mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-23 11:30:37 +00:00
premai[patch]: Standardize premai params (#21513)
Thank you for contributing to LangChain! community:premai[patch]: standardize init args - updated `temperature` with Pydantic Field, updated the unit test. - updated `max_tokens` with Pydantic Field, updated the unit test. - updated `max_retries` with Pydantic Field, updated the unit test. Related to #20085 --------- Co-authored-by: Isaac Francisco <78627776+isahers1@users.noreply.github.com> Co-authored-by: ccurme <chester.curme@gmail.com>
This commit is contained in:
@@ -271,13 +271,22 @@ class ChatPremAI(BaseChatModel, BaseModel):
|
||||
If model name is other than default model then it will override the calls
|
||||
from the model deployed from launchpad."""
|
||||
|
||||
temperature: Optional[float] = None
|
||||
session_id: Optional[str] = None
|
||||
"""The ID of the session to use. It helps to track the chat history."""
|
||||
|
||||
temperature: Optional[float] = Field(default=None)
|
||||
"""Model temperature. Value should be >= 0 and <= 1.0"""
|
||||
|
||||
max_tokens: Optional[int] = None
|
||||
top_p: Optional[float] = None
|
||||
"""top_p adjusts the number of choices for each predicted tokens based on
|
||||
cumulative probabilities. Value should be ranging between 0.0 and 1.0.
|
||||
"""
|
||||
|
||||
max_tokens: Optional[int] = Field(default=None)
|
||||
|
||||
"""The maximum number of tokens to generate"""
|
||||
|
||||
max_retries: int = 1
|
||||
max_retries: int = Field(default=1)
|
||||
"""Max number of retries to call the API"""
|
||||
|
||||
system_prompt: Optional[str] = ""
|
||||
|
Reference in New Issue
Block a user