feat: pytest, dataset_loader, --export to langsmith#15
Open
aniketwattamwar wants to merge 1 commit into
Open
Conversation
- Added support for data-driven evaluation by allowing scenarios to load `csv` or `jsonl` datasets directly in the manifest (`dataset` field), automatically mapping input/output columns to test steps. - Updated `manifest.schema.json` to enforce requiring either `steps` or `dataset` in a scenario. - Added `--export` flag to the `ecp run` CLI with support for exporting evaluation results to LangSmith as chain runs. - Bumped version to 0.4.1.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This PR introduces three major features to make ECP evaluations more extensible, scalable, and integrated: Pytest Integration, Dataset Support, and LangSmith Exports. It also bumps the package version to
0.4.1for release.Key Features
1. Pytest Integration 🧪
Added a native Pytest plugin (
ecp_runtime.pytest_plugin). ECP tests can now be discovered and run seamlessly as part of a standard Pytest suite, allowing developers to integrate agent evaluations directly into their existing unit/integration testing workflows.2. Dataset-driven Scenarios 📊
You can now define scenarios using external datasets instead of hard-coding individual steps in the YAML manifest. This is ideal for running evaluations against large benchmarks.
csvandjsonlfile types.input_columnandoutput_column(defaults to "input" and "output").text_matchgrader for the expected output if it exists in the dataset.manifest.schema.jsonto require eitherstepsordatasetper scenario.Example usage in manifest: