fix(bug): update model handling in OpenAI and AzureOpenAI configurations #1178
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request includes several updates to the
langtest/augmentation/utils.py
file to enhance model configuration and validation logic. The most important changes include switching fromvalidator
tofield_validator
, adding a newmodel
field to configuration classes, and dynamically setting the model name in template generation functions.Updates to model configuration and validation:
langtest/augmentation/utils.py
: Changed import frompydantic.v1
topydantic
and replacedvalidator
withfield_validator
for template validation. [1] [2]langtest/augmentation/utils.py
: Addedmodel
field with default value"gpt-4o-mini"
toOpenAIConfig
andAzureOpenAIConfig
classes. [1] [2]Dynamic model name setting:
langtest/augmentation/utils.py
: Introducedmodel_name
variable to dynamically set the model ingenerate_templates_azoi
andgenerate_templates_openai
functions, removing hardcoded model names. [1] [2] [3] [4]Removal of redundant code:
langtest/augmentation/utils.py
: Removed themax_tokens
parameter from thegenerate_templates_azoi
andgenerate_templates_openai
functions. [1] [2]