Refactored llm clients, removed maxContinuations feature, exposed finishReason instead;
This commit is contained in:
@@ -4,7 +4,6 @@ maxTokens=2000
|
||||
maxContextLength=8000
|
||||
temperature=0.4
|
||||
topP=1.0
|
||||
maxContinuations=1
|
||||
modelProvider=OAI_TEXT_COMPLETION
|
||||
modelName=
|
||||
url=http://localhost:5001
|
||||
|
||||
Reference in New Issue
Block a user