Add initial work on evals #935
Draft
Conversation
This file contains 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
mikeedjones
reviewed
Feb 17, 2025
Comment on lines
289
to
317
| def average(cases: list[EvalReportCase]) -> EvalReportCaseAggregate: | ||
| """Produce a synthetic "summary" case by averaging quantitative attributes.""" | ||
| num_cases = len(cases) | ||
| if num_cases == 0: | ||
| raise ValueError('Cannot summarize an empty list of cases') | ||
|
|
||
| def _averages_by_name(values_by_name: list[dict[str, int | float]]) -> dict[str, float]: | ||
| counts_by_name: dict[str, int] = defaultdict(int) | ||
| sums_by_name: dict[str, float] = defaultdict(float) | ||
| for values in values_by_name: | ||
| for name, value in values.items(): | ||
| counts_by_name[name] += 1 | ||
| sums_by_name[name] += value | ||
| return {name: sums_by_name[name] / counts_by_name[name] for name in sums_by_name} | ||
|
|
||
| average_task_duration = sum(case.task_duration for case in cases) / num_cases | ||
| average_total_duration = sum(case.total_duration for case in cases) / num_cases | ||
|
|
||
| average_scores: dict[str, float] = _averages_by_name([case.scores for case in cases]) | ||
| # TODO: Aggregate labels, showing the percentage occurrences of each label | ||
| average_metrics: dict[str, float] = _averages_by_name([case.metrics for case in cases]) | ||
|
|
||
| return EvalReportCaseAggregate( | ||
| name='Averages', | ||
| scores=average_scores, | ||
| metrics=average_metrics, | ||
| task_duration=average_task_duration, | ||
| total_duration=average_total_duration, | ||
| ) |
There was a problem hiding this comment.
is it worth making the averaging function injectable?
![hyperlint-ai[bot]](https://avatars.githubusercontent.com/in/718456?s=60&v=4){kind=small}
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Fix #915.
There's a lot more to polish/add before merging this but it shows the API I had in mind for benchmark-style / "offline" evals, and an initial stab at an API for (flexibly) producing reports.
The report stuff is probably more configurable than it should/needs to be, but it wasn't too hard to implement so I did. Happy to change how that works.
At least as of now, you can see an example run/output by running
uv run pydantic_ai_slim/pydantic_ai/evals/__init__.pyon this branch (that file has aif __name__ == '__main__'that produces an example report).As of when I last updated this, in my terminal the report looks like this:
Note that if there are no scores / labels / metrics present in the cases, those columns will be excluded from the report. (So you don't have to pay the visual price unless you make use of those.) You also have the option to include case inputs and/or outputs in the generated reports, and can override most of the value- and diff-rendering logic on a per-score/label/metric basis.