forked from phoenix/litellm-mirror
docs(completion-docs): adds more details on provider-specific params
This commit is contained in:
Krrish Dholakia
parent
aa615fea4f
commit
d69038883c
8 changed files with 749 additions and 35 deletions
184
litellm/llms/openai.py
Normal file
184
litellm/llms/openai.py
Normal file
|
|
@ -0,0 +1,184 @@
|
|||
from typing import Optional, Union
|
||||
import types
|
||||
|
||||
# This file just has the openai config classes.
|
||||
# For implementation check out completion() in main.py
|
||||
|
||||
class OpenAIConfig():
|
||||
"""
|
||||
Reference: https://platform.openai.com/docs/api-reference/chat/create
|
||||
|
||||
The class `OpenAIConfig` provides configuration for the OpenAI's Chat API interface. Below are the parameters:
|
||||
|
||||
- `frequency_penalty` (number or null): Defaults to 0. Allows a value between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, thereby minimizing repetition.
|
||||
|
||||
- `function_call` (string or object): This optional parameter controls how the model calls functions.
|
||||
|
||||
- `functions` (array): An optional parameter. It is a list of functions for which the model may generate JSON inputs.
|
||||
|
||||
- `logit_bias` (map): This optional parameter modifies the likelihood of specified tokens appearing in the completion.
|
||||
|
||||
- `max_tokens` (integer or null): This optional parameter helps to set the maximum number of tokens to generate in the chat completion.
|
||||
|
||||
- `n` (integer or null): This optional parameter helps to set how many chat completion choices to generate for each input message.
|
||||
|
||||
- `presence_penalty` (number or null): Defaults to 0. It penalizes new tokens based on if they appear in the text so far, hence increasing the model's likelihood to talk about new topics.
|
||||
|
||||
- `stop` (string / array / null): Specifies up to 4 sequences where the API will stop generating further tokens.
|
||||
|
||||
- `temperature` (number or null): Defines the sampling temperature to use, varying between 0 and 2.
|
||||
|
||||
- `top_p` (number or null): An alternative to sampling with temperature, used for nucleus sampling.
|
||||
"""
|
||||
frequency_penalty: Optional[int]=None
|
||||
function_call: Optional[Union[str, dict]]=None
|
||||
functions: Optional[list]=None
|
||||
logit_bias: Optional[dict]=None
|
||||
max_tokens: Optional[int]=None
|
||||
n: Optional[int]=None
|
||||
presence_penalty: Optional[int]=None
|
||||
stop: Optional[Union[str, list]]=None
|
||||
temperature: Optional[int]=None
|
||||
top_p: Optional[int]=None
|
||||
|
||||
def __init__(self,
|
||||
frequency_penalty: Optional[int]=None,
|
||||
function_call: Optional[Union[str, dict]]=None,
|
||||
functions: Optional[list]=None,
|
||||
logit_bias: Optional[dict]=None,
|
||||
max_tokens: Optional[int]=None,
|
||||
n: Optional[int]=None,
|
||||
presence_penalty: Optional[int]=None,
|
||||
stop: Optional[Union[str, list]]=None,
|
||||
temperature: Optional[int]=None,
|
||||
top_p: Optional[int]=None,) -> None:
|
||||
|
||||
locals_ = locals()
|
||||
for key, value in locals_.items():
|
||||
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}
|
||||
|
||||
class OpenAITextCompletionConfig():
|
||||
"""
|
||||
Reference: https://platform.openai.com/docs/api-reference/completions/create
|
||||
|
||||
The class `OpenAITextCompletionConfig` provides configuration for the OpenAI's text completion API interface. Below are the parameters:
|
||||
|
||||
- `best_of` (integer or null): This optional parameter generates server-side completions and returns the one with the highest log probability per token.
|
||||
|
||||
- `echo` (boolean or null): This optional parameter will echo back the prompt in addition to the completion.
|
||||
|
||||
- `frequency_penalty` (number or null): Defaults to 0. It is a numbers from -2.0 to 2.0, where positive values decrease the model's likelihood to repeat the same line.
|
||||
|
||||
- `logit_bias` (map): This optional parameter modifies the likelihood of specified tokens appearing in the completion.
|
||||
|
||||
- `logprobs` (integer or null): This optional parameter includes the log probabilities on the most likely tokens as well as the chosen tokens.
|
||||
|
||||
- `max_tokens` (integer or null): This optional parameter sets the maximum number of tokens to generate in the completion.
|
||||
|
||||
- `n` (integer or null): This optional parameter sets how many completions to generate for each prompt.
|
||||
|
||||
- `presence_penalty` (number or null): Defaults to 0 and can be between -2.0 and 2.0. Positive values increase the model's likelihood to talk about new topics.
|
||||
|
||||
- `stop` (string / array / null): Specifies up to 4 sequences where the API will stop generating further tokens.
|
||||
|
||||
- `suffix` (string or null): Defines the suffix that comes after a completion of inserted text.
|
||||
|
||||
- `temperature` (number or null): This optional parameter defines the sampling temperature to use.
|
||||
|
||||
- `top_p` (number or null): An alternative to sampling with temperature, used for nucleus sampling.
|
||||
"""
|
||||
best_of: Optional[int]=None
|
||||
echo: Optional[bool]=None
|
||||
frequency_penalty: Optional[int]=None
|
||||
logit_bias: Optional[dict]=None
|
||||
logprobs: Optional[int]=None
|
||||
max_tokens: Optional[int]=None
|
||||
n: Optional[int]=None
|
||||
presence_penalty: Optional[int]=None
|
||||
stop: Optional[Union[str, list]]=None
|
||||
suffix: Optional[str]=None
|
||||
temperature: Optional[float]=None
|
||||
top_p: Optional[float]=None
|
||||
|
||||
def __init__(self,
|
||||
best_of: Optional[int]=None,
|
||||
echo: Optional[bool]=None,
|
||||
frequency_penalty: Optional[int]=None,
|
||||
logit_bias: Optional[dict]=None,
|
||||
logprobs: Optional[int]=None,
|
||||
max_tokens: Optional[int]=None,
|
||||
n: Optional[int]=None,
|
||||
presence_penalty: Optional[int]=None,
|
||||
stop: Optional[Union[str, list]]=None,
|
||||
suffix: Optional[str]=None,
|
||||
temperature: Optional[float]=None,
|
||||
top_p: Optional[float]=None) -> None:
|
||||
locals_ = locals()
|
||||
for key, value in locals_.items():
|
||||
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}
|
||||
|
||||
|
||||
class AzureOpenAIConfig(OpenAIConfig):
|
||||
"""
|
||||
Reference: https://platform.openai.com/docs/api-reference/chat/create
|
||||
|
||||
The class `AzureOpenAIConfig` provides configuration for the OpenAI's Chat API interface, for use with Azure. It inherits from `OpenAIConfig`. Below are the parameters::
|
||||
|
||||
- `frequency_penalty` (number or null): Defaults to 0. Allows a value between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, thereby minimizing repetition.
|
||||
|
||||
- `function_call` (string or object): This optional parameter controls how the model calls functions.
|
||||
|
||||
- `functions` (array): An optional parameter. It is a list of functions for which the model may generate JSON inputs.
|
||||
|
||||
- `logit_bias` (map): This optional parameter modifies the likelihood of specified tokens appearing in the completion.
|
||||
|
||||
- `max_tokens` (integer or null): This optional parameter helps to set the maximum number of tokens to generate in the chat completion.
|
||||
|
||||
- `n` (integer or null): This optional parameter helps to set how many chat completion choices to generate for each input message.
|
||||
|
||||
- `presence_penalty` (number or null): Defaults to 0. It penalizes new tokens based on if they appear in the text so far, hence increasing the model's likelihood to talk about new topics.
|
||||
|
||||
- `stop` (string / array / null): Specifies up to 4 sequences where the API will stop generating further tokens.
|
||||
|
||||
- `temperature` (number or null): Defines the sampling temperature to use, varying between 0 and 2.
|
||||
|
||||
- `top_p` (number or null): An alternative to sampling with temperature, used for nucleus sampling.
|
||||
"""
|
||||
|
||||
def __init__(self,
|
||||
frequency_penalty: int | None = None,
|
||||
function_call: str | dict | None = None,
|
||||
functions: list | None = None,
|
||||
logit_bias: dict | None = None,
|
||||
max_tokens: int | None = None,
|
||||
n: int | None = None,
|
||||
presence_penalty: int | None = None,
|
||||
stop: str | list | None = None,
|
||||
temperature: int | None = None,
|
||||
top_p: int | None = None) -> None:
|
||||
super().__init__(frequency_penalty,
|
||||
function_call,
|
||||
functions,
|
||||
logit_bias,
|
||||
max_tokens,
|
||||
n,
|
||||
presence_penalty,
|
||||
stop,
|
||||
temperature,
|
||||
top_p)
|
||||
Loading…
Add table
Add a link
Reference in a new issue