mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 18:54:30 +00:00
refactor: add black formatting
This commit is contained in:
Krrish Dholakia
parent
b87d630b0a
commit
4905929de3
156 changed files with 19723 additions and 10869 deletions
|
|
@ -7,6 +7,7 @@ from typing import Callable, Optional
|
|||
import litellm
|
||||
from litellm.utils import ModelResponse, Usage
|
||||
|
||||
|
||||
class NLPCloudError(Exception):
|
||||
def __init__(self, status_code, message):
|
||||
self.status_code = status_code
|
||||
|
|
@ -15,7 +16,8 @@ class NLPCloudError(Exception):
|
|||
self.message
|
||||
) # Call the base class constructor with the parameters it needs
|
||||
|
||||
class NLPCloudConfig():
|
||||
|
||||
class NLPCloudConfig:
|
||||
"""
|
||||
Reference: https://docs.nlpcloud.com/#generation
|
||||
|
||||
|
|
@ -43,45 +45,57 @@ class NLPCloudConfig():
|
|||
|
||||
- `num_return_sequences` (int): Optional. The number of independently computed returned sequences.
|
||||
"""
|
||||
max_length: Optional[int]=None
|
||||
length_no_input: Optional[bool]=None
|
||||
end_sequence: Optional[str]=None
|
||||
remove_end_sequence: Optional[bool]=None
|
||||
remove_input: Optional[bool]=None
|
||||
bad_words: Optional[list]=None
|
||||
temperature: Optional[float]=None
|
||||
top_p: Optional[float]=None
|
||||
top_k: Optional[int]=None
|
||||
repetition_penalty: Optional[float]=None
|
||||
num_beams: Optional[int]=None
|
||||
num_return_sequences: Optional[int]=None
|
||||
|
||||
max_length: Optional[int] = None
|
||||
length_no_input: Optional[bool] = None
|
||||
end_sequence: Optional[str] = None
|
||||
remove_end_sequence: Optional[bool] = None
|
||||
remove_input: Optional[bool] = None
|
||||
bad_words: Optional[list] = None
|
||||
temperature: Optional[float] = None
|
||||
top_p: Optional[float] = None
|
||||
top_k: Optional[int] = None
|
||||
repetition_penalty: Optional[float] = None
|
||||
num_beams: Optional[int] = None
|
||||
num_return_sequences: Optional[int] = None
|
||||
|
||||
def __init__(self,
|
||||
max_length: Optional[int]=None,
|
||||
length_no_input: Optional[bool]=None,
|
||||
end_sequence: Optional[str]=None,
|
||||
remove_end_sequence: Optional[bool]=None,
|
||||
remove_input: Optional[bool]=None,
|
||||
bad_words: Optional[list]=None,
|
||||
temperature: Optional[float]=None,
|
||||
top_p: Optional[float]=None,
|
||||
top_k: Optional[int]=None,
|
||||
repetition_penalty: Optional[float]=None,
|
||||
num_beams: Optional[int]=None,
|
||||
num_return_sequences: Optional[int]=None) -> None:
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
max_length: Optional[int] = None,
|
||||
length_no_input: Optional[bool] = None,
|
||||
end_sequence: Optional[str] = None,
|
||||
remove_end_sequence: Optional[bool] = None,
|
||||
remove_input: Optional[bool] = None,
|
||||
bad_words: Optional[list] = None,
|
||||
temperature: Optional[float] = None,
|
||||
top_p: Optional[float] = None,
|
||||
top_k: Optional[int] = None,
|
||||
repetition_penalty: Optional[float] = None,
|
||||
num_beams: Optional[int] = None,
|
||||
num_return_sequences: Optional[int] = None,
|
||||
) -> None:
|
||||
locals_ = locals()
|
||||
for key, value in locals_.items():
|
||||
if key != 'self' and value is not None:
|
||||
if key != "self" and value is not None:
|
||||
setattr(self.__class__, key, value)
|
||||
|
||||
|
||||
@classmethod
|
||||
def get_config(cls):
|
||||
return {k: v for k, v in cls.__dict__.items()
|
||||
if not k.startswith('__')
|
||||
and not isinstance(v, (types.FunctionType, types.BuiltinFunctionType, classmethod, staticmethod))
|
||||
and v is not None}
|
||||
return {
|
||||
k: v
|
||||
for k, v in cls.__dict__.items()
|
||||
if not k.startswith("__")
|
||||
and not isinstance(
|
||||
v,
|
||||
(
|
||||
types.FunctionType,
|
||||
types.BuiltinFunctionType,
|
||||
classmethod,
|
||||
staticmethod,
|
||||
),
|
||||
)
|
||||
and v is not None
|
||||
}
|
||||
|
||||
|
||||
def validate_environment(api_key):
|
||||
|
|
@ -93,6 +107,7 @@ def validate_environment(api_key):
|
|||
headers["Authorization"] = f"Token {api_key}"
|
||||
return headers
|
||||
|
||||
|
||||
def completion(
|
||||
model: str,
|
||||
messages: list,
|
||||
|
|
@ -110,9 +125,11 @@ def completion(
|
|||
headers = validate_environment(api_key)
|
||||
|
||||
## Load Config
|
||||
config = litellm.NLPCloudConfig.get_config()
|
||||
for k, v in config.items():
|
||||
if k not in optional_params: # completion(top_k=3) > togetherai_config(top_k=3) <- allows for dynamic variables to be passed in
|
||||
config = litellm.NLPCloudConfig.get_config()
|
||||
for k, v in config.items():
|
||||
if (
|
||||
k not in optional_params
|
||||
): # completion(top_k=3) > togetherai_config(top_k=3) <- allows for dynamic variables to be passed in
|
||||
optional_params[k] = v
|
||||
|
||||
completion_url_fragment_1 = api_base
|
||||
|
|
@ -129,24 +146,31 @@ def completion(
|
|||
|
||||
## LOGGING
|
||||
logging_obj.pre_call(
|
||||
input=text,
|
||||
api_key=api_key,
|
||||
additional_args={"complete_input_dict": data, "headers": headers, "api_base": completion_url},
|
||||
)
|
||||
input=text,
|
||||
api_key=api_key,
|
||||
additional_args={
|
||||
"complete_input_dict": data,
|
||||
"headers": headers,
|
||||
"api_base": completion_url,
|
||||
},
|
||||
)
|
||||
## COMPLETION CALL
|
||||
response = requests.post(
|
||||
completion_url, headers=headers, data=json.dumps(data), stream=optional_params["stream"] if "stream" in optional_params else False
|
||||
completion_url,
|
||||
headers=headers,
|
||||
data=json.dumps(data),
|
||||
stream=optional_params["stream"] if "stream" in optional_params else False,
|
||||
)
|
||||
if "stream" in optional_params and optional_params["stream"] == True:
|
||||
return clean_and_iterate_chunks(response)
|
||||
else:
|
||||
## LOGGING
|
||||
logging_obj.post_call(
|
||||
input=text,
|
||||
api_key=api_key,
|
||||
original_response=response.text,
|
||||
additional_args={"complete_input_dict": data},
|
||||
)
|
||||
input=text,
|
||||
api_key=api_key,
|
||||
original_response=response.text,
|
||||
additional_args={"complete_input_dict": data},
|
||||
)
|
||||
print_verbose(f"raw model_response: {response.text}")
|
||||
## RESPONSE OBJECT
|
||||
try:
|
||||
|
|
@ -161,11 +185,16 @@ def completion(
|
|||
else:
|
||||
try:
|
||||
if len(completion_response["generated_text"]) > 0:
|
||||
model_response["choices"][0]["message"]["content"] = completion_response["generated_text"]
|
||||
model_response["choices"][0]["message"][
|
||||
"content"
|
||||
] = completion_response["generated_text"]
|
||||
except:
|
||||
raise NLPCloudError(message=json.dumps(completion_response), status_code=response.status_code)
|
||||
raise NLPCloudError(
|
||||
message=json.dumps(completion_response),
|
||||
status_code=response.status_code,
|
||||
)
|
||||
|
||||
## CALCULATING USAGE - baseten charges on time, not tokens - have some mapping of cost here.
|
||||
## CALCULATING USAGE - baseten charges on time, not tokens - have some mapping of cost here.
|
||||
prompt_tokens = completion_response["nb_input_tokens"]
|
||||
completion_tokens = completion_response["nb_generated_tokens"]
|
||||
|
||||
|
|
@ -174,7 +203,7 @@ def completion(
|
|||
usage = Usage(
|
||||
prompt_tokens=prompt_tokens,
|
||||
completion_tokens=completion_tokens,
|
||||
total_tokens=prompt_tokens + completion_tokens
|
||||
total_tokens=prompt_tokens + completion_tokens,
|
||||
)
|
||||
model_response.usage = usage
|
||||
return model_response
|
||||
|
|
@ -187,25 +216,27 @@ def completion(
|
|||
# # Perform further processing based on your needs
|
||||
# return cleaned_chunk
|
||||
|
||||
|
||||
# for line in response.iter_lines():
|
||||
# if line:
|
||||
# yield process_chunk(line)
|
||||
def clean_and_iterate_chunks(response):
|
||||
buffer = b''
|
||||
buffer = b""
|
||||
|
||||
for chunk in response.iter_content(chunk_size=1024):
|
||||
if not chunk:
|
||||
break
|
||||
|
||||
buffer += chunk
|
||||
while b'\x00' in buffer:
|
||||
buffer = buffer.replace(b'\x00', b'')
|
||||
yield buffer.decode('utf-8')
|
||||
buffer = b''
|
||||
while b"\x00" in buffer:
|
||||
buffer = buffer.replace(b"\x00", b"")
|
||||
yield buffer.decode("utf-8")
|
||||
buffer = b""
|
||||
|
||||
# No more data expected, yield any remaining data in the buffer
|
||||
if buffer:
|
||||
yield buffer.decode('utf-8')
|
||||
yield buffer.decode("utf-8")
|
||||
|
||||
|
||||
def embedding():
|
||||
# logic for parsing in - calling - parsing out model embedding calls
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue