File size: 6,193 Bytes
e3278e4 |
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 |
"""
Common base config for all LLM providers
"""
import types
from abc import ABC, abstractmethod
from typing import (
TYPE_CHECKING,
Any,
AsyncIterator,
Iterator,
List,
Optional,
Type,
Union,
)
import httpx
from pydantic import BaseModel
from litellm._logging import verbose_logger
from litellm.types.llms.openai import AllMessageValues
from litellm.types.utils import ModelResponse
from ..base_utils import (
map_developer_role_to_system_role,
type_to_response_format_param,
)
if TYPE_CHECKING:
from litellm.litellm_core_utils.litellm_logging import Logging as _LiteLLMLoggingObj
LiteLLMLoggingObj = _LiteLLMLoggingObj
else:
LiteLLMLoggingObj = Any
class BaseLLMException(Exception):
def __init__(
self,
status_code: int,
message: str,
headers: Optional[Union[dict, httpx.Headers]] = None,
request: Optional[httpx.Request] = None,
response: Optional[httpx.Response] = None,
):
self.status_code = status_code
self.message: str = message
self.headers = headers
if request:
self.request = request
else:
self.request = httpx.Request(
method="POST", url="https://docs.litellm.ai/docs"
)
if response:
self.response = response
else:
self.response = httpx.Response(
status_code=status_code, request=self.request
)
super().__init__(
self.message
) # Call the base class constructor with the parameters it needs
class BaseConfig(ABC):
def __init__(self):
pass
@classmethod
def get_config(cls):
return {
k: v
for k, v in cls.__dict__.items()
if not k.startswith("__")
and not k.startswith("_abc")
and not isinstance(
v,
(
types.FunctionType,
types.BuiltinFunctionType,
classmethod,
staticmethod,
),
)
and v is not None
}
def get_json_schema_from_pydantic_object(
self, response_format: Optional[Union[Type[BaseModel], dict]]
) -> Optional[dict]:
return type_to_response_format_param(response_format=response_format)
def should_fake_stream(
self,
model: Optional[str],
stream: Optional[bool],
custom_llm_provider: Optional[str] = None,
) -> bool:
"""
Returns True if the model/provider should fake stream
"""
return False
def translate_developer_role_to_system_role(
self,
messages: List[AllMessageValues],
) -> List[AllMessageValues]:
"""
Translate `developer` role to `system` role for non-OpenAI providers.
Overriden by OpenAI/Azure
"""
verbose_logger.debug(
"Translating developer role to system role for non-OpenAI providers."
) # ensure user knows what's happening with their input.
return map_developer_role_to_system_role(messages=messages)
def should_retry_llm_api_inside_llm_translation_on_http_error(
self, e: httpx.HTTPStatusError, litellm_params: dict
) -> bool:
"""
Returns True if the model/provider should retry the LLM API on UnprocessableEntityError
Overriden by azure ai - where different models support different parameters
"""
return False
def transform_request_on_unprocessable_entity_error(
self, e: httpx.HTTPStatusError, request_data: dict
) -> dict:
"""
Transform the request data on UnprocessableEntityError
"""
return request_data
@property
def max_retry_on_unprocessable_entity_error(self) -> int:
"""
Returns the max retry count for UnprocessableEntityError
Used if `should_retry_llm_api_inside_llm_translation_on_http_error` is True
"""
return 0
@abstractmethod
def get_supported_openai_params(self, model: str) -> list:
pass
@abstractmethod
def map_openai_params(
self,
non_default_params: dict,
optional_params: dict,
model: str,
drop_params: bool,
) -> dict:
pass
@abstractmethod
def validate_environment(
self,
headers: dict,
model: str,
messages: List[AllMessageValues],
optional_params: dict,
api_key: Optional[str] = None,
api_base: Optional[str] = None,
) -> dict:
pass
def get_complete_url(
self,
api_base: str,
model: str,
optional_params: dict,
stream: Optional[bool] = None,
) -> str:
"""
OPTIONAL
Get the complete url for the request
Some providers need `model` in `api_base`
"""
return api_base
@abstractmethod
def transform_request(
self,
model: str,
messages: List[AllMessageValues],
optional_params: dict,
litellm_params: dict,
headers: dict,
) -> dict:
pass
@abstractmethod
def transform_response(
self,
model: str,
raw_response: httpx.Response,
model_response: ModelResponse,
logging_obj: LiteLLMLoggingObj,
request_data: dict,
messages: List[AllMessageValues],
optional_params: dict,
litellm_params: dict,
encoding: Any,
api_key: Optional[str] = None,
json_mode: Optional[bool] = None,
) -> ModelResponse:
pass
@abstractmethod
def get_error_class(
self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers]
) -> BaseLLMException:
pass
def get_model_response_iterator(
self,
streaming_response: Union[Iterator[str], AsyncIterator[str], ModelResponse],
sync_stream: bool,
json_mode: Optional[bool] = False,
) -> Any:
pass
@property
def custom_llm_provider(self) -> Optional[str]:
return None
|