
Message
)
####### ENVIRONMENT VARIABLES ###################
dotenv.load_dotenv() # Loading env variables using dotenv
openai_chat_completions = OpenAIChatCompletion()
openai_text_completions = OpenAITextCompletion()
azure_chat_completions = AzureChatCompletion()
huggingface = Huggingface()
####### COMPLETION ENDPOINTS ################
class LiteLLM:
def __init__(self, *,
api_key=None,
organization: Optional[str] = None,
base_url: Optional[str]= None,
timeout: Optional[float] = 600,
max_retries: Optional[int] = litellm.num_retries,
default_headers: Optional[Mapping[str, str]] = None,):
self.params = locals()
self.chat = Chat(self.params)
class Chat():
def __init__(self, params):
self.params = params
self.completions = Completions(self.params)
class Completions():
def __init__(self, params):
self.params = params
def create(self, model, messages, **kwargs):
for k, v in kwargs.items():
self.params[k] = v
response = completion(model=model, messages=messages, **self.params)
return response
@client
async def acompletion(*args, **kwargs):
"""
Asynchronously executes a litellm.completion() call for any of litellm supported llms (example gpt-4, gpt-3.5-turbo, claude-2, command-nightly)
Parameters:
model (str): The name of the language model to use for text completion. see all supported LLMs: https://docs.litellm.ai/docs/providers/
messages (List): A list of message objects representing the conversation context (default is an empty list).
OPTIONAL PARAMS
functions (List, optional): A list of functions to apply to the conversation messages (default is an empty list).
function_call (str, optional): The name of the function to call within the conversation (default is an empty string).
temperature (float, optional): The temperature parameter for controlling the randomness of the output (default is 1.0).
top_p (float, optional): The top-p parameter for nucleus sampling (default is 1.0).
n (int, optional): The number of completions to generate (default is 1).
stream (bool, optional): If True, return a streaming response (default is False).
stop(string/list, optional): - Up to 4 sequences where the LLM API will stop generating further tokens.
max_tokens (integer, optional): The maximum number of tokens in the generated completion (default is infinity).
presence_penalty (float, optional): It is used to penalize new tokens based on their existence in the text so far.
frequency_penalty: It is used to penalize new tokens based on their frequency in the text so far.
logit_bias (dict, optional): Used to modify the probability of specific tokens appearing in the completion.
user (str, optional): A unique identifier representing your end-user. This can help the LLM provider to monitor and detect abuse.
metadata (dict, optional): Pass in additional metadata to tag your completion calls - eg. prompt version, details, etc.
api_base (str, optional): Base URL for the API (default is None).
api_version (str, optional): API version (default is None).
api_key (str, optional): API key (default is None).
model_list (list, optional): List of api base, version, keys
LITELLM Specific Params
mock_response (str, optional): If provided, return a mock completion response for testing or debugging purposes (default is None).
force_timeout (int, optional): The maximum execution time in seconds for the completion request (default is 600).
custom_llm_provider (str, optional): Used for Non-OpenAI LLMs, Example usage for bedrock, set model="amazon.titan-tg1-large" and custom_llm_provider="bedrock"
Returns:
ModelResponse: A response object containing the generated completion and associated metadata.
Notes:
- This function is an asynchronous version of the `completion` function.
- The `completion` function is called using `run_in_executor` to execute synchronously in the event loop.
- If `stream` is True, the function returns an async generator that yields completion lines.
"""
loop = asyncio.get_event_loop()
model = args[0] if len(args) > 0 else kwargs["model"]
### PASS ARGS TO COMPLETION ###
kwargs["acompletion"] = True
custom_llm_provider = None
try:
# Use a partial function to pass your keyword arguments
func = partial(completion, *args, **kwargs)
# Add the context to the function
ctx = contextvars.copy_context()
func_with_context = partial(ctx.run, func)
_, custom_llm_provider, _, _ = get_llm_provider(model=model, api_base=kwargs.get("api_base", None))
if (custom_llm_provider == "openai"
or custom_llm_provider == "azure"
or custom_llm_provider == "custom_openai"
or custom_llm_provider == "anyscale"
or custom_llm_provider == "openrouter"
or custom_llm_provider == "deepinfra"
or custom_llm_provider == "perplexity"
or custom_llm_provider == "text-completion-openai"
or custom_llm_provider == "huggingface"): # currently implemented aiohttp calls for just azure and openai, soon all.
if kwargs.get("stream", False):
response = completion(*args, **kwargs)
else:
# Await normally
init_response = await loop.run_in_executor(None, func_with_context)
if isinstance(init_response, dict) or isinstance(init_response, ModelResponse): ## CACHING SCENARIO
response = init_response
elif asyncio.iscoroutine(init_response):
response = await init_response
else:
# Call the synchronous function using run_in_executor
response = await loop.run_in_executor(None, func_with_context)
if kwargs.get("stream", False): # return an async generator
return _async_streaming(response=response, model=model, custom_llm_provider=custom_llm_provider, args=args)
else:
return response
except Exception as e:
custom_llm_provider = custom_llm_provider or "openai"
raise exception_type(
model=model, custom_llm_provider=custom_llm_provider, original_exception=e, completion_kwargs=args,
)
async def _async_streaming(response, model, custom_llm_provider, args):
try:
async for line in response:
yield line
except Exception as e:
raise exception_type(
model=model, custom_llm_provider=custom_llm_provider, original_exception=e, completion_kwargs=args,
)
def mock_completion(model: str, messages: List, stream: Optional[bool] = False, mock_response: str = "This is a mock request", **kwargs):
"""
Generate a mock completion response for testing or debugging purposes.
This is a helper function that simulates the response structure of the OpenAI completion API.
Parameters:
model (str): The name of the language model for which the mock response is generated.
messages (List): A list of message objects representing the conversation context.
stream (bool, optional): If True, returns a mock streaming response (default is False).
mock_response (str, optional): The content of the mock response (default is "This is a mock request").
**kwargs: Additional keyword arguments that can be used but are not required.
Returns:
litellm.ModelResponse: A ModelResponse simulating a completion response with the specified model, messages, and mock response.
Raises:
Exception: If an error occurs during the generation of the mock completion response.
Note:
- This function is intended for testing or debugging purposes to generate mock completion responses.
- If 'stream' is True, it returns a response that mimics the behavior of a streaming completion.
"""
try:
model_response = ModelResponse(stream=stream)
if stream is True:
# don't try to access stream object,
response = mock_completion_streaming_obj(model_response, mock_response=mock_response, model=model)
return response
model_response["choices"][0]["message"]["content"] = mock_response
model_response["created"] = int(time.time())
model_response["model"] = model
return model_response
except:
traceback.print_exc()
raise Exception("Mock completion response failed")
@client
def completion(
model: str,
# Optional OpenAI params: see https://platform.openai.com/docs/api-reference/chat/create
messages: List = [],
functions: List = [],
function_call: str = "", # optional params
timeout: Optional[Union[float, int]] = None,
temperature: Optional[float] = None,
top_p: Optional[float] = None,
n: Optional[int] = None,
stream: Optional[bool] = None,
stop=None,
max_tokens: Optional[float] = None,
presence_penalty: Optional[float] = None,
frequency_penalty: Optional[float]=None,
logit_bias: Optional[dict] = None,
user: Optional[str] = None,
# openai v1.0+ new params
response_format: Optional[dict] = None,
seed: Optional[int] = None,
tools: Optional[List] = None,
tool_choice: Optional[str] = None,
deployment_id = None,
# set api_base, api_version, api_key
base_url: Optional[str] = None,
api_version: Optional[str] = None,
api_key: Optional[str] = None,
model_list: Optional[list] = None, # pass in a list of api_base,keys, etc.
# Optional liteLLM function params
**kwargs,
) -> ModelResponse:
"""
Perform a completion() using any of litellm supported llms (example gpt-4, gpt-3.5-turbo, claude-2, command-nightly)
Parameters:
model (str): The name of the language model to use for text completion. see all supported LLMs: https://docs.litellm.ai/docs/providers/
messages (List): A list of message objects representing the conversation context (default is an empty list).
OPTIONAL PARAMS
functions (List, optional): A list of functions to apply to the conversation messages (default is an empty list).
function_call (str, optional): The name of the function to call within the conversation (default is an empty string).
temperature (float, optional): The temperature parameter for controlling the randomness of the output (default is 1.0).
top_p (float, optional): The top-p parameter for nucleus sampling (default is 1.0).
n (int, optional): The number of completions to generate (default is 1).
stream (bool, optional): If True, return a streaming response (default is False).
stop(string/list, optional): - Up to 4 sequences where the LLM API will stop generating further tokens.
max_tokens (integer, optional): The maximum number of tokens in the generated completion (default is infinity).
presence_penalty (float, optional): It is used to penalize new tokens based on their existence in the text so far.
frequency_penalty: It is used to penalize new tokens based on their frequency in the text so far.
logit_bias (dict, optional): Used to modify the probability of specific tokens appearing in the completion.
user (str, optional): A unique identifier representing your end-user. This can help the LLM provider to monitor and detect abuse.
metadata (dict, optional): Pass in additional metadata to tag your completion calls - eg. prompt version, details, etc.
api_base (str, optional): Base URL for the API (default is None).
api_version (str, optional): API version (default is None).
api_key (str, optional): API key (default is None).
model_list (list, optional): List of api base, version, keys
LITELLM Specific Params
mock_response (str, optional): If provided, return a mock completion response for testing or debugging purposes (default is None).
custom_llm_provider (str, optional): Used for Non-OpenAI LLMs, Example usage for bedrock, set model="amazon.titan-tg1-large" and custom_llm_provider="bedrock"
max_retries (int, optional): The number of retries to attempt (default is 0).
Returns:
ModelResponse: A response object containing the generated completion and associated metadata.
Note:
- This function is used to perform completions() using the specified language model.
- It supports various optional parameters for customizing the completion behavior.
- If 'mock_response' is provided, a mock completion response is returned for testing or debugging.
"""
######### unpacking kwargs #####################
args = locals()
api_base = kwargs.get('api_base', None)
return_async = kwargs.get('return_async', False)
mock_response = kwargs.get('mock_response', None)
force_timeout= kwargs.get('force_timeout', 600) ## deprecated
logger_fn = kwargs.get('logger_fn', None)
verbose = kwargs.get('verbose', False)
custom_llm_provider = kwargs.get('custom_llm_provider', None)
litellm_logging_obj = kwargs.get('litellm_logging_obj', None)
id = kwargs.get('id', None)
metadata = kwargs.get('metadata', None)
fallbacks = kwargs.get('fallbacks', None)
headers = kwargs.get("headers", None)
num_retries = kwargs.get("num_retries", None) ## deprecated
max_retries = kwargs.get("max_retries", None)
context_window_fallback_dict = kwargs.get("context_window_fallback_dict", None)
### CUSTOM MODEL COST ###
input_cost_per_token = kwargs.get("input_cost_per_token", None)
output_cost_per_token = kwargs.get("output_cost_per_token", None)
### CUSTOM PROMPT TEMPLATE ###
initial_prompt_value = kwargs.get("initial_prompt_value", None)
roles = kwargs.get("roles", None)
final_prompt_value = kwargs.get("final_prompt_value", None)
bos_token = kwargs.get("bos_token", None)
eos_token = kwargs.get("eos_token", None)
acompletion = kwargs.get("acompletion", False)
client = kwargs.get("client", None)
######## end of unpacking kwargs ###########
openai_params = ["functions", "function_call", "temperature", "temperature", "top_p", "n", "stream", "stop", "max_tokens", "presence_penalty", "frequency_penalty", "logit_bias", "user", "request_timeout", "api_base", "api_version", "api_key", "deployment_id", "organization", "base_url", "default_headers", "timeout", "response_format", "seed", "tools", "tool_choice", "max_retries"]
litellm_params = ["metadata", "acompletion", "caching", "return_async", "mock_response", "api_key", "api_version", "api_base", "force_timeout", "logger_fn", "verbose", "custom_llm_provider", "litellm_logging_obj", "litellm_call_id", "use_client", "id", "fallbacks", "azure", "headers", "model_list", "num_retries", "context_window_fallback_dict", "roles", "final_prompt_value", "bos_token", "eos_token", "request_timeout", "complete_response", "self", "client", "rpm", "tpm", "input_cost_per_token", "output_cost_per_token"]
default_params = openai_params + litellm_params
non_default_params = {k: v for k,v in kwargs.items() if k not in default_params} # model-specific params - pass them straight to the model/provider
if mock_response:
return mock_completion(model, messages, stream=stream, mock_response=mock_response)
if timeout is None:
timeout = kwargs.get("request_timeout", None) or 600 # set timeout for 10 minutes by default
timeout = float(timeout)
try:
if base_url is not None:
api_base = base_url
if max_retries is not None: # openai allows openai.OpenAI(max_retries=3)
num_retries = max_retries
logging = litellm_logging_obj
fallbacks = (
fallbacks
or litellm.model_fallbacks
)
if fallbacks is not None:
return completion_with_fallbacks(**args)
if model_list is not None:
deployments = [m["litellm_params"] for m in model_list if m["model_name"] == model]
return batch_completion_models(deployments=deployments, **args)
if litellm.model_alias_map and model in litellm.model_alias_map:
model = litellm.model_alias_map[
model
] # update the model to the actual value if an alias has been passed in
model_response = ModelResponse()
if kwargs.get('azure', False) == True: # don't remove flag check, to remain backwards compatible for repos like Codium
custom_llm_provider="azure"
if deployment_id != None: # azure llms
model=deployment_id
custom_llm_provider="azure"
model, custom_llm_provider, dynamic_api_key, api_base = get_llm_provider(model=model, custom_llm_provider=custom_llm_provider, api_base=api_base, api_key=api_key)
### REGISTER CUSTOM MODEL PRICING -- IF GIVEN ###
if input_cost_per_token is not None and output_cost_per_token is not None:
litellm.register_model({
model: {
"input_cost_per_token": input_cost_per_token,
"output_cost_per_token": output_cost_per_token,
"litellm_provider": custom_llm_provider
}
})
### BUILD CUSTOM PROMPT TEMPLATE -- IF GIVEN ###
custom_prompt_dict = {} # type: ignore
if initial_prompt_value or roles or final_prompt_value or bos_token or eos_token:
custom_prompt_dict = {model: {}}
if initial_prompt_value:
custom_prompt_dict[model]["initial_prompt_value"] = initial_prompt_value
if roles:
custom_prompt_dict[model]["roles"] = roles
if final_prompt_value:
custom_prompt_dict[model]["final_prompt_value"] = final_prompt_value
if bos_token:
custom_prompt_dict[model]["bos_token"] = bos_token
if eos_token:
custom_prompt_dict[model]["eos_token"] = eos_token
model_api_key = get_api_key(llm_provider=custom_llm_provider, dynamic_api_key=api_key) # get the api key from the environment if required for the model
if model_api_key and "sk-litellm" in model_api_key:
api_base = "https://proxy.litellm.ai"
custom_llm_provider = "openai"
api_key = model_api_key
if dynamic_api_key is not None:
api_key = dynamic_api_key
# check if user passed in any of the OpenAI optional params
optional_params = get_optional_params(
functions=functions,
function_call=function_call,
temperature=temperature,
top_p=top_p,
n=n,
stream=stream,
stop=stop,
max_tokens=max_tokens,
presence_penalty=presence_penalty,
frequency_penalty=frequency_penalty,
logit_bias=logit_bias,
user=user,
# params to identify the model
model=model,
custom_llm_provider=custom_llm_provider,
response_format=response_format,
seed=seed,
tools=tools,
tool_choice=tool_choice,
max_retries=max_retries,
**non_default_params
)
if litellm.add_function_to_prompt and optional_params.get("functions_unsupported_model", None): # if user opts to add it to prompt, when API doesn't support function calling
functions_unsupported_model = optional_params.pop("functions_unsupported_model")
messages = function_call_prompt(messages=messages, functions=functions_unsupported_model)
# For logging - save the values of the litellm-specific params passed in
litellm_params = get_litellm_params(
return_async=return_async,
api_key=api_key,
force_timeout=force_timeout,
logger_fn=logger_fn,
verbose=verbose,
custom_llm_provider=custom_llm_provider,
api_base=api_base,
litellm_call_id=kwargs.get('litellm_call_id', None),
model_alias_map=litellm.model_alias_map,
completion_call_id=id,
metadata=metadata
)
logging.update_environment_variables(model=model, user=user, optional_params=optional_params, litellm_params=litellm_params)
if custom_llm_provider == "azure":
# azure configs
api_type = get_secret("AZURE_API_TYPE") or "azure"
api_base = (
api_base
or litellm.api_base
or get_secret("AZURE_API_BASE")
)
api_version = (
api_version or
litellm.api_version or
get_secret("AZURE_API_VERSION")
)
api_key = (
api_key or
litellm.api_key or
litellm.azure_key or
get_secret("AZURE_OPENAI_API_KEY") or
get_secret("AZURE_API_KEY")
)
azure_ad_token = (
optional_params.pop("azure_ad_token", None) or
get_secret("AZURE_AD_TOKEN")
)
headers = (
headers or
litellm.headers
)
## LOAD CONFIG - if set
config=litellm.AzureOpenAIConfig.get_config()
for k, v in config.items():
if k not in optional_params: # completion(top_k=3) > azure_config(top_k=3) <- allows for dynamic variables to be passed in
optional_params[k] = v
## COMPLETION CALL
response = azure_chat_completions.completion(
model=model,
messages=messages,
headers=headers,
api_key=api_key,
api_base=api_base,
api_version=api_version,
api_type=api_type,
azure_ad_token=azure_ad_token,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
logging_obj=logging,
acompletion=acompletion,
timeout=timeout,
client=client # pass AsyncAzureOpenAI, AzureOpenAI client
)
## LOGGING
logging.post_call(
input=messages,
api_key=api_key,
original_response=response,
additional_args={
"headers": headers,
"api_version": api_version,
"api_base": api_base,
},
)
elif (
model in litellm.open_ai_chat_completion_models
or custom_llm_provider == "custom_openai"
or custom_llm_provider == "deepinfra"
or custom_llm_provider == "perplexity"
or custom_llm_provider == "anyscale"
or custom_llm_provider == "openai"
or "ft:gpt-3.5-turbo" in model # finetune gpt-3.5-turbo
): # allow user to make an openai call with a custom base
# note: if a user sets a custom base - we should ensure this works
# allow for the setting of dynamic and stateful api-bases
api_base = (
api_base # for deepinfra/perplexity/anyscale we check in get_llm_provider and pass in the api base from there
or litellm.api_base
or get_secret("OPENAI_API_BASE")
or "https://api.openai.com/v1"
)
openai.organization = (
litellm.organization
or get_secret("OPENAI_ORGANIZATION")
or None # default - https://github.com/openai/openai-python/blob/284c1799070c723c6a553337134148a7ab088dd8/openai/util.py#L105
)
# set API KEY
api_key = (
api_key or # for deepinfra/perplexity/anyscale we check in get_llm_provider and pass in the api key from there
litellm.api_key or
litellm.openai_key or
get_secret("OPENAI_API_KEY")
)
headers = (
headers or
litellm.headers
)
## LOAD CONFIG - if set
config=litellm.OpenAIConfig.get_config()
for k, v in config.items():
if k not in optional_params: # completion(top_k=3) > openai_config(top_k=3) <- allows for dynamic variables to be passed in
optional_params[k] = v
## COMPLETION CALL
try:
response = openai_chat_completions.completion(
model=model,
messages=messages,
model_response=model_response,
print_verbose=print_verbose,
api_key=api_key,
api_base=api_base,
acompletion=acompletion,
logging_obj=logging,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
timeout=timeout,
custom_prompt_dict=custom_prompt_dict,
client=client # pass AsyncOpenAI, OpenAI client
)
except Exception as e:
## LOGGING - log the original exception returned
logging.post_call(
input=messages,
api_key=api_key,
original_response=str(e),
additional_args={"headers": headers},
)
raise e
## LOGGING
logging.post_call(
input=messages,
api_key=api_key,
original_response=response,
additional_args={"headers": headers},
)
elif (
custom_llm_provider == "text-completion-openai"
or "ft:babbage-002" in model
or "ft:davinci-002" in model # support for finetuned completion models
):
# print("calling custom openai provider")
openai.api_type = "openai"
api_base = (
api_base
or litellm.api_base
or get_secret("OPENAI_API_BASE")
or "https://api.openai.com/v1"
)
openai.api_version = None
# set API KEY
api_key = (
api_key or
litellm.api_key or
litellm.openai_key or
get_secret("OPENAI_API_KEY")
)
headers = (
headers or
litellm.headers
)
## LOAD CONFIG - if set
config=litellm.OpenAITextCompletionConfig.get_config()
for k, v in config.items():
if k not in optional_params: # completion(top_k=3) > openai_text_config(top_k=3) <- allows for dynamic variables to be passed in
optional_params[k] = v
if litellm.organization:
openai.organization = litellm.organization
if len(messages)>0 and "content" in messages[0] and type(messages[0]["content"]) == list:
# text-davinci-003 can accept a string or array, if it's an array, assume the array is set in messages[0]['content']
# https://platform.openai.com/docs/api-reference/completions/create
prompt = messages[0]["content"]
else:
prompt = " ".join([message["content"] for message in messages]) # type: ignore
## LOGGING
logging.pre_call(
input=prompt,
api_key=api_key,
additional_args={
"openai_organization": litellm.organization,
"headers": headers,
"api_base": api_base,
"api_type": openai.api_type,
},
)
## COMPLETION CALL
model_response = openai_text_completions.completion(
model=model,
messages=messages,
model_response=model_response,
print_verbose=print_verbose,
api_key=api_key,
api_base=api_base,
acompletion=acompletion,
logging_obj=logging,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn
)
# if "stream" in optional_params and optional_params["stream"] == True:
# response = CustomStreamWrapper(model_response, model, custom_llm_provider="text-completion-openai", logging_obj=logging)
# return response
response = model_response
elif (
"replicate" in model or
custom_llm_provider == "replicate" or
model in litellm.replicate_models
):
# Setting the relevant API KEY for replicate, replicate defaults to using os.environ.get("REPLICATE_API_TOKEN")
replicate_key = None
replicate_key = (
api_key
or litellm.replicate_key
or litellm.api_key
or get_secret("REPLICATE_API_KEY")
or get_secret("REPLICATE_API_TOKEN")
)
api_base = (
api_base
or litellm.api_base
or get_secret("REPLICATE_API_BASE")
or "https://api.replicate.com/v1"
)
custom_prompt_dict = (
custom_prompt_dict
or litellm.custom_prompt_dict
)
model_response = replicate.completion(
model=model,
messages=messages,
api_base=api_base,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding, # for calculating input/output tokens
api_key=replicate_key,
logging_obj=logging,
custom_prompt_dict=custom_prompt_dict
)
if "stream" in optional_params and optional_params["stream"] == True:
# don't try to access stream object,
response = CustomStreamWrapper(model_response, model, logging_obj=logging, custom_llm_provider="replicate")
return response
response = model_response
elif custom_llm_provider=="anthropic":
api_key = (
api_key
or litellm.anthropic_key
or litellm.api_key
or os.environ.get("ANTHROPIC_API_KEY")
)
api_base = (
api_base
or litellm.api_base
or get_secret("ANTHROPIC_API_BASE")
or "https://api.anthropic.com/v1/complete"
)
custom_prompt_dict = (
custom_prompt_dict
or litellm.custom_prompt_dict
)
model_response = anthropic.completion(
model=model,
messages=messages,
api_base=api_base,
custom_prompt_dict=litellm.custom_prompt_dict,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding, # for calculating input/output tokens
api_key=api_key,
logging_obj=logging,
)
if "stream" in optional_params and optional_params["stream"] == True:
# don't try to access stream object,
response = CustomStreamWrapper(model_response, model, custom_llm_provider="anthropic", logging_obj=logging)
return response
response = model_response
elif custom_llm_provider == "nlp_cloud":
nlp_cloud_key = (
api_key or litellm.nlp_cloud_key or get_secret("NLP_CLOUD_API_KEY") or litellm.api_key
)
api_base = (
api_base
or litellm.api_base
or get_secret("NLP_CLOUD_API_BASE")
or "https://api.nlpcloud.io/v1/gpu/"
)
model_response = nlp_cloud.completion(
model=model,
messages=messages,
api_base=api_base,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
api_key=nlp_cloud_key,
logging_obj=logging
)
if "stream" in optional_params and optional_params["stream"] == True:
# don't try to access stream object,
response = CustomStreamWrapper(model_response, model, custom_llm_provider="nlp_cloud", logging_obj=logging)
return response
response = model_response
elif custom_llm_provider == "aleph_alpha":
aleph_alpha_key = (
api_key or litellm.aleph_alpha_key or get_secret("ALEPH_ALPHA_API_KEY") or get_secret("ALEPHALPHA_API_KEY") or litellm.api_key
)
api_base = (
api_base
or litellm.api_base
or get_secret("ALEPH_ALPHA_API_BASE")
or "https://api.aleph-alpha.com/complete"
)
model_response = aleph_alpha.completion(
model=model,
messages=messages,
api_base=api_base,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
default_max_tokens_to_sample=litellm.max_tokens,
api_key=aleph_alpha_key,
logging_obj=logging # model call logging done inside the class as we make need to modify I/O to fit aleph alpha's requirements
)
if "stream" in optional_params and optional_params["stream"] == True:
# don't try to access stream object,
response = CustomStreamWrapper(model_response, model, custom_llm_provider="aleph_alpha", logging_obj=logging)
return response
response = model_response
elif custom_llm_provider == "cohere":
cohere_key = (
api_key
or litellm.cohere_key
or get_secret("COHERE_API_KEY")
or get_secret("CO_API_KEY")
or litellm.api_key
)
api_base = (
api_base
or litellm.api_base
or get_secret("COHERE_API_BASE")
or "https://api.cohere.ai/v1/generate"
)
model_response = cohere.completion(
model=model,
messages=messages,
api_base=api_base,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
api_key=cohere_key,
logging_obj=logging # model call logging done inside the class as we make need to modify I/O to fit aleph alpha's requirements
)
if "stream" in optional_params and optional_params["stream"] == True:
# don't try to access stream object,
response = CustomStreamWrapper(model_response, model, custom_llm_provider="cohere", logging_obj=logging)
return response
response = model_response
elif custom_llm_provider == "maritalk":
maritalk_key = (
api_key
or litellm.maritalk_key
or get_secret("MARITALK_API_KEY")
or litellm.api_key
)
api_base = (
api_base
or litellm.api_base
or get_secret("MARITALK_API_BASE")
or "https://chat.maritaca.ai/api/chat/inference"
)
model_response = maritalk.completion(
model=model,
messages=messages,
api_base=api_base,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
api_key=maritalk_key,
logging_obj=logging
)
if "stream" in optional_params and optional_params["stream"] == True:
# don't try to access stream object,
response = CustomStreamWrapper(model_response, model, custom_llm_provider="maritalk", logging_obj=logging)
return response
response = model_response
elif (
custom_llm_provider == "huggingface"
):
custom_llm_provider = "huggingface"
huggingface_key = (
api_key
or litellm.huggingface_key
or os.environ.get("HF_TOKEN")
or os.environ.get("HUGGINGFACE_API_KEY")
or litellm.api_key
)
hf_headers = (
headers
or litellm.headers
)
custom_prompt_dict = (
custom_prompt_dict
or litellm.custom_prompt_dict
)
model_response = huggingface.completion(
model=model,
messages=messages,
api_base=api_base, # type: ignore
headers=hf_headers,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
api_key=huggingface_key,
acompletion=acompletion,
logging_obj=logging,
custom_prompt_dict=custom_prompt_dict
)
if "stream" in optional_params and optional_params["stream"] == True and acompletion is False:
# don't try to access stream object,
response = CustomStreamWrapper(
model_response, model, custom_llm_provider="huggingface", logging_obj=logging
)
return response
response = model_response
elif custom_llm_provider == "oobabooga":
custom_llm_provider = "oobabooga"
model_response = oobabooga.completion(
model=model,
messages=messages,
model_response=model_response,
api_base=api_base, # type: ignore
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
api_key=None,
logger_fn=logger_fn,
encoding=encoding,
logging_obj=logging
)
if "stream" in optional_params and optional_params["stream"] == True:
# don't try to access stream object,
response = CustomStreamWrapper(
model_response, model, custom_llm_provider="oobabooga", logging_obj=logging
)
return response
response = model_response
elif custom_llm_provider == "openrouter":
api_base = (
api_base
or litellm.api_base
or "https://openrouter.ai/api/v1"
)
api_key = (
api_key or
litellm.api_key or
litellm.openrouter_key or
get_secret("OPENROUTER_API_KEY") or
get_secret("OR_API_KEY")
)
openrouter_site_url = (
get_secret("OR_SITE_URL")
or "https://litellm.ai"
)
openrouter_app_name = (
get_secret("OR_APP_NAME")
or "liteLLM"
)
headers = (
headers or
litellm.headers or
{
"HTTP-Referer": openrouter_site_url,
"X-Title": openrouter_app_name,
}
)
data = {
"model": model,
"messages": messages,
**optional_params
}
## LOGGING
logging.pre_call(input=messages, api_key=openai.api_key, additional_args={"complete_input_dict": data, "headers": headers})
## COMPLETION CALL
## COMPLETION CALL
response = openai_chat_completions.completion(
model=model,
messages=messages,
headers=headers,
api_key=api_key,
api_base=api_base,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
logging_obj=logging,
acompletion=acompletion,
timeout=timeout
)
## LOGGING
logging.post_call(
input=messages, api_key=openai.api_key, original_response=response
)
elif custom_llm_provider == "together_ai" or ("togethercomputer" in model) or (model in litellm.together_ai_models):
custom_llm_provider = "together_ai"
together_ai_key = (
api_key
or litellm.togetherai_api_key
or get_secret("TOGETHER_AI_TOKEN")
or get_secret("TOGETHERAI_API_KEY")
or litellm.api_key
)
api_base = (
api_base
or litellm.api_base
or get_secret("TOGETHERAI_API_BASE")
or "https://api.together.xyz/inference"
)
custom_prompt_dict = (
custom_prompt_dict
or litellm.custom_prompt_dict
)
model_response = together_ai.completion(
model=model,
messages=messages,
api_base=api_base,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
api_key=together_ai_key,
logging_obj=logging,
custom_prompt_dict=custom_prompt_dict
)
if "stream_tokens" in optional_params and optional_params["stream_tokens"] == True:
# don't try to access stream object,
response = CustomStreamWrapper(
model_response, model, custom_llm_provider="together_ai", logging_obj=logging
)
return response
response = model_response
elif custom_llm_provider == "palm":
palm_api_key = (
api_key
or get_secret("PALM_API_KEY")
or litellm.api_key
)
# palm does not support streaming as yet :(
model_response = palm.completion(
model=model,
messages=messages,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
api_key=palm_api_key,
logging_obj=logging
)
# fake palm streaming
if "stream" in optional_params and optional_params["stream"] == True:
# fake streaming for palm
resp_string = model_response["choices"][0]["message"]["content"]
response = CustomStreamWrapper(
resp_string, model, custom_llm_provider="palm", logging_obj=logging
)
return response
response = model_response
elif model in litellm.vertex_chat_models or model in litellm.vertex_code_chat_models or model in litellm.vertex_text_models or model in litellm.vertex_code_text_models:
vertex_ai_project = (litellm.vertex_project
or get_secret("VERTEXAI_PROJECT"))
vertex_ai_location = (litellm.vertex_location
or get_secret("VERTEXAI_LOCATION"))
model_response = vertex_ai.completion(
model=model,
messages=messages,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
vertex_location=vertex_ai_location,
vertex_project=vertex_ai_project,
logging_obj=logging
)
if "stream" in optional_params and optional_params["stream"] == True:
response = CustomStreamWrapper(
model_response, model, custom_llm_provider="vertex_ai", logging_obj=logging
)
return response
response = model_response
elif custom_llm_provider == "ai21":
custom_llm_provider = "ai21"
ai21_key = (
api_key
or litellm.ai21_key
or os.environ.get("AI21_API_KEY")
or litellm.api_key
)
api_base = (
api_base
or litellm.api_base
or get_secret("AI21_API_BASE")
or "https://api.ai21.com/studio/v1/"
)
model_response = ai21.completion(
model=model,
messages=messages,
api_base=api_base,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
api_key=ai21_key,
logging_obj=logging
)
if "stream" in optional_params and optional_params["stream"] == True:
# don't try to access stream object,
response = CustomStreamWrapper(
model_response, model, custom_llm_provider="ai21", logging_obj=logging
)
return response
## RESPONSE OBJECT
response = model_response
elif custom_llm_provider == "sagemaker":
# boto3 reads keys from .env
model_response = sagemaker.completion(
model=model,
messages=messages,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
logging_obj=logging
)
if "stream" in optional_params and optional_params["stream"]==True: ## [BETA]
# sagemaker does not support streaming as of now so we're faking streaming:
# /static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fstreaming-output-text-when-deploying-on-sagemaker%2F39611%3C%2Fspan%3E
# "SageMaker is currently not supporting streaming responses."
# fake streaming for sagemaker
resp_string = model_response["choices"][0]["message"]["content"]
response = CustomStreamWrapper(
resp_string, model, custom_llm_provider="sagemaker", logging_obj=logging
)
return response
## RESPONSE OBJECT
response = model_response
elif custom_llm_provider == "bedrock":
# boto3 reads keys from .env
custom_prompt_dict = (
custom_prompt_dict
or litellm.custom_prompt_dict
)
model_response = bedrock.completion(
model=model,
messages=messages,
custom_prompt_dict=litellm.custom_prompt_dict,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
logging_obj=logging,
)
if "stream" in optional_params and optional_params["stream"] == True:
# don't try to access stream object,
if "ai21" in model:
response = CustomStreamWrapper(
model_response, model, custom_llm_provider="bedrock", logging_obj=logging
)
else:
response = CustomStreamWrapper(
iter(model_response), model, custom_llm_provider="bedrock", logging_obj=logging
)
return response
## RESPONSE OBJECT
response = model_response
elif custom_llm_provider == "vllm":
model_response = vllm.completion(
model=model,
messages=messages,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
logging_obj=logging
)
if "stream" in optional_params and optional_params["stream"] == True: ## [BETA]
# don't try to access stream object,
response = CustomStreamWrapper(
model_response, model, custom_llm_provider="vllm", logging_obj=logging
)
return response
## RESPONSE OBJECT
response = model_response
elif custom_llm_provider == "ollama":
api_base = (
litellm.api_base or
api_base or
get_secret("OLLAMA_API_BASE") or
"http://localhost:11434"
)
custom_prompt_dict = (
custom_prompt_dict
or litellm.custom_prompt_dict
)
if model in custom_prompt_dict:
# check if the model has a registered custom prompt
model_prompt_details = custom_prompt_dict[model]
prompt = custom_prompt(
role_dict=model_prompt_details["roles"],
initial_prompt_value=model_prompt_details["initial_prompt_value"],
final_prompt_value=model_prompt_details["final_prompt_value"],
messages=messages
)
else:
prompt = prompt_factory(model=model, messages=messages, custom_llm_provider=custom_llm_provider)
## LOGGING
if kwargs.get('acompletion', False) == True:
if optional_params.get("stream", False) == True:
# assume all ollama responses are streamed
async_generator = ollama.async_get_ollama_response_stream(api_base, model, prompt, optional_params, logging_obj=logging)
return async_generator
generator = ollama.get_ollama_response_stream(api_base, model, prompt, optional_params, logging_obj=logging)
if optional_params.get("stream", False) == True:
# assume all ollama responses are streamed
response = CustomStreamWrapper(
generator, model, custom_llm_provider="ollama", logging_obj=logging
)
return response
else:
response_string = ""
for chunk in generator:
response_string+=chunk['content']
## RESPONSE OBJECT
model_response["choices"][0]["finish_reason"] = "stop"
model_response["choices"][0]["message"]["content"] = response_string
model_response["created"] = int(time.time())
model_response["model"] = "ollama/" + model
prompt_tokens = len(encoding.encode(prompt)) # type: ignore
completion_tokens = len(encoding.encode(response_string))
model_response["usage"] = Usage(prompt_tokens=prompt_tokens, completion_tokens=completion_tokens, total_tokens=prompt_tokens + completion_tokens)
response = model_response
elif (
custom_llm_provider == "baseten"
or litellm.api_base == "https://app.baseten.co"
):
custom_llm_provider = "baseten"
baseten_key = (
api_key or litellm.baseten_key or os.environ.get("BASETEN_API_KEY") or litellm.api_key
)
model_response = baseten.completion(
model=model,
messages=messages,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
api_key=baseten_key,
logging_obj=logging
)
if inspect.isgenerator(model_response) or ("stream" in optional_params and optional_params["stream"] == True):
# don't try to access stream object,
response = CustomStreamWrapper(
model_response, model, custom_llm_provider="baseten", logging_obj=logging
)
return response
response = model_response
elif (
custom_llm_provider == "petals"
or model in litellm.petals_models
):
api_base = (
api_base or
litellm.api_base
)
custom_llm_provider = "petals"
stream = optional_params.pop("stream", False)
model_response = petals.completion(
model=model,
messages=messages,
api_base=api_base,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
logging_obj=logging
)
if stream==True: ## [BETA]
# Fake streaming for petals
resp_string = model_response["choices"][0]["message"]["content"]
response = CustomStreamWrapper(
resp_string, model, custom_llm_provider="petals", logging_obj=logging
)
return response
response = model_response
elif (
custom_llm_provider == "custom"
):
import requests
url = (
litellm.api_base or
api_base or
""
)
if url == None or url == "":
raise ValueError("api_base not set. Set api_base or litellm.api_base for custom endpoints")
"""
assume input to custom LLM api bases follow this format:
resp = requests.post(
api_base,
json={
'model': 'meta-llama/Llama-2-13b-hf', # model name
'params': {
'prompt': ["The capital of France is P"],
'max_tokens': 32,
'temperature': 0.7,
'top_p': 1.0,
'top_k': 40,
}
}
)
"""
prompt = " ".join([message["content"] for message in messages]) # type: ignore
resp = requests.post(url, json={
'model': model,
'params': {
'prompt': [prompt],
'max_tokens': max_tokens,
'temperature': temperature,
'top_p': top_p,
'top_k': kwargs.get('top_k', 40),
}
})
response_json = resp.json()
"""
assume all responses from custom api_bases of this format:
{
'data': [
{
'prompt': 'The capital of France is P',
'output': ['The capital of France is PARIS.\nThe capital of France is PARIS.\nThe capital of France is PARIS.\nThe capital of France is PARIS.\nThe capital of France is PARIS.\nThe capital of France is PARIS.\nThe capital of France is PARIS.\nThe capital of France is PARIS.\nThe capital of France is PARIS.\nThe capital of France is PARIS.\nThe capital of France is PARIS.\nThe capital of France is PARIS.\nThe capital of France is PARIS.\nThe capital of France'],
'params': {'temperature': 0.7, 'top_k': 40, 'top_p': 1}}],
'message': 'ok'
}
]
}
"""
string_response = response_json['data'][0]['output'][0]
## RESPONSE OBJECT
model_response["choices"][0]["message"]["content"] = string_response
model_response["created"] = int(time.time())
model_response["model"] = model
response = model_response
else:
raise ValueError(
f"Unable to map your input to a model. Check your input - {args}"
)
return response
except Exception as e:
## Map to OpenAI Exception
raise exception_type(
model=model, custom_llm_provider=custom_llm_provider, original_exception=e, completion_kwargs=args,
)
def completion_with_retries(*args, **kwargs):
"""
Executes a litellm.completion() with 3 retries
"""
try:
import tenacity
except Exception as e:
raise Exception(f"tenacity import failed please run `pip install tenacity`. Error{e}")
num_retries = kwargs.pop("num_retries", 3)
retry_strategy = kwargs.pop("retry_strategy", "constant_retry")
original_function = kwargs.pop("original_function", completion)
if retry_strategy == "constant_retry":
retryer = tenacity.Retrying(stop=tenacity.stop_after_attempt(num_retries), reraise=True)
elif retry_strategy == "exponential_backoff_retry":
retryer = tenacity.Retrying(wait=tenacity.wait_exponential(multiplier=1, max=10), stop=tenacity.stop_after_attempt(num_retries), reraise=True)
return retryer(original_function, *args, **kwargs)
async def acompletion_with_retries(*args, **kwargs):
"""
Executes a litellm.completion() with 3 retries
"""
try:
import tenacity
except Exception as e:
raise Exception(f"tenacity import failed please run `pip install tenacity`. Error{e}")
num_retries = kwargs.pop("num_retries", 3)
retry_strategy = kwargs.pop("retry_strategy", "constant_retry")
original_function = kwargs.pop("original_function", completion)
if retry_strategy == "constant_retry":
retryer = tenacity.Retrying(stop=tenacity.stop_after_attempt(num_retries), reraise=True)
elif retry_strategy == "exponential_backoff_retry":
retryer = tenacity.Retrying(wait=tenacity.wait_exponential(multiplier=1, max=10), stop=tenacity.stop_after_attempt(num_retries), reraise=True)
return await retryer(original_function, *args, **kwargs)
def batch_completion(
model: str,
# Optional OpenAI params: see https://platform.openai.com/docs/api-reference/chat/create
messages: List = [],
functions: List = [],
function_call: str = "", # optional params
temperature: Optional[float] = None,
top_p: Optional[float] = None,
n: Optional[int] = None,
stream: Optional[bool] = None,
stop=None,
max_tokens: Optional[float] = None,
presence_penalty: Optional[float] = None,
frequency_penalty: Optional[float]=None,
logit_bias: Optional[dict] = None,
user: Optional[str] = None,
deployment_id = None,
request_timeout: Optional[int] = None,
# Optional liteLLM function params
**kwargs):
"""
Batch litellm.completion function for a given model.
Args:
model (str): The model to use for generating completions.
messages (List, optional): List of messages to use as input for generating completions. Defaults to [].
functions (List, optional): List of functions to use as input for generating completions. Defaults to [].
function_call (str, optional): The function call to use as input for generating completions. Defaults to "".
temperature (float, optional): The temperature parameter for generating completions. Defaults to None.
top_p (float, optional): The top-p parameter for generating completions. Defaults to None.
n (int, optional): The number of completions to generate. Defaults to None.
stream (bool, optional): Whether to stream completions or not. Defaults to None.
stop (optional): The stop parameter for generating completions. Defaults to None.
max_tokens (float, optional): The maximum number of tokens to generate. Defaults to None.
presence_penalty (float, optional): The presence penalty for generating completions. Defaults to None.
frequency_penalty (float, optional): The frequency penalty for generating completions. Defaults to None.
logit_bias (dict, optional): The logit bias for generating completions. Defaults to {}.
user (str, optional): The user string for generating completions. Defaults to "".
deployment_id (optional): The deployment ID for generating completions. Defaults to None.
request_timeout (int, optional): The request timeout for generating completions. Defaults to None.
Returns:
list: A list of completion results.
"""
args = locals()
batch_messages = messages
completions = []
model = model
custom_llm_provider = None
if model.split("/", 1)[0] in litellm.provider_list:
custom_llm_provider = model.split("/", 1)[0]
model = model.split("/", 1)[1]
if custom_llm_provider == "vllm":
optional_params = get_optional_params(
functions=functions,
function_call=function_call,
temperature=temperature,
top_p=top_p,
n=n,
stream=stream,
stop=stop,
max_tokens=max_tokens,
presence_penalty=presence_penalty,
frequency_penalty=frequency_penalty,
logit_bias=logit_bias,
user=user,
# params to identify the model
model=model,
custom_llm_provider=custom_llm_provider
)
results = vllm.batch_completions(model=model, messages=batch_messages, custom_prompt_dict=litellm.custom_prompt_dict, optional_params=optional_params)
# all non VLLM models for batch completion models
else:
def chunks(lst, n):
"""Yield successive n-sized chunks from lst."""
for i in range(0, len(lst), n):
yield lst[i:i + n]
with ThreadPoolExecutor(max_workers=100) as executor:
for sub_batch in chunks(batch_messages, 100):
for message_list in sub_batch:
kwargs_modified = args.copy()
kwargs_modified["messages"] = message_list
original_kwargs = {}
if "kwargs" in kwargs_modified:
original_kwargs = kwargs_modified.pop("kwargs")
future = executor.submit(completion, **kwargs_modified, **original_kwargs)
completions.append(future)
# Retrieve the results from the futures
results = [future.result() for future in completions]
return results
# send one request to multiple models
# return as soon as one of the llms responds
def batch_completion_models(*args, **kwargs):
"""
Send a request to multiple language models concurrently and return the response
as soon as one of the models responds.
Args:
*args: Variable-length positional arguments passed to the completion function.
**kwargs: Additional keyword arguments:
- models (str or list of str): The language models to send requests to.
- Other keyword arguments to be passed to the completion function.
Returns:
str or None: The response from one of the language models, or None if no response is received.
Note:
This function utilizes a ThreadPoolExecutor to parallelize requests to multiple models.
It sends requests concurrently and returns the response from the first model that responds.
"""
import concurrent
if "model" in kwargs:
kwargs.pop("model")
if "models" in kwargs:
models = kwargs["models"]
kwargs.pop("models")
futures = {}
with concurrent.futures.ThreadPoolExecutor(max_workers=len(models)) as executor:
for model in models:
futures[model] = executor.submit(completion, *args, model=model, **kwargs)
for model, future in sorted(futures.items(), key=lambda x: models.index(x[0])):
if future.result() is not None:
return future.result()
elif "deployments" in kwargs:
deployments = kwargs["deployments"]
kwargs.pop("deployments")
kwargs.pop("model_list")
nested_kwargs = kwargs.pop("kwargs", {})
futures = {}
with concurrent.futures.ThreadPoolExecutor(max_workers=len(deployments)) as executor:
for deployment in deployments:
for key in kwargs.keys():
if key not in deployment: # don't override deployment values e.g. model name, api base, etc.
deployment[key] = kwargs[key]
kwargs = {**deployment, **nested_kwargs}
futures[deployment["model"]] = executor.submit(completion, **kwargs)
while futures:
# wait for the first returned future
print_verbose("\n\n waiting for next result\n\n")
done, _ = concurrent.futures.wait(futures.values(), return_when=concurrent.futures.FIRST_COMPLETED)
print_verbose(f"done list\n{done}")
for future in done:
try:
result = future.result()
return result
except Exception as e:
# if model 1 fails, continue with response from model 2, model3
print_verbose(f"\n\ngot an exception, ignoring, removing from futures")
print_verbose(futures)
new_futures = {}
for key, value in futures.items():
if future == value:
print_verbose(f"removing key{key}")
continue
else:
new_futures[key] = value
futures = new_futures
print_verbose(f"new futures{futures}")
continue
print_verbose("\n\ndone looping through futures\n\n")
print_verbose(futures)
return None # If no response is received from any model
def batch_completion_models_all_responses(*args, **kwargs):
"""
Send a request to multiple language models concurrently and return a list of responses
from all models that respond.
Args:
*args: Variable-length positional arguments passed to the completion function.
**kwargs: Additional keyword arguments:
- models (str or list of str): The language models to send requests to.
- Other keyword arguments to be passed to the completion function.
Returns:
list: A list of responses from the language models that responded.
Note:
This function utilizes a ThreadPoolExecutor to parallelize requests to multiple models.
It sends requests concurrently and collects responses from all models that respond.
"""
import concurrent.futures
# ANSI escape codes for colored output
GREEN = "\033[92m"
RED = "\033[91m"
RESET = "\033[0m"
if "model" in kwargs:
kwargs.pop("model")
if "models" in kwargs:
models = kwargs["models"]
kwargs.pop("models")
responses = []
with concurrent.futures.ThreadPoolExecutor(max_workers=len(models)) as executor:
for idx, model in enumerate(models):
future = executor.submit(completion, *args, model=model, **kwargs)
if future.result() is not None:
responses.append(future.result())
return responses
### EMBEDDING ENDPOINTS ####################
async def aembedding(*args, **kwargs):
"""
Asynchronously calls the `embedding` function with the given arguments and keyword arguments.
Parameters:
- `args` (tuple): Positional arguments to be passed to the `embedding` function.
- `kwargs` (dict): Keyword arguments to be passed to the `embedding` function.
Returns:
- `response` (Any): The response returned by the `embedding` function.
"""
loop = asyncio.get_event_loop()
model = args[0] if len(args) > 0 else kwargs["model"]
### PASS ARGS TO Embedding ###
kwargs["aembedding"] = True
custom_llm_provider = None
try:
# Use a partial function to pass your keyword arguments
func = partial(embedding, *args, **kwargs)
# Add the context to the function
ctx = contextvars.copy_context()
func_with_context = partial(ctx.run, func)
_, custom_llm_provider, _, _ = get_llm_provider(model=model, api_base=kwargs.get("api_base", None))
if (custom_llm_provider == "openai"
or custom_llm_provider == "azure"
or custom_llm_provider == "custom_openai"
or custom_llm_provider == "anyscale"
or custom_llm_provider == "openrouter"
or custom_llm_provider == "deepinfra"
or custom_llm_provider == "perplexity"
or custom_llm_provider == "huggingface"): # currently implemented aiohttp calls for just azure and openai, soon all.
# Await normally
init_response = await loop.run_in_executor(None, func_with_context)
if isinstance(init_response, dict) or isinstance(init_response, ModelResponse): ## CACHING SCENARIO
response = init_response
elif asyncio.iscoroutine(init_response):
response = await init_response
else:
# Call the synchronous function using run_in_executor
response = await loop.run_in_executor(None, func_with_context)
return response
except Exception as e:
custom_llm_provider = custom_llm_provider or "openai"
raise exception_type(
model=model, custom_llm_provider=custom_llm_provider, original_exception=e, completion_kwargs=args,
)
@client
def embedding(
model,
input=[],
# Optional params
timeout=600, # default to 10 minutes
# set api_base, api_version, api_key
api_base: Optional[str] = None,
api_version: Optional[str] = None,
api_key: Optional[str] = None,
api_type: Optional[str] = None,
caching: bool=False,
user: Optional[str]=None,
custom_llm_provider=None,
litellm_call_id=None,
litellm_logging_obj=None,
logger_fn=None,
**kwargs
):
"""
Embedding function that calls an API to generate embeddings for the given input.
Parameters:
- model: The embedding model to use.
- input: The input for which embeddings are to be generated.
- timeout: The timeout value for the API call, default 10 mins
- litellm_call_id: The call ID for litellm logging.
- litellm_logging_obj: The litellm logging object.
- logger_fn: The logger function.
- api_base: Optional. The base URL for the API.
- api_version: Optional. The version of the API.
- api_key: Optional. The API key to use.
- api_type: Optional. The type of the API.
- caching: A boolean indicating whether to enable caching.
- custom_llm_provider: The custom llm provider.
Returns:
- response: The response received from the API call.
Raises:
- exception_type: If an exception occurs during the API call.
"""
azure = kwargs.get("azure", None)
client = kwargs.pop("client", None)
rpm = kwargs.pop("rpm", None)
tpm = kwargs.pop("tpm", None)
aembedding = kwargs.pop("aembedding", None)
optional_params = {}
for param in kwargs:
if param != "metadata": # filter out metadata from optional_params
optional_params[param] = kwargs[param]
model, custom_llm_provider, dynamic_api_key, api_base = get_llm_provider(model=model, custom_llm_provider=custom_llm_provider, api_base=api_base, api_key=api_key)
try:
response = None
logging = litellm_logging_obj
logging.update_environment_variables(model=model, user="", optional_params={}, litellm_params={"timeout": timeout, "azure": azure, "litellm_call_id": litellm_call_id, "logger_fn": logger_fn})
if azure == True or custom_llm_provider == "azure":
# azure configs
api_type = get_secret("AZURE_API_TYPE") or "azure"
api_base = (
api_base
or litellm.api_base
or get_secret("AZURE_API_BASE")
)
api_version = (
api_version or
litellm.api_version or
get_secret("AZURE_API_VERSION")
)
azure_ad_token = (
kwargs.pop("azure_ad_token", None) or
get_secret("AZURE_AD_TOKEN")
)
api_key = (
api_key or
litellm.api_key or
litellm.azure_key or
get_secret("AZURE_API_KEY")
)
## EMBEDDING CALL
response = azure_chat_completions.embedding(
model=model,
input=input,
api_base=api_base,
api_key=api_key,
api_version=api_version,
azure_ad_token=azure_ad_token,
logging_obj=logging,
timeout=timeout,
model_response=EmbeddingResponse(),
optional_params=optional_params,
client=client,
aembedding=aembedding
)
elif model in litellm.open_ai_embedding_models or custom_llm_provider == "openai":
api_base = (
api_base
or litellm.api_base
or get_secret("OPENAI_API_BASE")
or "https://api.openai.com/v1"
)
openai.organization = (
litellm.organization
or get_secret("OPENAI_ORGANIZATION")
or None # default - https://github.com/openai/openai-python/blob/284c1799070c723c6a553337134148a7ab088dd8/openai/util.py#L105
)
# set API KEY
api_key = (
api_key or
litellm.api_key or
litellm.openai_key or
get_secret("OPENAI_API_KEY")
)
api_type = "openai"
api_version = None
## EMBEDDING CALL
response = openai_chat_completions.embedding(
model=model,
input=input,
api_base=api_base,
api_key=api_key,
logging_obj=logging,
timeout=timeout,
model_response=EmbeddingResponse(),
optional_params=optional_params,
client=client,
aembedding=aembedding,
)
elif model in litellm.cohere_embedding_models:
cohere_key = (
api_key
or litellm.cohere_key
or get_secret("COHERE_API_KEY")
or get_secret("CO_API_KEY")
or litellm.api_key
)
response = cohere.embedding(
model=model,
input=input,
optional_params=optional_params,
encoding=encoding,
api_key=cohere_key,
logging_obj=logging,
model_response= EmbeddingResponse()
)
elif custom_llm_provider == "huggingface":
api_key = (
api_key
or litellm.huggingface_key
or get_secret("HUGGINGFACE_API_KEY")
or litellm.api_key
)
response = huggingface.embedding(
model=model,
input=input,
encoding=encoding,
api_key=api_key,
api_base=api_base,
logging_obj=logging,
model_response= EmbeddingResponse()
)
elif custom_llm_provider == "bedrock":
response = bedrock.embedding(
model=model,
input=input,
encoding=encoding,
logging_obj=logging,
optional_params=kwargs,
model_response= EmbeddingResponse()
)
else:
args = locals()
raise ValueError(f"No valid embedding model args passed in - {args}")
return response
except Exception as e:
## LOGGING
logging.post_call(
input=input,
api_key=openai.api_key,
original_response=str(e),
)
## Map to OpenAI Exception
raise exception_type(
model=model,
original_exception=e,
custom_llm_provider="azure" if azure == True else None,
)
###### Text Completion ################
def text_completion(
prompt: Union[str, List[Union[str, List[Union[str, List[int]]]]]], # Required: The prompt(s) to generate completions for.
model: Optional[str]=None, # Optional: either `model` or `engine` can be set
best_of: Optional[int] = None, # Optional: Generates best_of completions server-side.
echo: Optional[bool] = None, # Optional: Echo back the prompt in addition to the completion.
frequency_penalty: Optional[float] = None, # Optional: Penalize new tokens based on their existing frequency.
logit_bias: Optional[Dict[int, int]] = None, # Optional: Modify the likelihood of specified tokens.
logprobs: Optional[int] = None, # Optional: Include the log probabilities on the most likely tokens.
max_tokens: Optional[int] = None, # Optional: The maximum number of tokens to generate in the completion.
n: Optional[int] = None, # Optional: How many completions to generate for each prompt.
presence_penalty: Optional[float] = None, # Optional: Penalize new tokens based on whether they appear in the text so far.
stop: Optional[Union[str, List[str]]] = None, # Optional: Sequences where the API will stop generating further tokens.
stream: Optional[bool] = None, # Optional: Whether to stream back partial progress.
suffix: Optional[str] = None, # Optional: The suffix that comes after a completion of inserted text.
temperature: Optional[float] = None, # Optional: Sampling temperature to use.
top_p: Optional[float] = None, # Optional: Nucleus sampling parameter.
user: Optional[str] = None, # Optional: A unique identifier representing your end-user.
# set api_base, api_version, api_key
api_base: Optional[str] = None,
api_version: Optional[str] = None,
api_key: Optional[str] = None,
model_list: Optional[list] = None, # pass in a list of api_base,keys, etc.
# Optional liteLLM function params
custom_llm_provider: Optional[str] = None,
*args,
**kwargs
):
global print_verbose
import copy
"""
Generate text completions using the OpenAI API.
Args:
model (str): ID of the model to use.
prompt (Union[str, List[Union[str, List[Union[str, List[int]]]]]): The prompt(s) to generate completions for.
best_of (Optional[int], optional): Generates best_of completions server-side. Defaults to 1.
echo (Optional[bool], optional): Echo back the prompt in addition to the completion. Defaults to False.
frequency_penalty (Optional[float], optional): Penalize new tokens based on their existing frequency. Defaults to 0.
logit_bias (Optional[Dict[int, int]], optional): Modify the likelihood of specified tokens. Defaults to None.
logprobs (Optional[int], optional): Include the log probabilities on the most likely tokens. Defaults to None.
max_tokens (Optional[int], optional): The maximum number of tokens to generate in the completion. Defaults to 16.
n (Optional[int], optional): How many completions to generate for each prompt. Defaults to 1.
presence_penalty (Optional[float], optional): Penalize new tokens based on whether they appear in the text so far. Defaults to 0.
stop (Optional[Union[str, List[str]]], optional): Sequences where the API will stop generating further tokens. Defaults to None.
stream (Optional[bool], optional): Whether to stream back partial progress. Defaults to False.
suffix (Optional[str], optional): The suffix that comes after a completion of inserted text. Defaults to None.
temperature (Optional[float], optional): Sampling temperature to use. Defaults to 1.
top_p (Optional[float], optional): Nucleus sampling parameter. Defaults to 1.
user (Optional[str], optional): A unique identifier representing your end-user.
Returns:
TextCompletionResponse: A response object containing the generated completion and associated metadata.
Example:
Your example of how to use this function goes here.
"""
if "engine" in kwargs:
if model==None:
# only use engine when model not passed
model = kwargs["engine"]
kwargs.pop("engine")
text_completion_response = TextCompletionResponse()
optional_params: Dict[str, Any] = {}
# default values for all optional params are none, litellm only passes them to the llm when they are set to non None values
if best_of is not None:
optional_params["best_of"] = best_of
if echo is not None:
optional_params["echo"] = echo
if frequency_penalty is not None:
optional_params["frequency_penalty"] = frequency_penalty
if logit_bias is not None:
optional_params["logit_bias"] = logit_bias
if logprobs is not None:
optional_params["logprobs"] = logprobs
if max_tokens is not None:
optional_params["max_tokens"] = max_tokens
if n is not None:
optional_params["n"] = n
if presence_penalty is not None:
optional_params["presence_penalty"] = presence_penalty
if stop is not None:
optional_params["stop"] = stop
if stream is not None:
optional_params["stream"] = stream
if suffix is not None:
optional_params["suffix"] = suffix
if temperature is not None:
optional_params["temperature"] = temperature
if top_p is not None:
optional_params["top_p"] = top_p
if user is not None:
optional_params["user"] = user
if api_base is not None:
optional_params["api_base"] = api_base
if api_version is not None:
optional_params["api_version"] = api_version
if api_key is not None:
optional_params["api_key"] = api_key
if custom_llm_provider is not None:
optional_params["custom_llm_provider"] = custom_llm_provider
# get custom_llm_provider
_, custom_llm_provider, dynamic_api_key, api_base = get_llm_provider(model=model, custom_llm_provider=custom_llm_provider, api_base=api_base) # type: ignore
if custom_llm_provider == "huggingface":
# if echo == True, for TGI llms we need to set top_n_tokens to 3
if echo == True:
# for tgi llms
if "top_n_tokens" not in kwargs:
kwargs["top_n_tokens"] = 3
# processing prompt - users can pass raw tokens to OpenAI Completion()
if type(prompt) == list:
import concurrent.futures
tokenizer = tiktoken.encoding_for_model("text-davinci-003")
## if it's a 2d list - each element in the list is a text_completion() request
if len(prompt) > 0 and type(prompt[0]) == list:
responses = [None for x in prompt] # init responses
def process_prompt(i, individual_prompt):
decoded_prompt = tokenizer.decode(individual_prompt)
all_params = {**kwargs, **optional_params}
response = text_completion(
model=model,
prompt=decoded_prompt,
num_retries=3,# ensure this does not fail for the batch
*args,
**all_params,
)
#print(response)
text_completion_response["id"] = response.get("id", None)
text_completion_response["object"] = "text_completion"
text_completion_response["created"] = response.get("created", None)
text_completion_response["model"] = response.get("model", None)
return response["choices"][0]
with concurrent.futures.ThreadPoolExecutor() as executor:
futures = [executor.submit(process_prompt, i, individual_prompt) for i, individual_prompt in enumerate(prompt)]
for i, future in enumerate(concurrent.futures.as_completed(futures)):
responses[i] = future.result()
text_completion_response.choices = responses
return text_completion_response
# else:
# check if non default values passed in for best_of, echo, logprobs, suffix
# these are the params supported by Completion() but not ChatCompletion
# default case, non OpenAI requests go through here
messages = [{"role": "system", "content": prompt}]
kwargs.pop("prompt", None)
response = completion(
model = model,
messages=messages,
*args,
**kwargs,
**optional_params,
)
if stream == True or kwargs.get("stream", False) == True:
response = TextCompletionStreamWrapper(completion_stream=response, model=model)
return response
transformed_logprobs = None
# only supported for TGI models
try:
raw_response = response._hidden_params.get("original_response", None)
transformed_logprobs = litellm.utils.transform_logprobs(raw_response)
except Exception as e:
print_verbose(f"LiteLLM non blocking exception: {e}")
text_completion_response["id"] = response.get("id", None)
text_completion_response["object"] = "text_completion"
text_completion_response["created"] = response.get("created", None)
text_completion_response["model"] = response.get("model", None)
text_choices = TextChoices()
text_choices["text"] = response["choices"][0]["message"]["content"]
text_choices["index"] = response["choices"][0]["index"]
text_choices["logprobs"] = transformed_logprobs
text_choices["finish_reason"] = response["choices"][0]["finish_reason"]
text_completion_response["choices"] = [text_choices]
text_completion_response["usage"] = response.get("usage", None)
return text_completion_response
##### Moderation #######################
def moderation(input: str, api_key: Optional[str]=None):
# only supports open ai for now
api_key = (
api_key or
litellm.api_key or
litellm.openai_key or
get_secret("OPENAI_API_KEY")
)
openai.api_key = api_key
openai.api_type = "open_ai" # type: ignore
openai.api_version = None
openai.base_url = "https://api.openai.com/v1/"
response = openai.moderations.create(input=input)
return response
####### HELPER FUNCTIONS ################
## Set verbose to true -> ```litellm.set_verbose = True```
def print_verbose(print_statement):
if litellm.set_verbose:
print(print_statement) # noqa
def config_completion(**kwargs):
if litellm.config_path != None:
config_args = read_config_args(litellm.config_path)
# overwrite any args passed in with config args
return completion(**kwargs, **config_args)
else:
raise ValueError(
"No config path set, please set a config path using `litellm.config_path = 'path/to/config.json'`"
)
def stream_chunk_builder(chunks: list, messages: Optional[list]=None):
id = chunks[0]["id"]
object = chunks[0]["object"]
created = chunks[0]["created"]
model = chunks[0]["model"]
system_fingerprint = chunks[0].get("system_fingerprint", None)
role = chunks[0]["choices"][0]["delta"]["role"]
finish_reason = chunks[-1]["choices"][0]["finish_reason"]
# Initialize the response dictionary
response = {
"id": id,
"object": object,
"created": created,
"model": model,
"system_fingerprint": system_fingerprint,
"choices": [
{
"index": 0,
"message": {
"role": role,
"content": ""
},
"finish_reason": finish_reason,
}
],
"usage": {
"prompt_tokens": 0, # Modify as needed
"completion_tokens": 0, # Modify as needed
"total_tokens": 0 # Modify as needed
}
}
# Extract the "content" strings from the nested dictionaries within "choices"
content_list = []
combined_content = ""
combined_arguments = ""
if "tool_calls" in chunks[0]["choices"][0]["delta"] and chunks[0]["choices"][0]["delta"]["tool_calls"] is not None:
argument_list = []
delta = chunks[0]["choices"][0]["delta"]
message = response["choices"][0]["message"]
message["tool_calls"] = []
id = None
name = None
type = None
tool_calls_list = []
prev_index = 0
prev_id = None
curr_id = None
curr_index = 0
for chunk in chunks:
choices = chunk["choices"]
for choice in choices:
delta = choice.get("delta", {})
tool_calls = delta.get("tool_calls", "")
# Check if a tool call is present
if tool_calls and tool_calls[0].function is not None:
if tool_calls[0].id:
id = tool_calls[0].id
curr_id = id
if prev_id is None:
prev_id = curr_id
if tool_calls[0].index:
curr_index = tool_calls[0].index
if tool_calls[0].function.arguments:
# Now, tool_calls is expected to be a dictionary
arguments = tool_calls[0].function.arguments
argument_list.append(arguments)
if tool_calls[0].function.name:
name = tool_calls[0].function.name
if tool_calls[0].type:
type = tool_calls[0].type
if curr_index != prev_index: # new tool call
combined_arguments = "".join(argument_list)
tool_calls_list.append({"id": prev_id, "index": prev_index, "function": {"arguments": combined_arguments, "name": name}, "type": type})
argument_list = [] # reset
prev_index = curr_index
prev_id = curr_id
combined_arguments = "".join(argument_list)
tool_calls_list.append({"id": id, "function": {"arguments": combined_arguments, "name": name}, "type": type})
response["choices"][0]["message"]["content"] = None
response["choices"][0]["message"]["tool_calls"] = tool_calls_list
elif "function_call" in chunks[0]["choices"][0]["delta"] and chunks[0]["choices"][0]["delta"]["function_call"] is not None:
argument_list = []
delta = chunks[0]["choices"][0]["delta"]
function_call = delta.get("function_call", "")
function_call_name = function_call.name
message = response["choices"][0]["message"]
message["function_call"] = {}
message["function_call"]["name"] = function_call_name
for chunk in chunks:
choices = chunk["choices"]
for choice in choices:
delta = choice.get("delta", {})
function_call = delta.get("function_call", "")
# Check if a function call is present
if function_call:
# Now, function_call is expected to be a dictionary
arguments = function_call.arguments
argument_list.append(arguments)
combined_arguments = "".join(argument_list)
response["choices"][0]["message"]["content"] = None
response["choices"][0]["message"]["function_call"]["arguments"] = combined_arguments
else:
for chunk in chunks:
choices = chunk["choices"]
for choice in choices:
delta = choice.get("delta", {})
content = delta.get("content", "")
if content == None:
continue # openai v1.0.0 sets content = None for chunks
content_list.append(content)
# Combine the "content" strings into a single string || combine the 'function' strings into a single string
combined_content = "".join(content_list)
# Update the "content" field within the response dictionary
response["choices"][0]["message"]["content"] = combined_content
if len(combined_content) > 0:
completion_output = combined_content
elif len(combined_arguments) > 0:
completion_output = combined_arguments
# # Update usage information if needed
try:
response["usage"]["prompt_tokens"] = token_counter(model=model, messages=messages)
except: # don't allow this failing to block a complete streaming response from being returned
print_verbose(f"token_counter failed, assuming prompt tokens is 0")
response["usage"]["prompt_tokens"] = 0
response["usage"]["completion_tokens"] = token_counter(model=model, text=completion_output)
response["usage"]["total_tokens"] = response["usage"]["prompt_tokens"] + response["usage"]["completion_tokens"]
return convert_to_model_response_object(response_object=response, model_response_object=litellm.ModelResponse())
|