Merge branch 'main' into litellm_svc_logger

This commit is contained in:
Ishaan Jaff 2024-06-07 14:01:54 -07:00 committed by GitHub
commit 2cf3133669
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
84 changed files with 3848 additions and 5302 deletions

View file

@ -79,7 +79,7 @@ from .llms.anthropic import AnthropicChatCompletion
from .llms.anthropic_text import AnthropicTextCompletion
from .llms.huggingface_restapi import Huggingface
from .llms.predibase import PredibaseChatCompletion
from .llms.bedrock_httpx import BedrockLLM
from .llms.bedrock_httpx import BedrockLLM, BedrockConverseLLM
from .llms.vertex_httpx import VertexLLM
from .llms.triton import TritonChatCompletion
from .llms.prompt_templates.factory import (
@ -122,6 +122,7 @@ huggingface = Huggingface()
predibase_chat_completions = PredibaseChatCompletion()
triton_chat_completions = TritonChatCompletion()
bedrock_chat_completion = BedrockLLM()
bedrock_converse_chat_completion = BedrockConverseLLM()
vertex_chat_completion = VertexLLM()
####### COMPLETION ENDPOINTS ################
@ -364,7 +365,10 @@ async def acompletion(
) # sets the logging event loop if the user does sync streaming (e.g. on proxy for sagemaker calls)
return response
except Exception as e:
traceback.print_exc()
verbose_logger.error(
"litellm.acompletion(): Exception occured - {}".format(str(e))
)
verbose_logger.debug(traceback.format_exc())
custom_llm_provider = custom_llm_provider or "openai"
raise exception_type(
model=model,
@ -477,7 +481,10 @@ def mock_completion(
except Exception as e:
if isinstance(e, openai.APIError):
raise e
traceback.print_exc()
verbose_logger.error(
"litellm.mock_completion(): Exception occured - {}".format(str(e))
)
verbose_logger.debug(traceback.format_exc())
raise Exception("Mock completion response failed")
@ -2100,22 +2107,40 @@ def completion(
logging_obj=logging,
)
else:
response = bedrock_chat_completion.completion(
model=model,
messages=messages,
custom_prompt_dict=custom_prompt_dict,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
logging_obj=logging,
extra_headers=extra_headers,
timeout=timeout,
acompletion=acompletion,
client=client,
)
if model.startswith("anthropic"):
response = bedrock_converse_chat_completion.completion(
model=model,
messages=messages,
custom_prompt_dict=custom_prompt_dict,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
logging_obj=logging,
extra_headers=extra_headers,
timeout=timeout,
acompletion=acompletion,
client=client,
)
else:
response = bedrock_chat_completion.completion(
model=model,
messages=messages,
custom_prompt_dict=custom_prompt_dict,
model_response=model_response,
print_verbose=print_verbose,
optional_params=optional_params,
litellm_params=litellm_params,
logger_fn=logger_fn,
encoding=encoding,
logging_obj=logging,
extra_headers=extra_headers,
timeout=timeout,
acompletion=acompletion,
client=client,
)
if optional_params.get("stream", False):
## LOGGING
logging.post_call(
@ -4433,7 +4458,10 @@ async def ahealth_check(
response = {} # args like remaining ratelimit etc.
return response
except Exception as e:
traceback.print_exc()
verbose_logger.error(
"litellm.ahealth_check(): Exception occured - {}".format(str(e))
)
verbose_logger.debug(traceback.format_exc())
stack_trace = traceback.format_exc()
if isinstance(stack_trace, str):
stack_trace = stack_trace[:1000]