update default cross-encoder model to Xenova/ms-marco-MiniLM-L-6-v2 across docs

[Goodnight77]

summary

fix default cross-encoder model name in docs
the default model was DEFAULT_MODEL = "Xenova/ms-marco-MiniLM-L-6-v2" in CrossEncoderEmbedder class
changed cross-encoder/ms-marco-MiniLM-L-6-v2 to Xenova/ms-marco-MiniLM-L-6-v2 in:

• docs/reference.md
• docs/search.md
• tests/test_parser.py
• resources/Features.md

Summary by CodeRabbit

• Documentation

  • Updated default reranker model references in reference, search, and feature documentation.

• Tests

  • Updated test assertions to align with reranker model reference updates.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Repository UI

Review profile: CHILL

Plan: Pro Plus

Run ID: 329e50ca-f8b0-4702-86cf-f958b524d363

📥 Commits

Reviewing files that changed from the base of the PR and between f2dda99 and 40124bb.

📒 Files selected for processing (4)

• docs/reference.md
• docs/search.md
• resources/Features.md
• tests/test_parser.py

---

📝 Walkthrough

Walkthrough

Cross-encoder reranking model identifiers are updated from cross-encoder/ to Xenova/ branding across reference and search documentation, feature examples, and parser tests. The model variant names (MiniLM-L-6-v2 and MiniLM-L-12-v2) remain unchanged.

Changes

Cross-encoder model rebranding from cross-encoder to Xenova

Layer / File(s)	Summary
Documentation updates for model identifiers docs/reference.md, docs/search.md	Reference documentation table and search documentation section are updated to reflect the new default Xenova model identifier (Xenova/ms-marco-MiniLM-L-6-v2) and larger variant (Xenova/ms-marco-MiniLM-L-12-v2).
Example and test validation resources/Features.md, tests/test_parser.py	Feature example and parser test cases are updated to expect the new Xenova model identifier in RERANK MODEL configurations and parsing assertions.

Poem

🐰 The cross-encoder hops away,
Xenova takes the stage today,
Models renamed, tests align,
Docs shine bright with L-six and L-twelve in line! ✨

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately summarizes the primary change: updating the default cross-encoder model to Xenova/ms-marco-MiniLM-L-6-v2 across documentation files, matching the actual changeset.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}