litellm-mirror/litellm/llms/mistral/mistral_chat_transformation.py
Krish Dholakia 713d762411 LiteLLM Minor Fixes and Improvements (09/13/2024) (#5689)
* refactor: cleanup unused variables + fix pyright errors

* feat(health_check.py): Closes https://github.com/BerriAI/litellm/issues/5686

* fix(o1_reasoning.py): add stricter check for o-1 reasoning model

* refactor(mistral/): make it easier to see mistral transformation logic

* fix(openai.py): fix openai o-1 model param mapping

Fixes https://github.com/BerriAI/litellm/issues/5685

* feat(main.py): infer finetuned gemini model from base model

Fixes https://github.com/BerriAI/litellm/issues/5678

* docs(vertex.md): update docs to call finetuned gemini models

* feat(proxy_server.py): allow admin to hide proxy model aliases

Closes https://github.com/BerriAI/litellm/issues/5692

* docs(load_balancing.md): add docs on hiding alias models from proxy config

* fix(base.py): don't raise notimplemented error

* fix(user_api_key_auth.py): fix model max budget check

* fix(router.py): fix elif

* fix(user_api_key_auth.py): don't set team_id to empty str

* fix(team_endpoints.py): fix response type

* test(test_completion.py): handle predibase error

* test(test_proxy_server.py): fix test

* fix(o1_transformation.py): fix max_completion_token mapping

* test(test_image_generation.py): mark flaky test
2024-09-14 10:02:55 -07:00

126 lines
5.2 KiB
Python

"""
Transformation logic from OpenAI /v1/chat/completion format to Mistral's /chat/completion format.
Why separate file? Make it easy to see how transformation works
Docs - https://docs.mistral.ai/api/
"""
import types
from typing import List, Literal, Optional, Union
class MistralConfig:
"""
Reference: https://docs.mistral.ai/api/
The class `MistralConfig` provides configuration for the Mistral's Chat API interface. Below are the parameters:
- `temperature` (number or null): Defines the sampling temperature to use, varying between 0 and 2. API Default - 0.7.
- `top_p` (number or null): An alternative to sampling with temperature, used for nucleus sampling. API Default - 1.
- `max_tokens` (integer or null): This optional parameter helps to set the maximum number of tokens to generate in the chat completion. API Default - null.
- `tools` (list or null): A list of available tools for the model. Use this to specify functions for which the model can generate JSON inputs.
- `tool_choice` (string - 'auto'/'any'/'none' or null): Specifies if/how functions are called. If set to none the model won't call a function and will generate a message instead. If set to auto the model can choose to either generate a message or call a function. If set to any the model is forced to call a function. Default - 'auto'.
- `stop` (string or array of strings): Stop generation if this token is detected. Or if one of these tokens is detected when providing an array
- `random_seed` (integer or null): The seed to use for random sampling. If set, different calls will generate deterministic results.
- `safe_prompt` (boolean): Whether to inject a safety prompt before all conversations. API Default - 'false'.
- `response_format` (object or null): An object specifying the format that the model must output. Setting to { "type": "json_object" } enables JSON mode, which guarantees the message the model generates is in JSON. When using JSON mode you MUST also instruct the model to produce JSON yourself with a system or a user message.
"""
temperature: Optional[int] = None
top_p: Optional[int] = None
max_tokens: Optional[int] = None
tools: Optional[list] = None
tool_choice: Optional[Literal["auto", "any", "none"]] = None
random_seed: Optional[int] = None
safe_prompt: Optional[bool] = None
response_format: Optional[dict] = None
stop: Optional[Union[str, list]] = None
def __init__(
self,
temperature: Optional[int] = None,
top_p: Optional[int] = None,
max_tokens: Optional[int] = None,
tools: Optional[list] = None,
tool_choice: Optional[Literal["auto", "any", "none"]] = None,
random_seed: Optional[int] = None,
safe_prompt: Optional[bool] = None,
response_format: Optional[dict] = None,
stop: Optional[Union[str, list]] = 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):
return [
"stream",
"temperature",
"top_p",
"max_tokens",
"tools",
"tool_choice",
"seed",
"stop",
"response_format",
]
def _map_tool_choice(self, tool_choice: str) -> str:
if tool_choice == "auto" or tool_choice == "none":
return tool_choice
elif tool_choice == "required":
return "any"
else: # openai 'tool_choice' object param not supported by Mistral API
return "any"
def map_openai_params(self, non_default_params: dict, optional_params: dict):
for param, value in non_default_params.items():
if param == "max_tokens":
optional_params["max_tokens"] = value
if param == "tools":
optional_params["tools"] = value
if param == "stream" and value is True:
optional_params["stream"] = value
if param == "temperature":
optional_params["temperature"] = value
if param == "top_p":
optional_params["top_p"] = value
if param == "stop":
optional_params["stop"] = value
if param == "tool_choice" and isinstance(value, str):
optional_params["tool_choice"] = self._map_tool_choice(
tool_choice=value
)
if param == "seed":
optional_params["extra_body"] = {"random_seed": value}
if param == "response_format":
optional_params["response_format"] = value
return optional_params