openai_gpt
langroid/language_models/openai_gpt.py
OpenAICallParams
¶
Bases: BaseModel
Various params that can be sent to an OpenAI API chat-completion call. When specified, any param here overrides the one with same name in the OpenAIGPTConfig. See OpenAI API Reference for details on the params: https://platform.openai.com/docs/api-reference/chat
LiteLLMProxyConfig
¶
Bases: BaseSettings
Configuration for LiteLLM proxy connection.
OpenAIGPTConfig(**kwargs)
¶
Bases: LLMConfig
Class for any LLM with an OpenAI-like API: besides the OpenAI models this includes: (a) locally-served models behind an OpenAI-compatible API (b) non-local models, using a proxy adaptor lib like litellm that provides an OpenAI-compatible API. (We could rename this class to OpenAILikeConfig, but we keep it as-is for now)
Important Note:
Due to the env_prefix = "OPENAI_" defined below,
all of the fields below can be set AND OVERRIDDEN via env vars,
by upper-casing the name and prefixing with OPENAI_, e.g.¶
OPENAI_MAX_OUTPUT_TOKENS=1000.¶
If any of these is defined in this way in the environment¶
(either via explicit setenv or export or via .env file + load_dotenv()),¶
the environment variable takes precedence over the value in the config.¶
Source code in langroid/language_models/openai_gpt.py
model_copy(*, update=None, deep=False)
¶
Copy config while preserving nested model instances and subclasses.
Important: Avoid reconstructing via model_dump as that coerces nested
models to their annotated base types (dropping subclass-only fields).
Instead, defer to Pydantic's native model_copy, which keeps nested
BaseModel instances (and their concrete subclasses) intact.
An api_base supplied through update is caller configuration, so the
copy must retain that provenance for provider-specific routing.
Source code in langroid/language_models/openai_gpt.py
create(prefix)
classmethod
¶
Create a config class whose params can be set via a desired prefix from the .env file or env vars. E.g., using
you can have a group of params prefixed by "OLLAMA_", to be used with models served viaollama.
This way, you can maintain several setting-groups in your .env file,
one per model type.
Source code in langroid/language_models/openai_gpt.py
VertexAIConfig(**kwargs)
¶
Bases: OpenAIGPTConfig
Config for Google Vertex AI models served at its OpenAI-compatible endpoint,
i.e. chat_model="vertexai/<publisher>/<model>".
This is a separate config class, rather than extra fields on
OpenAIGPTConfig, for one reason: OpenAIGPTConfig is a pydantic
BaseSettings with env_prefix="OPENAI_", so a config built in a process
that has OPENAI_API_KEY, OPENAI_HEADERS, OPENAI_ORGANIZATION or
OPENAI_API_BASE set inherits every one of them -- and would then send
them to Google. Overriding env_prefix to VERTEXAI_ means those
variables are not an env source for this class at all, so there is nothing
to inherit: the fix is structural rather than a field-by-field scrub.
Credentials, in precedence order:
api_key_provider, called per request (so a rotating token never goes stale);api_key(orVERTEXAI_API_KEY);- otherwise Google Application Default Credentials, installed as an
api_key_provider, which requiresgcloud auth application-default loginorGOOGLE_APPLICATION_CREDENTIALS.
See docs/notes/gemini.md.
Source code in langroid/language_models/openai_gpt.py
OpenAIResponse
¶
Bases: BaseModel
OpenAI response model, either completion or chat.
OpenAIGPT(config=OpenAIGPTConfig())
¶
Bases: LanguageModel
Class for OpenAI LLMs
Source code in langroid/language_models/openai_gpt.py
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 | |
is_gemini_model()
¶
is_minimax_model()
¶
Are we using the MiniMax OpenAI-compatible API?
Source code in langroid/language_models/openai_gpt.py
unsupported_params()
¶
List of params that are not supported by the current model
rename_params()
¶
Map of param name -> new name for specific models. Currently main troublemaker is o1* series.
chat_context_length()
¶
Context-length for chat-completion models/endpoints. Get it from the config if explicitly given, otherwise use model_info based on model name, and fall back to generic model_info if there's no match.
Source code in langroid/language_models/openai_gpt.py
completion_context_length()
¶
Context-length for completion models/endpoints. Get it from the config if explicitly given, otherwise use model_info based on model name, and fall back to generic model_info if there's no match.
Source code in langroid/language_models/openai_gpt.py
chat_cost()
¶
(Prompt, Cached, Generation) cost per 1000 tokens, for chat-completion models/endpoints. Get it from the dict, otherwise fail-over to general method
Source code in langroid/language_models/openai_gpt.py
set_stream(stream)
¶
Enable or disable streaming output from API. Args: stream: enable streaming output from API Returns: previous value of stream
Source code in langroid/language_models/openai_gpt.py
get_stream()
¶
tool_deltas_to_tools(tools, strict=False)
staticmethod
¶
Convert accumulated tool-call deltas to OpenAIToolCall objects. Adapted from this excellent code: https://community.openai.com/t/help-for-function-calls-with-streaming/627170/2
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
tools
|
List[Dict[str, Any]]
|
list of tool deltas received from streaming API |
required |
strict
|
bool
|
if True, discard any call whose accumulated |
False
|
Returns:
| Name | Type | Description |
|---|---|---|
str |
str
|
plain text corresponding to tool calls that failed to parse |
List[OpenAIToolCall]
|
List[OpenAIToolCall]: list of OpenAIToolCall objects |
|
List[Dict[str, Any]]
|
List[Dict[str, Any]]: list of tool dicts (to reconstruct OpenAI API response, so it can be cached) |
Source code in langroid/language_models/openai_gpt.py
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 | |
noop()
¶
litellm_logging_fn(model_call_dict)
¶
Logging function for litellm