You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We cannot change the default temperature set on a model at creation per model invocation, neither as an option to invoke nor as a bind change.
Propose a Solution
Base implementation of sdk chat model on @langchain/oneai models.
On first glace they seem to handle this.
Describe Alternatives
Configure 2 models and use them interchangeably, since the end http client is shared and discovery is shared/cached it should work.
But this gets nasty if we want to provide several gpt versions doubling possibly active models needed.
Affected Development Phase
Development
Impact
Inconvenience
Timeline
Next months
Additional Context
No response
The text was updated successfully, but these errors were encountered:
Describe the Problem
We cannot change the default temperature set on a model at creation per model invocation, neither as an option to
invoke
nor as abind
change.Propose a Solution
Base implementation of sdk chat model on @langchain/oneai models.
On first glace they seem to handle this.
Describe Alternatives
Configure 2 models and use them interchangeably, since the end http client is shared and discovery is shared/cached it should work.
But this gets nasty if we want to provide several gpt versions doubling possibly active models needed.
Affected Development Phase
Development
Impact
Inconvenience
Timeline
Next months
Additional Context
No response
The text was updated successfully, but these errors were encountered: