refactor: reuse app metadata extraction flow in evals

[juliehinge]

❤️ Thank you for your contribution!

Description

Refactored the evals to use Orcha endpoints and download the dataset from GitHub via dataset_sync.py.

• Removed duplicated extractor modules and model setup.
• Normalized the schema in evaluators.py to match the schema predicted by the Orcha app. This required updating some tests in test_evaluators.py.

Fixed an issue in dataset.py related to how the dataset is created/fetched from Langfuse.
Pinned the Langfuse version due to a change in the newer Langfuse API affecting the parameters required when creating dataset items.

• Therefore the current Langfuse version is intentionally limited because newer versions require an additional parameter when creating dataset items. In the future, we can upgrade to a newer version and update the dataset item creation accordingly.

Checklist

Ticks in all boxes and 🟢 on all GitHub actions status checks are required to merge:

• [ x] I'm aware of the code of conduct.
• [ x] I've created logical separate commits and followed the commit message format.
• [ x] I've added relevant test cases.
• I've added relevant documentation.
• I've marked translation strings.
• [x ] I've identified the copyright holder(s) and updated copyright headers for touched files (>15 lines contributions).
• [x ] I've NOT included third-party code (copy/pasted source code or new dependencies).
  • If you have added third-party code (copy/pasted or new dependencies), please reach out to an architect on Discord.

Frontend

• I've followed the CSS/JS and React guidelines.
• I've followed the web accessibility guidelines.
• I've followed the user interface guidelines.

Reminder

By using GitHub, you have already agreed to the GitHub’s Terms of Service including that:

1. You license your contribution under the same terms as the current repository’s license.
2. You agree that you have the right to license your contribution under the current repository’s license.

[OliverGeneser]

lgtm