feat(eval): support embedding metric

[Kunlun-Zhu]

Closes #

📑 Description

✅ Checks

• My pull request adheres to the code style of this project
• My code requires changes to the documentation
• I have updated the documentation as required
• All the tests have passed
• Branch name follows type/descript (e.g. feature/add-llm-agents)
• Ready for code review

ℹ Additional Information

[codecov]

Codecov Report

Attention: Patch coverage is 0% with 18 lines in your changes missing coverage. Please review.

Project coverage is 76.17%. Comparing base (7a3397e) to head (7135dc7).
Report is 2 commits behind head on main.

Files with missing lines	Patch %	Lines
research_bench/proposal_eval.py	0.00%	16 Missing ⚠️
research_bench/collect_nips_paper_links.py	0.00%	2 Missing ⚠️

@@            Coverage Diff             @@
##             main     #810      +/-   ##
==========================================
- Coverage   76.61%   76.17%   -0.44%     
==========================================
  Files          69       69              
  Lines        3121     3139      +18     
==========================================
  Hits         2391     2391              
- Misses        730      748      +18     

Files with missing lines	Coverage Δ
research_bench/collect_nips_paper_links.py	0.00% <0.00%> (ø)
research_bench/proposal_eval.py	0.00% <0.00%> (ø)