proposal: Integration of 3rd party evaluation frameworks

[shadeMe]

Proposed Changes:

Proposal for implementing third-party LLM evaluation frameworks in haystack-core-integrations.

Rendered.

Checklist

• I have read the contributors guidelines and the code of conduct
• I have updated the related issue with new insights and changes
• I added unit tests and updated the docstrings
• I've used one of the conventional commit types for my PR title: fix:, feat:, build:, chore:, ci:, docs:, style:, refactor:, perf:, test:.
• I documented my code
• I ran pre-commit hooks and fixed any issue

[sandangel]

Is it possible to also add https://github.com/Arize-ai/phoenix (both evaluation and tracing) ? I think they have plan to integrate with haystack for tracing but postponed it to wait for haystack 2.0

[julian-risch]

@sandangel Yes, we are not limiting the integrations to the three frameworks mentioned in this proposal. We'll start with one framework as an example and adding more is encouraged through similar integrations. I can imagine a PhoenixEvaluator component as a Haystack integration based on https://github.com/Arize-ai/phoenix?tab=readme-ov-file#llm-evals 👍

[sandangel]

That sounds great. Thanks for putting this together.