mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 18:54:30 +00:00
350cfc36f7
* build: merge branch * test: fix openai naming * fix(main.py): fix openai renaming * style: ignore function length for config factory * fix(sagemaker/): fix routing logic * fix: fix imports * fix: fix override
53 lines
2.4 KiB
Python
53 lines
2.4 KiB
Python
from typing import Optional, Union
|
|
|
|
from ...openai.completion.transformation import OpenAITextCompletionConfig
|
|
|
|
|
|
class AzureOpenAITextConfig(OpenAITextCompletionConfig):
|
|
"""
|
|
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: Optional[int] = 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:
|
|
super().__init__(
|
|
frequency_penalty=frequency_penalty,
|
|
logit_bias=logit_bias,
|
|
max_tokens=max_tokens,
|
|
n=n,
|
|
presence_penalty=presence_penalty,
|
|
stop=stop,
|
|
temperature=temperature,
|
|
top_p=top_p,
|
|
)
|