mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-27 11:43:54 +00:00
* LiteLLM Minor Fixes & Improvements (09/16/2024) (#5723) * coverage (#5713) Signed-off-by: dbczumar <corey.zumar@databricks.com> * Move (#5714) Signed-off-by: dbczumar <corey.zumar@databricks.com> * fix(litellm_logging.py): fix logging client re-init (#5710) Fixes https://github.com/BerriAI/litellm/issues/5695 * fix(presidio.py): Fix logging_hook response and add support for additional presidio variables in guardrails config Fixes https://github.com/BerriAI/litellm/issues/5682 * feat(o1_handler.py): fake streaming for openai o1 models Fixes https://github.com/BerriAI/litellm/issues/5694 * docs: deprecated traceloop integration in favor of native otel (#5249) * fix: fix linting errors * fix: fix linting errors * fix(main.py): fix o1 import --------- Signed-off-by: dbczumar <corey.zumar@databricks.com> Co-authored-by: Corey Zumar <39497902+dbczumar@users.noreply.github.com> Co-authored-by: Nir Gazit <nirga@users.noreply.github.com> * feat(spend_management_endpoints.py): expose `/global/spend/refresh` endpoint for updating material view (#5730) * feat(spend_management_endpoints.py): expose `/global/spend/refresh` endpoint for updating material view Supports having `MonthlyGlobalSpend` view be a material view, and exposes an endpoint to refresh it * fix(custom_logger.py): reset calltype * fix: fix linting errors * fix: fix linting error * fix: fix import * test(test_databricks.py): fix databricks tests --------- Signed-off-by: dbczumar <corey.zumar@databricks.com> Co-authored-by: Corey Zumar <39497902+dbczumar@users.noreply.github.com> Co-authored-by: Nir Gazit <nirga@users.noreply.github.com>
This commit is contained in:
Krish Dholakia
GitHub
parent
618ea01ed7
commit
82b542df8f
34 changed files with 1387 additions and 502 deletions
|
|
@ -1,143 +0,0 @@
|
|||
"""
|
||||
Support for gpt model family
|
||||
"""
|
||||
|
||||
import types
|
||||
from typing import Optional, Union
|
||||
|
||||
import litellm
|
||||
from litellm.types.llms.openai import AllMessageValues, ChatCompletionUserMessage
|
||||
|
||||
|
||||
class OpenAIGPTConfig:
|
||||
"""
|
||||
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
|
||||
response_format: Optional[dict] = 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,
|
||||
response_format: Optional[dict] = None,
|
||||
) -> None:
|
||||
locals_ = locals().copy()
|
||||
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
|
||||
}
|
||||
|
||||
def get_supported_openai_params(self, model: str) -> list:
|
||||
base_params = [
|
||||
"frequency_penalty",
|
||||
"logit_bias",
|
||||
"logprobs",
|
||||
"top_logprobs",
|
||||
"max_tokens",
|
||||
"max_completion_tokens",
|
||||
"n",
|
||||
"presence_penalty",
|
||||
"seed",
|
||||
"stop",
|
||||
"stream",
|
||||
"stream_options",
|
||||
"temperature",
|
||||
"top_p",
|
||||
"tools",
|
||||
"tool_choice",
|
||||
"function_call",
|
||||
"functions",
|
||||
"max_retries",
|
||||
"extra_headers",
|
||||
"parallel_tool_calls",
|
||||
] # works across all models
|
||||
|
||||
model_specific_params = []
|
||||
if (
|
||||
model != "gpt-3.5-turbo-16k" and model != "gpt-4"
|
||||
): # gpt-4 does not support 'response_format'
|
||||
model_specific_params.append("response_format")
|
||||
|
||||
if (
|
||||
model in litellm.open_ai_chat_completion_models
|
||||
) or model in litellm.open_ai_text_completion_models:
|
||||
model_specific_params.append(
|
||||
"user"
|
||||
) # user is not a param supported by all openai-compatible endpoints - e.g. azure ai
|
||||
return base_params + model_specific_params
|
||||
|
||||
def _map_openai_params(
|
||||
self, non_default_params: dict, optional_params: dict, model: str
|
||||
) -> dict:
|
||||
supported_openai_params = self.get_supported_openai_params(model)
|
||||
for param, value in non_default_params.items():
|
||||
if param in supported_openai_params:
|
||||
optional_params[param] = value
|
||||
return optional_params
|
||||
|
||||
def map_openai_params(
|
||||
self, non_default_params: dict, optional_params: dict, model: str
|
||||
) -> dict:
|
||||
return self._map_openai_params(
|
||||
non_default_params=non_default_params,
|
||||
optional_params=optional_params,
|
||||
model=model,
|
||||
)
|
||||
Loading…
Add table
Add a link
Reference in a new issue