File size: 11,854 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 |
import json
from typing import Callable, List, Optional, Union
from openai import AsyncOpenAI, OpenAI
import litellm
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
from litellm.litellm_core_utils.streaming_handler import CustomStreamWrapper
from litellm.llms.base import BaseLLM
from litellm.types.llms.openai import AllMessageValues, OpenAITextCompletionUserMessage
from litellm.types.utils import LlmProviders, ModelResponse, TextCompletionResponse
from litellm.utils import ProviderConfigManager
from ..common_utils import OpenAIError
from .transformation import OpenAITextCompletionConfig
class OpenAITextCompletion(BaseLLM):
openai_text_completion_global_config = OpenAITextCompletionConfig()
def __init__(self) -> None:
super().__init__()
def validate_environment(self, api_key):
headers = {
"content-type": "application/json",
}
if api_key:
headers["Authorization"] = f"Bearer {api_key}"
return headers
def completion(
self,
model_response: ModelResponse,
api_key: str,
model: str,
messages: Union[List[AllMessageValues], List[OpenAITextCompletionUserMessage]],
timeout: float,
custom_llm_provider: str,
logging_obj: LiteLLMLoggingObj,
optional_params: dict,
print_verbose: Optional[Callable] = None,
api_base: Optional[str] = None,
acompletion: bool = False,
litellm_params=None,
logger_fn=None,
client=None,
organization: Optional[str] = None,
headers: Optional[dict] = None,
):
try:
if headers is None:
headers = self.validate_environment(api_key=api_key)
if model is None or messages is None:
raise OpenAIError(status_code=422, message="Missing model or messages")
# don't send max retries to the api, if set
provider_config = ProviderConfigManager.get_provider_text_completion_config(
model=model,
provider=LlmProviders(custom_llm_provider),
)
data = provider_config.transform_text_completion_request(
model=model,
messages=messages,
optional_params=optional_params,
headers=headers,
)
max_retries = data.pop("max_retries", 2)
## LOGGING
logging_obj.pre_call(
input=messages,
api_key=api_key,
additional_args={
"headers": headers,
"api_base": api_base,
"complete_input_dict": data,
},
)
if acompletion is True:
if optional_params.get("stream", False):
return self.async_streaming(
logging_obj=logging_obj,
api_base=api_base,
api_key=api_key,
data=data,
headers=headers,
model_response=model_response,
model=model,
timeout=timeout,
max_retries=max_retries,
client=client,
organization=organization,
)
else:
return self.acompletion(api_base=api_base, data=data, headers=headers, model_response=model_response, api_key=api_key, logging_obj=logging_obj, model=model, timeout=timeout, max_retries=max_retries, organization=organization, client=client) # type: ignore
elif optional_params.get("stream", False):
return self.streaming(
logging_obj=logging_obj,
api_base=api_base,
api_key=api_key,
data=data,
headers=headers,
model_response=model_response,
model=model,
timeout=timeout,
max_retries=max_retries, # type: ignore
client=client,
organization=organization,
)
else:
if client is None:
openai_client = OpenAI(
api_key=api_key,
base_url=api_base,
http_client=litellm.client_session,
timeout=timeout,
max_retries=max_retries, # type: ignore
organization=organization,
)
else:
openai_client = client
raw_response = openai_client.completions.with_raw_response.create(**data) # type: ignore
response = raw_response.parse()
response_json = response.model_dump()
## LOGGING
logging_obj.post_call(
api_key=api_key,
original_response=response_json,
additional_args={
"headers": headers,
"api_base": api_base,
},
)
## RESPONSE OBJECT
return TextCompletionResponse(**response_json)
except Exception as e:
status_code = getattr(e, "status_code", 500)
error_headers = getattr(e, "headers", None)
error_text = getattr(e, "text", str(e))
error_response = getattr(e, "response", None)
if error_headers is None and error_response:
error_headers = getattr(error_response, "headers", None)
raise OpenAIError(
status_code=status_code, message=error_text, headers=error_headers
)
async def acompletion(
self,
logging_obj,
api_base: str,
data: dict,
headers: dict,
model_response: ModelResponse,
api_key: str,
model: str,
timeout: float,
max_retries: int,
organization: Optional[str] = None,
client=None,
):
try:
if client is None:
openai_aclient = AsyncOpenAI(
api_key=api_key,
base_url=api_base,
http_client=litellm.aclient_session,
timeout=timeout,
max_retries=max_retries,
organization=organization,
)
else:
openai_aclient = client
raw_response = await openai_aclient.completions.with_raw_response.create(
**data
)
response = raw_response.parse()
response_json = response.model_dump()
## LOGGING
logging_obj.post_call(
api_key=api_key,
original_response=response,
additional_args={
"headers": headers,
"api_base": api_base,
},
)
## RESPONSE OBJECT
response_obj = TextCompletionResponse(**response_json)
response_obj._hidden_params.original_response = json.dumps(response_json)
return response_obj
except Exception as e:
status_code = getattr(e, "status_code", 500)
error_headers = getattr(e, "headers", None)
error_text = getattr(e, "text", str(e))
error_response = getattr(e, "response", None)
if error_headers is None and error_response:
error_headers = getattr(error_response, "headers", None)
raise OpenAIError(
status_code=status_code, message=error_text, headers=error_headers
)
def streaming(
self,
logging_obj,
api_key: str,
data: dict,
headers: dict,
model_response: ModelResponse,
model: str,
timeout: float,
api_base: Optional[str] = None,
max_retries=None,
client=None,
organization=None,
):
if client is None:
openai_client = OpenAI(
api_key=api_key,
base_url=api_base,
http_client=litellm.client_session,
timeout=timeout,
max_retries=max_retries, # type: ignore
organization=organization,
)
else:
openai_client = client
try:
raw_response = openai_client.completions.with_raw_response.create(**data)
response = raw_response.parse()
except Exception as e:
status_code = getattr(e, "status_code", 500)
error_headers = getattr(e, "headers", None)
error_text = getattr(e, "text", str(e))
error_response = getattr(e, "response", None)
if error_headers is None and error_response:
error_headers = getattr(error_response, "headers", None)
raise OpenAIError(
status_code=status_code, message=error_text, headers=error_headers
)
streamwrapper = CustomStreamWrapper(
completion_stream=response,
model=model,
custom_llm_provider="text-completion-openai",
logging_obj=logging_obj,
stream_options=data.get("stream_options", None),
)
try:
for chunk in streamwrapper:
yield chunk
except Exception as e:
status_code = getattr(e, "status_code", 500)
error_headers = getattr(e, "headers", None)
error_text = getattr(e, "text", str(e))
error_response = getattr(e, "response", None)
if error_headers is None and error_response:
error_headers = getattr(error_response, "headers", None)
raise OpenAIError(
status_code=status_code, message=error_text, headers=error_headers
)
async def async_streaming(
self,
logging_obj,
api_key: str,
data: dict,
headers: dict,
model_response: ModelResponse,
model: str,
timeout: float,
max_retries: int,
api_base: Optional[str] = None,
client=None,
organization=None,
):
if client is None:
openai_client = AsyncOpenAI(
api_key=api_key,
base_url=api_base,
http_client=litellm.aclient_session,
timeout=timeout,
max_retries=max_retries,
organization=organization,
)
else:
openai_client = client
raw_response = await openai_client.completions.with_raw_response.create(**data)
response = raw_response.parse()
streamwrapper = CustomStreamWrapper(
completion_stream=response,
model=model,
custom_llm_provider="text-completion-openai",
logging_obj=logging_obj,
stream_options=data.get("stream_options", None),
)
try:
async for transformed_chunk in streamwrapper:
yield transformed_chunk
except Exception as e:
status_code = getattr(e, "status_code", 500)
error_headers = getattr(e, "headers", None)
error_text = getattr(e, "text", str(e))
error_response = getattr(e, "response", None)
if error_headers is None and error_response:
error_headers = getattr(error_response, "headers", None)
raise OpenAIError(
status_code=status_code, message=error_text, headers=error_headers
)
|