File size: 17,190 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 |
import json
import urllib
from typing import Any, Callable, Optional, Union
import httpx
import litellm
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObject
from litellm.llms.custom_httpx.http_handler import (
AsyncHTTPHandler,
HTTPHandler,
_get_httpx_client,
get_async_httpx_client,
)
from litellm.types.utils import ModelResponse
from litellm.utils import CustomStreamWrapper, get_secret
from ..base_aws_llm import BaseAWSLLM, Credentials
from ..common_utils import BedrockError
from .invoke_handler import AWSEventStreamDecoder, MockResponseIterator, make_call
def make_sync_call(
client: Optional[HTTPHandler],
api_base: str,
headers: dict,
data: str,
model: str,
messages: list,
logging_obj: LiteLLMLoggingObject,
json_mode: Optional[bool] = False,
fake_stream: bool = False,
):
if client is None:
client = _get_httpx_client() # Create a new client if none provided
response = client.post(
api_base,
headers=headers,
data=data,
stream=not fake_stream,
logging_obj=logging_obj,
)
if response.status_code != 200:
raise BedrockError(
status_code=response.status_code, message=str(response.read())
)
if fake_stream:
model_response: (
ModelResponse
) = litellm.AmazonConverseConfig()._transform_response(
model=model,
response=response,
model_response=litellm.ModelResponse(),
stream=True,
logging_obj=logging_obj,
optional_params={},
api_key="",
data=data,
messages=messages,
print_verbose=litellm.print_verbose,
encoding=litellm.encoding,
) # type: ignore
completion_stream: Any = MockResponseIterator(
model_response=model_response, json_mode=json_mode
)
else:
decoder = AWSEventStreamDecoder(model=model)
completion_stream = decoder.iter_bytes(response.iter_bytes(chunk_size=1024))
# LOGGING
logging_obj.post_call(
input=messages,
api_key="",
original_response="first stream response received",
additional_args={"complete_input_dict": data},
)
return completion_stream
class BedrockConverseLLM(BaseAWSLLM):
def __init__(self) -> None:
super().__init__()
def encode_model_id(self, model_id: str) -> str:
"""
Double encode the model ID to ensure it matches the expected double-encoded format.
Args:
model_id (str): The model ID to encode.
Returns:
str: The double-encoded model ID.
"""
return urllib.parse.quote(model_id, safe="") # type: ignore
async def async_streaming(
self,
model: str,
messages: list,
api_base: str,
model_response: ModelResponse,
print_verbose: Callable,
timeout: Optional[Union[float, httpx.Timeout]],
encoding,
logging_obj,
stream,
optional_params: dict,
litellm_params: dict,
credentials: Credentials,
logger_fn=None,
headers={},
client: Optional[AsyncHTTPHandler] = None,
fake_stream: bool = False,
json_mode: Optional[bool] = False,
) -> CustomStreamWrapper:
request_data = await litellm.AmazonConverseConfig()._async_transform_request(
model=model,
messages=messages,
optional_params=optional_params,
litellm_params=litellm_params,
)
data = json.dumps(request_data)
prepped = self.get_request_headers(
credentials=credentials,
aws_region_name=litellm_params.get("aws_region_name") or "us-west-2",
extra_headers=headers,
endpoint_url=api_base,
data=data,
headers=headers,
)
## LOGGING
logging_obj.pre_call(
input=messages,
api_key="",
additional_args={
"complete_input_dict": data,
"api_base": api_base,
"headers": dict(prepped.headers),
},
)
completion_stream = await make_call(
client=client,
api_base=api_base,
headers=dict(prepped.headers),
data=data,
model=model,
messages=messages,
logging_obj=logging_obj,
fake_stream=fake_stream,
json_mode=json_mode,
)
streaming_response = CustomStreamWrapper(
completion_stream=completion_stream,
model=model,
custom_llm_provider="bedrock",
logging_obj=logging_obj,
)
return streaming_response
async def async_completion(
self,
model: str,
messages: list,
api_base: str,
model_response: ModelResponse,
print_verbose: Callable,
timeout: Optional[Union[float, httpx.Timeout]],
encoding,
logging_obj: LiteLLMLoggingObject,
stream,
optional_params: dict,
litellm_params: dict,
credentials: Credentials,
logger_fn=None,
headers: dict = {},
client: Optional[AsyncHTTPHandler] = None,
) -> Union[ModelResponse, CustomStreamWrapper]:
request_data = await litellm.AmazonConverseConfig()._async_transform_request(
model=model,
messages=messages,
optional_params=optional_params,
litellm_params=litellm_params,
)
data = json.dumps(request_data)
prepped = self.get_request_headers(
credentials=credentials,
aws_region_name=litellm_params.get("aws_region_name") or "us-west-2",
extra_headers=headers,
endpoint_url=api_base,
data=data,
headers=headers,
)
## LOGGING
logging_obj.pre_call(
input=messages,
api_key="",
additional_args={
"complete_input_dict": data,
"api_base": api_base,
"headers": prepped.headers,
},
)
headers = dict(prepped.headers)
if client is None or not isinstance(client, AsyncHTTPHandler):
_params = {}
if timeout is not None:
if isinstance(timeout, float) or isinstance(timeout, int):
timeout = httpx.Timeout(timeout)
_params["timeout"] = timeout
client = get_async_httpx_client(
params=_params, llm_provider=litellm.LlmProviders.BEDROCK
)
else:
client = client # type: ignore
try:
response = await client.post(
url=api_base,
headers=headers,
data=data,
logging_obj=logging_obj,
) # type: ignore
response.raise_for_status()
except httpx.HTTPStatusError as err:
error_code = err.response.status_code
raise BedrockError(status_code=error_code, message=err.response.text)
except httpx.TimeoutException:
raise BedrockError(status_code=408, message="Timeout error occurred.")
return litellm.AmazonConverseConfig()._transform_response(
model=model,
response=response,
model_response=model_response,
stream=stream if isinstance(stream, bool) else False,
logging_obj=logging_obj,
api_key="",
data=data,
messages=messages,
print_verbose=print_verbose,
optional_params=optional_params,
encoding=encoding,
)
def completion( # noqa: PLR0915
self,
model: str,
messages: list,
api_base: Optional[str],
custom_prompt_dict: dict,
model_response: ModelResponse,
print_verbose: Callable,
encoding,
logging_obj: LiteLLMLoggingObject,
optional_params: dict,
acompletion: bool,
timeout: Optional[Union[float, httpx.Timeout]],
litellm_params: dict,
logger_fn=None,
extra_headers: Optional[dict] = None,
client: Optional[Union[AsyncHTTPHandler, HTTPHandler]] = None,
):
try:
from botocore.credentials import Credentials
except ImportError:
raise ImportError("Missing boto3 to call bedrock. Run 'pip install boto3'.")
## SETUP ##
stream = optional_params.pop("stream", None)
modelId = optional_params.pop("model_id", None)
fake_stream = optional_params.pop("fake_stream", False)
json_mode = optional_params.get("json_mode", False)
if modelId is not None:
modelId = self.encode_model_id(model_id=modelId)
else:
modelId = model
if stream is True and "ai21" in modelId:
fake_stream = True
## CREDENTIALS ##
# pop aws_secret_access_key, aws_access_key_id, aws_region_name from kwargs, since completion calls fail with them
aws_secret_access_key = optional_params.pop("aws_secret_access_key", None)
aws_access_key_id = optional_params.pop("aws_access_key_id", None)
aws_session_token = optional_params.pop("aws_session_token", None)
aws_region_name = optional_params.pop("aws_region_name", None)
aws_role_name = optional_params.pop("aws_role_name", None)
aws_session_name = optional_params.pop("aws_session_name", None)
aws_profile_name = optional_params.pop("aws_profile_name", None)
aws_bedrock_runtime_endpoint = optional_params.pop(
"aws_bedrock_runtime_endpoint", None
) # https://bedrock-runtime.{region_name}.amazonaws.com
aws_web_identity_token = optional_params.pop("aws_web_identity_token", None)
aws_sts_endpoint = optional_params.pop("aws_sts_endpoint", None)
### SET REGION NAME ###
if aws_region_name is None:
# check env #
litellm_aws_region_name = get_secret("AWS_REGION_NAME", None)
if litellm_aws_region_name is not None and isinstance(
litellm_aws_region_name, str
):
aws_region_name = litellm_aws_region_name
standard_aws_region_name = get_secret("AWS_REGION", None)
if standard_aws_region_name is not None and isinstance(
standard_aws_region_name, str
):
aws_region_name = standard_aws_region_name
if aws_region_name is None:
aws_region_name = "us-west-2"
litellm_params["aws_region_name"] = (
aws_region_name # [DO NOT DELETE] important for async calls
)
credentials: Credentials = self.get_credentials(
aws_access_key_id=aws_access_key_id,
aws_secret_access_key=aws_secret_access_key,
aws_session_token=aws_session_token,
aws_region_name=aws_region_name,
aws_session_name=aws_session_name,
aws_profile_name=aws_profile_name,
aws_role_name=aws_role_name,
aws_web_identity_token=aws_web_identity_token,
aws_sts_endpoint=aws_sts_endpoint,
)
### SET RUNTIME ENDPOINT ###
endpoint_url, proxy_endpoint_url = self.get_runtime_endpoint(
api_base=api_base,
aws_bedrock_runtime_endpoint=aws_bedrock_runtime_endpoint,
aws_region_name=aws_region_name,
)
if (stream is not None and stream is True) and not fake_stream:
endpoint_url = f"{endpoint_url}/model/{modelId}/converse-stream"
proxy_endpoint_url = f"{proxy_endpoint_url}/model/{modelId}/converse-stream"
else:
endpoint_url = f"{endpoint_url}/model/{modelId}/converse"
proxy_endpoint_url = f"{proxy_endpoint_url}/model/{modelId}/converse"
## COMPLETION CALL
headers = {"Content-Type": "application/json"}
if extra_headers is not None:
headers = {"Content-Type": "application/json", **extra_headers}
### ROUTING (ASYNC, STREAMING, SYNC)
if acompletion:
if isinstance(client, HTTPHandler):
client = None
if stream is True:
return self.async_streaming(
model=model,
messages=messages,
api_base=proxy_endpoint_url,
model_response=model_response,
print_verbose=print_verbose,
encoding=encoding,
logging_obj=logging_obj,
optional_params=optional_params,
stream=True,
litellm_params=litellm_params,
logger_fn=logger_fn,
headers=headers,
timeout=timeout,
client=client,
json_mode=json_mode,
fake_stream=fake_stream,
credentials=credentials,
) # type: ignore
### ASYNC COMPLETION
return self.async_completion(
model=model,
messages=messages,
api_base=proxy_endpoint_url,
model_response=model_response,
print_verbose=print_verbose,
encoding=encoding,
logging_obj=logging_obj,
optional_params=optional_params,
stream=stream, # type: ignore
litellm_params=litellm_params,
logger_fn=logger_fn,
headers=headers,
timeout=timeout,
client=client,
credentials=credentials,
) # type: ignore
## TRANSFORMATION ##
_data = litellm.AmazonConverseConfig()._transform_request(
model=model,
messages=messages,
optional_params=optional_params,
litellm_params=litellm_params,
)
data = json.dumps(_data)
prepped = self.get_request_headers(
credentials=credentials,
aws_region_name=aws_region_name,
extra_headers=extra_headers,
endpoint_url=proxy_endpoint_url,
data=data,
headers=headers,
)
## LOGGING
logging_obj.pre_call(
input=messages,
api_key="",
additional_args={
"complete_input_dict": data,
"api_base": proxy_endpoint_url,
"headers": prepped.headers,
},
)
if client is None or isinstance(client, AsyncHTTPHandler):
_params = {}
if timeout is not None:
if isinstance(timeout, float) or isinstance(timeout, int):
timeout = httpx.Timeout(timeout)
_params["timeout"] = timeout
client = _get_httpx_client(_params) # type: ignore
else:
client = client
if stream is not None and stream is True:
completion_stream = make_sync_call(
client=(
client
if client is not None and isinstance(client, HTTPHandler)
else None
),
api_base=proxy_endpoint_url,
headers=prepped.headers, # type: ignore
data=data,
model=model,
messages=messages,
logging_obj=logging_obj,
json_mode=json_mode,
fake_stream=fake_stream,
)
streaming_response = CustomStreamWrapper(
completion_stream=completion_stream,
model=model,
custom_llm_provider="bedrock",
logging_obj=logging_obj,
)
return streaming_response
### COMPLETION
try:
response = client.post(
url=proxy_endpoint_url,
headers=prepped.headers,
data=data,
logging_obj=logging_obj,
) # type: ignore
response.raise_for_status()
except httpx.HTTPStatusError as err:
error_code = err.response.status_code
raise BedrockError(status_code=error_code, message=err.response.text)
except httpx.TimeoutException:
raise BedrockError(status_code=408, message="Timeout error occurred.")
return litellm.AmazonConverseConfig()._transform_response(
model=model,
response=response,
model_response=model_response,
stream=stream if isinstance(stream, bool) else False,
logging_obj=logging_obj,
api_key="",
data=data,
messages=messages,
print_verbose=print_verbose,
optional_params=optional_params,
encoding=encoding,
)
|