mirror of
https://github.com/NicolasBohn/NexQuant.git
synced 2026-07-27 23:47:46 +00:00
feat: add reasoning_effort parameter to LiteLLMAPIBackend and LLMSett… (#754)
* feat: Add reasoning_effort parameter to LiteLLMAPIBackend and LLMSettings * style: Use consistent quotation marks for reasoning_effort literals
This commit is contained in:
@@ -88,6 +88,7 @@ class LiteLLMAPIBackend(APIBackend):
|
||||
stream=LITELLM_SETTINGS.chat_stream,
|
||||
temperature=LITELLM_SETTINGS.chat_temperature,
|
||||
max_tokens=LITELLM_SETTINGS.chat_max_tokens,
|
||||
reasoning_effort=LITELLM_SETTINGS.reasoning_effort,
|
||||
**kwargs,
|
||||
)
|
||||
logger.info(
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from pathlib import Path
|
||||
from typing import Literal
|
||||
|
||||
from pydantic import Field
|
||||
|
||||
@@ -14,6 +15,8 @@ class LLMSettings(ExtendedBaseSettings):
|
||||
chat_model: str = "gpt-4-turbo"
|
||||
embedding_model: str = "text-embedding-3-small"
|
||||
|
||||
reasoning_effort: Literal["low", "medium", "high"] | None = None
|
||||
|
||||
# TODO: most of the settings are only used on deprec.DeprecBackend.
|
||||
# So they should move the settings to that folder.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user