File size: 13,925 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 |
# What is this?
## handler file for TextCompletionCodestral Integration - https://codestral.com/
import json
from functools import partial
from typing import Callable, List, Optional, Union
import httpx # type: ignore
import litellm
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLogging
from litellm.litellm_core_utils.prompt_templates.factory import (
custom_prompt,
prompt_factory,
)
from litellm.llms.custom_httpx.http_handler import (
AsyncHTTPHandler,
get_async_httpx_client,
)
from litellm.types.utils import TextChoices
from litellm.utils import CustomStreamWrapper, TextCompletionResponse
class TextCompletionCodestralError(Exception):
def __init__(
self,
status_code,
message,
request: Optional[httpx.Request] = None,
response: Optional[httpx.Response] = None,
):
self.status_code = status_code
self.message = message
if request is not None:
self.request = request
else:
self.request = httpx.Request(
method="POST",
url="https://docs.codestral.com/user-guide/inference/rest_api",
)
if response is not None:
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
async def make_call(
client: AsyncHTTPHandler,
api_base: str,
headers: dict,
data: str,
model: str,
messages: list,
logging_obj,
):
response = await client.post(api_base, headers=headers, data=data, stream=True)
if response.status_code != 200:
raise TextCompletionCodestralError(
status_code=response.status_code, message=response.text
)
completion_stream = response.aiter_lines()
# LOGGING
logging_obj.post_call(
input=messages,
api_key="",
original_response=completion_stream, # Pass the completion stream for logging
additional_args={"complete_input_dict": data},
)
return completion_stream
class CodestralTextCompletion:
def __init__(self) -> None:
super().__init__()
def _validate_environment(
self,
api_key: Optional[str],
user_headers: dict,
) -> dict:
if api_key is None:
raise ValueError(
"Missing CODESTRAL_API_Key - Please add CODESTRAL_API_Key to your environment variables"
)
headers = {
"content-type": "application/json",
"Authorization": "Bearer {}".format(api_key),
}
if user_headers is not None and isinstance(user_headers, dict):
headers = {**headers, **user_headers}
return headers
def output_parser(self, generated_text: str):
"""
Parse the output text to remove any special characters. In our current approach we just check for ChatML tokens.
Initial issue that prompted this - https://github.com/BerriAI/litellm/issues/763
"""
chat_template_tokens = [
"<|assistant|>",
"<|system|>",
"<|user|>",
"<s>",
"</s>",
]
for token in chat_template_tokens:
if generated_text.strip().startswith(token):
generated_text = generated_text.replace(token, "", 1)
if generated_text.endswith(token):
generated_text = generated_text[::-1].replace(token[::-1], "", 1)[::-1]
return generated_text
def process_text_completion_response(
self,
model: str,
response: httpx.Response,
model_response: TextCompletionResponse,
stream: bool,
logging_obj: LiteLLMLogging,
optional_params: dict,
api_key: str,
data: Union[dict, str],
messages: list,
print_verbose,
encoding,
) -> TextCompletionResponse:
## LOGGING
logging_obj.post_call(
input=messages,
api_key=api_key,
original_response=response.text,
additional_args={"complete_input_dict": data},
)
print_verbose(f"codestral api: raw model_response: {response.text}")
## RESPONSE OBJECT
if response.status_code != 200:
raise TextCompletionCodestralError(
message=str(response.text),
status_code=response.status_code,
)
try:
completion_response = response.json()
except Exception:
raise TextCompletionCodestralError(message=response.text, status_code=422)
_original_choices = completion_response.get("choices", [])
_choices: List[TextChoices] = []
for choice in _original_choices:
# This is what 1 choice looks like from codestral API
# {
# "index": 0,
# "message": {
# "role": "assistant",
# "content": "\n assert is_odd(1)\n assert",
# "tool_calls": null
# },
# "finish_reason": "length",
# "logprobs": null
# }
_finish_reason = None
_index = 0
_text = None
_logprobs = None
_choice_message = choice.get("message", {})
_choice = litellm.utils.TextChoices(
finish_reason=choice.get("finish_reason"),
index=choice.get("index"),
text=_choice_message.get("content"),
logprobs=choice.get("logprobs"),
)
_choices.append(_choice)
_response = litellm.TextCompletionResponse(
id=completion_response.get("id"),
choices=_choices,
created=completion_response.get("created"),
model=completion_response.get("model"),
usage=completion_response.get("usage"),
stream=False,
object=completion_response.get("object"),
)
return _response
def completion(
self,
model: str,
messages: list,
api_base: str,
custom_prompt_dict: dict,
model_response: TextCompletionResponse,
print_verbose: Callable,
encoding,
api_key: str,
logging_obj,
optional_params: dict,
timeout: Union[float, httpx.Timeout],
acompletion=None,
litellm_params=None,
logger_fn=None,
headers: dict = {},
) -> Union[TextCompletionResponse, CustomStreamWrapper]:
headers = self._validate_environment(api_key, headers)
if optional_params.pop("custom_endpoint", None) is True:
completion_url = api_base
else:
completion_url = (
api_base or "https://codestral.mistral.ai/v1/fim/completions"
)
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)
## Load Config
config = litellm.CodestralTextCompletionConfig.get_config()
for k, v in config.items():
if (
k not in optional_params
): # completion(top_k=3) > anthropic_config(top_k=3) <- allows for dynamic variables to be passed in
optional_params[k] = v
stream = optional_params.pop("stream", False)
data = {
"model": model,
"prompt": prompt,
**optional_params,
}
input_text = prompt
## LOGGING
logging_obj.pre_call(
input=input_text,
api_key=api_key,
additional_args={
"complete_input_dict": data,
"headers": headers,
"api_base": completion_url,
"acompletion": acompletion,
},
)
## COMPLETION CALL
if acompletion is True:
### ASYNC STREAMING
if stream is True:
return self.async_streaming(
model=model,
messages=messages,
data=data,
api_base=completion_url,
model_response=model_response,
print_verbose=print_verbose,
encoding=encoding,
api_key=api_key,
logging_obj=logging_obj,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
headers=headers,
timeout=timeout,
) # type: ignore
else:
### ASYNC COMPLETION
return self.async_completion(
model=model,
messages=messages,
data=data,
api_base=completion_url,
model_response=model_response,
print_verbose=print_verbose,
encoding=encoding,
api_key=api_key,
logging_obj=logging_obj,
optional_params=optional_params,
stream=False,
litellm_params=litellm_params,
logger_fn=logger_fn,
headers=headers,
timeout=timeout,
) # type: ignore
### SYNC STREAMING
if stream is True:
response = litellm.module_level_client.post(
completion_url,
headers=headers,
data=json.dumps(data),
stream=stream,
)
_response = CustomStreamWrapper(
response.iter_lines(),
model,
custom_llm_provider="codestral",
logging_obj=logging_obj,
)
return _response
### SYNC COMPLETION
else:
response = litellm.module_level_client.post(
url=completion_url,
headers=headers,
data=json.dumps(data),
)
return self.process_text_completion_response(
model=model,
response=response,
model_response=model_response,
stream=optional_params.get("stream", False),
logging_obj=logging_obj, # type: ignore
optional_params=optional_params,
api_key=api_key,
data=data,
messages=messages,
print_verbose=print_verbose,
encoding=encoding,
)
async def async_completion(
self,
model: str,
messages: list,
api_base: str,
model_response: TextCompletionResponse,
print_verbose: Callable,
encoding,
api_key,
logging_obj,
stream,
data: dict,
optional_params: dict,
timeout: Union[float, httpx.Timeout],
litellm_params=None,
logger_fn=None,
headers={},
) -> TextCompletionResponse:
async_handler = get_async_httpx_client(
llm_provider=litellm.LlmProviders.TEXT_COMPLETION_CODESTRAL,
params={"timeout": timeout},
)
try:
response = await async_handler.post(
api_base, headers=headers, data=json.dumps(data)
)
except httpx.HTTPStatusError as e:
raise TextCompletionCodestralError(
status_code=e.response.status_code,
message="HTTPStatusError - {}".format(e.response.text),
)
except Exception as e:
raise TextCompletionCodestralError(
status_code=500, message="{}".format(str(e))
) # don't use verbose_logger.exception, if exception is raised
return self.process_text_completion_response(
model=model,
response=response,
model_response=model_response,
stream=stream,
logging_obj=logging_obj,
api_key=api_key,
data=data,
messages=messages,
print_verbose=print_verbose,
optional_params=optional_params,
encoding=encoding,
)
async def async_streaming(
self,
model: str,
messages: list,
api_base: str,
model_response: TextCompletionResponse,
print_verbose: Callable,
encoding,
api_key,
logging_obj,
data: dict,
timeout: Union[float, httpx.Timeout],
optional_params=None,
litellm_params=None,
logger_fn=None,
headers={},
) -> CustomStreamWrapper:
data["stream"] = True
streamwrapper = CustomStreamWrapper(
completion_stream=None,
make_call=partial(
make_call,
api_base=api_base,
headers=headers,
data=json.dumps(data),
model=model,
messages=messages,
logging_obj=logging_obj,
),
model=model,
custom_llm_provider="text-completion-codestral",
logging_obj=logging_obj,
)
return streamwrapper
def embedding(self, *args, **kwargs):
pass
|