Add configurable default model support#161
Merged
Merged
Conversation
Stephen Belanger (Qard)
added
enhancement
Braintrust eval reportAutoevals (model-flexibility-1768324125)
|
Stephen Belanger (Qard)
force-pushed
the
model-flexibility
branch
3 times, most recently
from
48320a5 to
91f19f8
Compare
Stephen Belanger (Qard)
force-pushed
the
model-flexibility
branch
3 times, most recently
from
7d7b9da to
7f8c1fd
Compare
Olmo Maldonado (ibolmo)
approved these changes
Jan 13, 2026
This change allows users to configure which model to use as the default
for all evaluations, replacing the hardcoded gpt-4o default.
Changes:
- Add `defaultModel` parameter to `init()` in both JS and Python
- Add `getDefaultModel()` function to retrieve configured default model
- Update LLMClassifier and RAGAS scorers to use configurable default model
- Update documentation with examples for different use cases
This enables:
- Using different OpenAI models (gpt-4-turbo, o1, gpt-3.5-turbo, etc.)
- Using non-OpenAI models via Braintrust proxy (Claude, Gemini, Llama, etc.)
- Configuring once and having all evaluators use the preferred model
Example usage:
```javascript
init({
client: new OpenAI({
apiKey: process.env.BRAINTRUST_API_KEY,
baseURL: "https://api.braintrust.dev/v1/proxy",
}),
defaultModel: "claude-3-5-sonnet-20241022",
});
```
Fixes #136
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Stephen Belanger (Qard)
force-pushed
the
model-flexibility
branch
from
7f8c1fd to
d616f67
Compare
Braintrust eval report
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 change allows users to configure which model to use as the default for all evaluations, replacing the hardcoded gpt-4o default.
Changes:
defaultModelparameter toinit()in both JS and PythongetDefaultModel()function to retrieve configured default modelThis enables:
Example usage:
Fixes #136