feat: adding Maximum Margin Relevance Ranker

[davidsbatista]

Related Issues

• fixes Adding Maximum Margin Relevance Ranker #8555

Proposed Changes:

• I've added a new strategy to rank the documents based on diversity. The function implements the Maximum Marginal Relevance (MMR) scoring and uses it for ranking the documents based on similarity with the query and diversity from the already selected documents (see: PDF)

• Added to new init parameters, to decide which diversity strategy is used, and another one to set the threshold between similarity with the query and document diversity.

• Extracted some common code from both strategies into a new private function.

How did you test it?

• Manual verification, plus local tests run successfully

Notes for the reviewer

• I'm trying to debug and understand why the CI coverage tool doesn't account for the new test I've added

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 11974762094

Details

• 0 of 0 changed or added relevant lines in 0 files are covered.
• 6 unchanged lines in 1 file lost coverage.
• Overall coverage increased (+0.004%) to 90.286%

---

Files with Coverage Reduction	New Missed Lines	%
components/rankers/sentence_transformers_diversity.py	6	95.86%

Totals
Change from base Build 11974755029:	0.004%
Covered Lines:	7937
Relevant Lines:	8791

---

💛 - Coveralls

[anakin87]

Nice addition!

I had a first look and left some comments.
Let's also add some unit tests.

[anakin87]

I will let @shadeMe take a final look, but LGTM

[anakin87]

Merge main to remove linting failures.