Add option to pass in multiple template text files for LLM-as-judge eval

[rchan26]

Fix for #98.

With this PR, you can pass in a number of .txt files for a new --templates argument separated with commas, e.g.

prompto_run_experiment ... --templates temp1.txt,temp2.txt

or

prompto_create_judge_file ... --templates 'temp1.txt, temp2.txt'

Tests have been updated for this.

To do:

• Write up docs for evaluation framework (for Improve evaluation functionalities #84)
• Add notebook example (for Improve evaluation functionalities #84)

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[codecov-commenter]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 63.86%. Comparing base (48d0440) to head (c3c9ee2).
Report is 16 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main      #99      +/-   ##
==========================================
+ Coverage   63.62%   63.86%   +0.23%     
==========================================
  Files          40       40              
  Lines        2128     2142      +14     
==========================================
+ Hits         1354     1368      +14     
  Misses        774      774              

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.