mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 18:54:30 +00:00
Litellm ruff linting enforcement (#5992)
* ci(config.yml): add a 'check_code_quality' step Addresses https://github.com/BerriAI/litellm/issues/5991 * ci(config.yml): check why circle ci doesn't pick up this test * ci(config.yml): fix to run 'check_code_quality' tests * fix(__init__.py): fix unprotected import * fix(__init__.py): don't remove unused imports * build(ruff.toml): update ruff.toml to ignore unused imports * fix: fix: ruff + pyright - fix linting + type-checking errors * fix: fix linting errors * fix(lago.py): fix module init error * fix: fix linting errors * ci(config.yml): cd into correct dir for checks * fix(proxy_server.py): fix linting error * fix(utils.py): fix bare except causes ruff linting errors * fix: ruff - fix remaining linting errors * fix(clickhouse.py): use standard logging object * fix(__init__.py): fix unprotected import * fix: ruff - fix linting errors * fix: fix linting errors * ci(config.yml): cleanup code qa step (formatting handled in local_testing) * fix(_health_endpoints.py): fix ruff linting errors * ci(config.yml): just use ruff in check_code_quality pipeline for now * build(custom_guardrail.py): include missing file * style(embedding_handler.py): fix ruff check
This commit is contained in:
Krish Dholakia
GitHub
parent
3fc4ae0d65
commit
d57be47b0f
263 changed files with 1687 additions and 3320 deletions
134
litellm/main.py
134
litellm/main.py
|
|
@ -106,6 +106,7 @@ from .llms.prompt_templates.factory import (
|
|||
custom_prompt,
|
||||
function_call_prompt,
|
||||
map_system_message_pt,
|
||||
ollama_pt,
|
||||
prompt_factory,
|
||||
stringify_json_tool_call_content,
|
||||
)
|
||||
|
|
@ -150,7 +151,6 @@ from .types.utils import (
|
|||
encoding = tiktoken.get_encoding("cl100k_base")
|
||||
from litellm.utils import (
|
||||
Choices,
|
||||
CustomStreamWrapper,
|
||||
EmbeddingResponse,
|
||||
ImageResponse,
|
||||
Message,
|
||||
|
|
@ -159,8 +159,6 @@ from litellm.utils import (
|
|||
TextCompletionResponse,
|
||||
TextCompletionStreamWrapper,
|
||||
TranscriptionResponse,
|
||||
get_secret,
|
||||
read_config_args,
|
||||
)
|
||||
|
||||
####### ENVIRONMENT VARIABLES ###################
|
||||
|
|
@ -214,7 +212,7 @@ class LiteLLM:
|
|||
class Chat:
|
||||
def __init__(self, params, router_obj: Optional[Any]):
|
||||
self.params = params
|
||||
if self.params.get("acompletion", False) == True:
|
||||
if self.params.get("acompletion", False) is True:
|
||||
self.params.pop("acompletion")
|
||||
self.completions: Union[AsyncCompletions, Completions] = AsyncCompletions(
|
||||
self.params, router_obj=router_obj
|
||||
|
|
@ -837,10 +835,10 @@ def completion(
|
|||
model_response = ModelResponse()
|
||||
setattr(model_response, "usage", litellm.Usage())
|
||||
if (
|
||||
kwargs.get("azure", False) == True
|
||||
kwargs.get("azure", False) is True
|
||||
): # don't remove flag check, to remain backwards compatible for repos like Codium
|
||||
custom_llm_provider = "azure"
|
||||
if deployment_id != None: # azure llms
|
||||
if deployment_id is not None: # azure llms
|
||||
model = deployment_id
|
||||
custom_llm_provider = "azure"
|
||||
model, custom_llm_provider, dynamic_api_key, api_base = get_llm_provider(
|
||||
|
|
@ -1156,7 +1154,7 @@ def completion(
|
|||
client=client, # pass AsyncAzureOpenAI, AzureOpenAI client
|
||||
)
|
||||
|
||||
if optional_params.get("stream", False) or acompletion == True:
|
||||
if optional_params.get("stream", False) or acompletion is True:
|
||||
## LOGGING
|
||||
logging.post_call(
|
||||
input=messages,
|
||||
|
|
@ -1278,7 +1276,7 @@ def completion(
|
|||
if (
|
||||
len(messages) > 0
|
||||
and "content" in messages[0]
|
||||
and type(messages[0]["content"]) == list
|
||||
and isinstance(messages[0]["content"], list)
|
||||
):
|
||||
# text-davinci-003 can accept a string or array, if it's an array, assume the array is set in messages[0]['content']
|
||||
# https://platform.openai.com/docs/api-reference/completions/create
|
||||
|
|
@ -1304,16 +1302,16 @@ def completion(
|
|||
)
|
||||
|
||||
if (
|
||||
optional_params.get("stream", False) == False
|
||||
and acompletion == False
|
||||
and text_completion == False
|
||||
optional_params.get("stream", False) is False
|
||||
and acompletion is False
|
||||
and text_completion is False
|
||||
):
|
||||
# convert to chat completion response
|
||||
_response = litellm.OpenAITextCompletionConfig().convert_to_chat_model_response_object(
|
||||
response_object=_response, model_response_object=model_response
|
||||
)
|
||||
|
||||
if optional_params.get("stream", False) or acompletion == True:
|
||||
if optional_params.get("stream", False) or acompletion is True:
|
||||
## LOGGING
|
||||
logging.post_call(
|
||||
input=messages,
|
||||
|
|
@ -1519,7 +1517,7 @@ def completion(
|
|||
acompletion=acompletion,
|
||||
)
|
||||
|
||||
if optional_params.get("stream", False) == True:
|
||||
if optional_params.get("stream", False) is True:
|
||||
## LOGGING
|
||||
logging.post_call(
|
||||
input=messages,
|
||||
|
|
@ -1566,7 +1564,7 @@ def completion(
|
|||
custom_prompt_dict=custom_prompt_dict,
|
||||
)
|
||||
|
||||
if "stream" in optional_params and optional_params["stream"] == True:
|
||||
if "stream" in optional_params and optional_params["stream"] is True:
|
||||
# don't try to access stream object,
|
||||
## LOGGING
|
||||
logging.post_call(
|
||||
|
|
@ -1575,7 +1573,7 @@ def completion(
|
|||
original_response=model_response,
|
||||
)
|
||||
|
||||
if optional_params.get("stream", False) or acompletion == True:
|
||||
if optional_params.get("stream", False) or acompletion is True:
|
||||
## LOGGING
|
||||
logging.post_call(
|
||||
input=messages,
|
||||
|
|
@ -1654,7 +1652,7 @@ def completion(
|
|||
timeout=timeout,
|
||||
client=client,
|
||||
)
|
||||
if optional_params.get("stream", False) or acompletion == True:
|
||||
if optional_params.get("stream", False) or acompletion is True:
|
||||
## LOGGING
|
||||
logging.post_call(
|
||||
input=messages,
|
||||
|
|
@ -1691,7 +1689,7 @@ def completion(
|
|||
logging_obj=logging,
|
||||
)
|
||||
|
||||
if "stream" in optional_params and optional_params["stream"] == True:
|
||||
if "stream" in optional_params and optional_params["stream"] is True:
|
||||
# don't try to access stream object,
|
||||
response = CustomStreamWrapper(
|
||||
response,
|
||||
|
|
@ -1700,7 +1698,7 @@ def completion(
|
|||
logging_obj=logging,
|
||||
)
|
||||
|
||||
if optional_params.get("stream", False) or acompletion == True:
|
||||
if optional_params.get("stream", False) or acompletion is True:
|
||||
## LOGGING
|
||||
logging.post_call(
|
||||
input=messages,
|
||||
|
|
@ -1740,7 +1738,7 @@ def completion(
|
|||
logging_obj=logging, # model call logging done inside the class as we make need to modify I/O to fit aleph alpha's requirements
|
||||
)
|
||||
|
||||
if "stream" in optional_params and optional_params["stream"] == True:
|
||||
if "stream" in optional_params and optional_params["stream"] is True:
|
||||
# don't try to access stream object,
|
||||
response = CustomStreamWrapper(
|
||||
model_response,
|
||||
|
|
@ -1788,7 +1786,7 @@ def completion(
|
|||
logging_obj=logging, # model call logging done inside the class as we make need to modify I/O to fit aleph alpha's requirements
|
||||
)
|
||||
|
||||
if "stream" in optional_params and optional_params["stream"] == True:
|
||||
if "stream" in optional_params and optional_params["stream"] is True:
|
||||
# don't try to access stream object,
|
||||
response = CustomStreamWrapper(
|
||||
model_response,
|
||||
|
|
@ -1836,7 +1834,7 @@ def completion(
|
|||
logging_obj=logging, # model call logging done inside the class as we make need to modify I/O to fit aleph alpha's requirements
|
||||
)
|
||||
|
||||
if "stream" in optional_params and optional_params["stream"] == True:
|
||||
if "stream" in optional_params and optional_params["stream"] is True:
|
||||
# don't try to access stream object,
|
||||
response = CustomStreamWrapper(
|
||||
model_response,
|
||||
|
|
@ -1875,7 +1873,7 @@ def completion(
|
|||
logging_obj=logging,
|
||||
)
|
||||
|
||||
if "stream" in optional_params and optional_params["stream"] == True:
|
||||
if "stream" in optional_params and optional_params["stream"] is True:
|
||||
# don't try to access stream object,
|
||||
response = CustomStreamWrapper(
|
||||
model_response,
|
||||
|
|
@ -1916,7 +1914,7 @@ def completion(
|
|||
)
|
||||
if (
|
||||
"stream" in optional_params
|
||||
and optional_params["stream"] == True
|
||||
and optional_params["stream"] is True
|
||||
and acompletion is False
|
||||
):
|
||||
# don't try to access stream object,
|
||||
|
|
@ -1943,7 +1941,7 @@ def completion(
|
|||
encoding=encoding,
|
||||
logging_obj=logging,
|
||||
)
|
||||
if "stream" in optional_params and optional_params["stream"] == True:
|
||||
if "stream" in optional_params and optional_params["stream"] is True:
|
||||
# don't try to access stream object,
|
||||
response = CustomStreamWrapper(
|
||||
model_response,
|
||||
|
|
@ -2095,7 +2093,7 @@ def completion(
|
|||
logging_obj=logging,
|
||||
)
|
||||
# fake palm streaming
|
||||
if "stream" in optional_params and optional_params["stream"] == True:
|
||||
if "stream" in optional_params and optional_params["stream"] is True:
|
||||
# fake streaming for palm
|
||||
resp_string = model_response["choices"][0]["message"]["content"]
|
||||
response = CustomStreamWrapper(
|
||||
|
|
@ -2390,7 +2388,7 @@ def completion(
|
|||
logging_obj=logging,
|
||||
)
|
||||
|
||||
if "stream" in optional_params and optional_params["stream"] == True:
|
||||
if "stream" in optional_params and optional_params["stream"] is True:
|
||||
# don't try to access stream object,
|
||||
response = CustomStreamWrapper(
|
||||
model_response,
|
||||
|
|
@ -2527,7 +2525,7 @@ def completion(
|
|||
)
|
||||
if (
|
||||
"stream" in optional_params
|
||||
and optional_params["stream"] == True
|
||||
and optional_params["stream"] is True
|
||||
and not isinstance(response, CustomStreamWrapper)
|
||||
):
|
||||
# don't try to access stream object,
|
||||
|
|
@ -2563,7 +2561,7 @@ def completion(
|
|||
)
|
||||
|
||||
if (
|
||||
"stream" in optional_params and optional_params["stream"] == True
|
||||
"stream" in optional_params and optional_params["stream"] is True
|
||||
): ## [BETA]
|
||||
# don't try to access stream object,
|
||||
response = CustomStreamWrapper(
|
||||
|
|
@ -2587,38 +2585,38 @@ def completion(
|
|||
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(
|
||||
ollama_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,
|
||||
custom_llm_provider=custom_llm_provider,
|
||||
)
|
||||
if isinstance(prompt, dict):
|
||||
modified_prompt = ollama_pt(model=model, messages=messages)
|
||||
if isinstance(modified_prompt, dict):
|
||||
# for multimode models - ollama/llava prompt_factory returns a dict {
|
||||
# "prompt": prompt,
|
||||
# "images": images
|
||||
# }
|
||||
prompt, images = prompt["prompt"], prompt["images"]
|
||||
ollama_prompt, images = (
|
||||
modified_prompt["prompt"],
|
||||
modified_prompt["images"],
|
||||
)
|
||||
optional_params["images"] = images
|
||||
|
||||
else:
|
||||
ollama_prompt = modified_prompt
|
||||
## LOGGING
|
||||
generator = ollama.get_ollama_response(
|
||||
api_base=api_base,
|
||||
model=model,
|
||||
prompt=prompt,
|
||||
prompt=ollama_prompt,
|
||||
optional_params=optional_params,
|
||||
logging_obj=logging,
|
||||
acompletion=acompletion,
|
||||
model_response=model_response,
|
||||
encoding=encoding,
|
||||
)
|
||||
if acompletion is True or optional_params.get("stream", False) == True:
|
||||
if acompletion is True or optional_params.get("stream", False) is True:
|
||||
return generator
|
||||
|
||||
response = generator
|
||||
|
|
@ -2701,7 +2699,7 @@ def completion(
|
|||
api_key=api_key,
|
||||
logging_obj=logging,
|
||||
)
|
||||
if "stream" in optional_params and optional_params["stream"] == True:
|
||||
if "stream" in optional_params and optional_params["stream"] is True:
|
||||
# don't try to access stream object,
|
||||
response = CustomStreamWrapper(
|
||||
response,
|
||||
|
|
@ -2710,7 +2708,7 @@ def completion(
|
|||
logging_obj=logging,
|
||||
)
|
||||
|
||||
if optional_params.get("stream", False) or acompletion == True:
|
||||
if optional_params.get("stream", False) or acompletion is True:
|
||||
## LOGGING
|
||||
logging.post_call(
|
||||
input=messages,
|
||||
|
|
@ -2743,7 +2741,7 @@ def completion(
|
|||
logging_obj=logging,
|
||||
)
|
||||
if inspect.isgenerator(model_response) or (
|
||||
"stream" in optional_params and optional_params["stream"] == True
|
||||
"stream" in optional_params and optional_params["stream"] is True
|
||||
):
|
||||
# don't try to access stream object,
|
||||
response = CustomStreamWrapper(
|
||||
|
|
@ -2771,7 +2769,7 @@ def completion(
|
|||
encoding=encoding,
|
||||
logging_obj=logging,
|
||||
)
|
||||
if stream == True: ## [BETA]
|
||||
if stream is True: ## [BETA]
|
||||
# Fake streaming for petals
|
||||
resp_string = model_response["choices"][0]["message"]["content"]
|
||||
response = CustomStreamWrapper(
|
||||
|
|
@ -2786,7 +2784,7 @@ def completion(
|
|||
import requests
|
||||
|
||||
url = litellm.api_base or api_base or ""
|
||||
if url == None or url == "":
|
||||
if url is None or url == "":
|
||||
raise ValueError(
|
||||
"api_base not set. Set api_base or litellm.api_base for custom endpoints"
|
||||
)
|
||||
|
|
@ -3145,10 +3143,10 @@ def batch_completion_models(*args, **kwargs):
|
|||
try:
|
||||
result = future.result()
|
||||
return result
|
||||
except Exception as e:
|
||||
except Exception:
|
||||
# if model 1 fails, continue with response from model 2, model3
|
||||
print_verbose(
|
||||
f"\n\ngot an exception, ignoring, removing from futures"
|
||||
"\n\ngot an exception, ignoring, removing from futures"
|
||||
)
|
||||
print_verbose(futures)
|
||||
new_futures = {}
|
||||
|
|
@ -3189,9 +3187,6 @@ def batch_completion_models_all_responses(*args, **kwargs):
|
|||
import concurrent.futures
|
||||
|
||||
# ANSI escape codes for colored output
|
||||
GREEN = "\033[92m"
|
||||
RED = "\033[91m"
|
||||
RESET = "\033[0m"
|
||||
|
||||
if "model" in kwargs:
|
||||
kwargs.pop("model")
|
||||
|
|
@ -3520,7 +3515,7 @@ def embedding(
|
|||
|
||||
if api_base is None:
|
||||
raise ValueError(
|
||||
f"No API Base provided for Azure OpenAI LLM provider. Set 'AZURE_API_BASE' in .env"
|
||||
"No API Base provided for Azure OpenAI LLM provider. Set 'AZURE_API_BASE' in .env"
|
||||
)
|
||||
|
||||
## EMBEDDING CALL
|
||||
|
|
@ -4106,7 +4101,6 @@ def text_completion(
|
|||
*args,
|
||||
**kwargs,
|
||||
):
|
||||
global print_verbose
|
||||
import copy
|
||||
|
||||
"""
|
||||
|
|
@ -4136,7 +4130,7 @@ def text_completion(
|
|||
Your example of how to use this function goes here.
|
||||
"""
|
||||
if "engine" in kwargs:
|
||||
if model == None:
|
||||
if model is None:
|
||||
# only use engine when model not passed
|
||||
model = kwargs["engine"]
|
||||
kwargs.pop("engine")
|
||||
|
|
@ -4189,18 +4183,18 @@ def text_completion(
|
|||
|
||||
if custom_llm_provider == "huggingface":
|
||||
# if echo == True, for TGI llms we need to set top_n_tokens to 3
|
||||
if echo == True:
|
||||
if echo is True:
|
||||
# for tgi llms
|
||||
if "top_n_tokens" not in kwargs:
|
||||
kwargs["top_n_tokens"] = 3
|
||||
|
||||
# processing prompt - users can pass raw tokens to OpenAI Completion()
|
||||
if type(prompt) == list:
|
||||
if isinstance(prompt, list):
|
||||
import concurrent.futures
|
||||
|
||||
tokenizer = tiktoken.encoding_for_model("text-davinci-003")
|
||||
## if it's a 2d list - each element in the list is a text_completion() request
|
||||
if len(prompt) > 0 and type(prompt[0]) == list:
|
||||
if len(prompt) > 0 and isinstance(prompt[0], list):
|
||||
responses = [None for x in prompt] # init responses
|
||||
|
||||
def process_prompt(i, individual_prompt):
|
||||
|
|
@ -4299,7 +4293,7 @@ def text_completion(
|
|||
raw_response = response._hidden_params.get("original_response", None)
|
||||
transformed_logprobs = litellm.utils.transform_logprobs(raw_response)
|
||||
except Exception as e:
|
||||
print_verbose(f"LiteLLM non blocking exception: {e}")
|
||||
verbose_logger.exception(f"LiteLLM non blocking exception: {e}")
|
||||
|
||||
if isinstance(response, TextCompletionResponse):
|
||||
return response
|
||||
|
|
@ -4813,12 +4807,12 @@ def transcription(
|
|||
Allows router to load balance between them
|
||||
"""
|
||||
atranscription = kwargs.get("atranscription", False)
|
||||
litellm_call_id = kwargs.get("litellm_call_id", None)
|
||||
logger_fn = kwargs.get("logger_fn", None)
|
||||
proxy_server_request = kwargs.get("proxy_server_request", None)
|
||||
model_info = kwargs.get("model_info", None)
|
||||
metadata = kwargs.get("metadata", {})
|
||||
tags = kwargs.pop("tags", [])
|
||||
kwargs.get("litellm_call_id", None)
|
||||
kwargs.get("logger_fn", None)
|
||||
kwargs.get("proxy_server_request", None)
|
||||
kwargs.get("model_info", None)
|
||||
kwargs.get("metadata", {})
|
||||
kwargs.pop("tags", [])
|
||||
|
||||
drop_params = kwargs.get("drop_params", None)
|
||||
client: Optional[
|
||||
|
|
@ -4996,7 +4990,7 @@ def speech(
|
|||
model_info = kwargs.get("model_info", None)
|
||||
metadata = kwargs.get("metadata", {})
|
||||
model, custom_llm_provider, dynamic_api_key, api_base = get_llm_provider(model=model, custom_llm_provider=custom_llm_provider, api_base=api_base) # type: ignore
|
||||
tags = kwargs.pop("tags", [])
|
||||
kwargs.pop("tags", [])
|
||||
|
||||
optional_params = {}
|
||||
if response_format is not None:
|
||||
|
|
@ -5345,12 +5339,12 @@ def print_verbose(print_statement):
|
|||
verbose_logger.debug(print_statement)
|
||||
if litellm.set_verbose:
|
||||
print(print_statement) # noqa
|
||||
except:
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
|
||||
def config_completion(**kwargs):
|
||||
if litellm.config_path != None:
|
||||
if litellm.config_path is not None:
|
||||
config_args = read_config_args(litellm.config_path)
|
||||
# overwrite any args passed in with config args
|
||||
return completion(**kwargs, **config_args)
|
||||
|
|
@ -5408,16 +5402,18 @@ def stream_chunk_builder_text_completion(chunks: list, messages: Optional[List]
|
|||
response["choices"][0]["text"] = combined_content
|
||||
|
||||
if len(combined_content) > 0:
|
||||
completion_output = combined_content
|
||||
pass
|
||||
else:
|
||||
completion_output = ""
|
||||
pass
|
||||
# # Update usage information if needed
|
||||
try:
|
||||
response["usage"]["prompt_tokens"] = token_counter(
|
||||
model=model, messages=messages
|
||||
)
|
||||
except: # don't allow this failing to block a complete streaming response from being returned
|
||||
print_verbose(f"token_counter failed, assuming prompt tokens is 0")
|
||||
except (
|
||||
Exception
|
||||
): # don't allow this failing to block a complete streaming response from being returned
|
||||
print_verbose("token_counter failed, assuming prompt tokens is 0")
|
||||
response["usage"]["prompt_tokens"] = 0
|
||||
response["usage"]["completion_tokens"] = token_counter(
|
||||
model=model,
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue