fix: Support isolated node eval in run_batch in Generators

[bogdankostic]

Related Issues

• related to PromptNode doesn't support isolated node evaluation #3275

Proposed Changes:

This PR adds the parameter add_isolated_node_eval to the run_batch method of the BaseGenerator. This is needed for cases where a user calls eval_batch on a Pipeline with add_isolated_node_eval=True. Previously, this parameter was just ignored.

How did you test it?

I added two unit tests, one for run and one for run_batch.

Notes for the reviewer

I moved the EVAL_LABELS from test_eval.py to a fixture in conftest.py to be able to use them in test_generator.py.

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

[coveralls]

Pull Request Test Coverage Report for Build 5476609584

• 0 of 0 changed or added relevant lines in 0 files are covered.
• 20 unchanged lines in 1 file lost coverage.
• Overall coverage increased (+0.06%) to 44.712%

---

Files with Coverage Reduction	New Missed Lines	%
nodes/answer_generator/base.py	20	54.88%

Totals
Change from base Build 5474864964:	0.06%
Covered Lines:	10294
Relevant Lines:	23023

---

💛 - Coveralls

[julian-risch]

LGTM! 👍 The unit tests could have maybe checked whether the answer from the mocked prediction appears in the result. Right now it's basically just answers_isolated in result so the check could be more detailed.
I saw that you updated the related issue, which is good. 👍 For Generators I consider the problem fixed. Let's see whether we can add the functionality for PromptNode too in the next sprint.
Thank you for the extra effort in this sprint to reduce our backlog! 🙌