[AUTO-MERGE] Updating the MLFlow backend from file to sqlite-based.

[drewoldag]

Change Description

Closes #780

Solution Description

Updating the default location for MLflow metrics to be tracked. Using SQLite database now instead of file-backed storage.

See this migration guide: https://mlflow.org/docs/latest/self-hosting/migrate-from-file-store

[Copilot]

Pull request overview

Updates Hyrax’s MLflow tracking configuration to avoid the deprecated filesystem backend by switching the tracking URI to a SQLite database under the configured results root directory.

Changes:

• Switch MLflow tracking URI in train to sqlite://.../mlflow/mlflow.db.
• Switch MLflow tracking URI in test to sqlite://.../mlflow/mlflow.db.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
src/hyrax/verbs/train.py	Points MLflow tracking to a SQLite DB under the results root.
src/hyrax/verbs/test.py	Points MLflow tracking to the same SQLite DB under the results root.

---

You can also share your feedback on Copilot code review. Take the survey.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 64.73%. Comparing base (6b45631) to head (2e72f5a).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #781      +/-   ##
==========================================
+ Coverage   64.71%   64.73%   +0.01%     
==========================================
  Files          61       61              
  Lines        5887     5890       +3     
==========================================
+ Hits         3810     3813       +3     
  Misses       2077     2077              

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

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[drewoldag]

@copilot make the changes that are mentioned in the two comments, and be sure that the change is consistent in both train.py and test.py. Eventually we would like to abstract that logic out, but not in this PR.

[Copilot]

@drewoldag I've opened a new pull request, #782, to work on those changes. Once the pull request is ready, I'll request review from you.

[github-actions]

Before [6b45631]	After [b9dc52e]	Ratio	Benchmark (Parameter)
failed	failed	n/a	data_cache_benchmarks.DataCacheBenchmarks.time_preload_cache_hsc1k
failed	failed	n/a	data_cache_benchmarks.DataCacheBenchmarks.track_cache_hsc1k_hyrax_size_undercount
failed	failed	n/a	data_request_benchmarks.DatasetRequestBenchmarks.time_request_all_data
38.9±0.5ms	40.0±0.4ms	1.03	benchmarks.time_nb_obj_dir
1.91±0.02s	1.94±0.01s	1.01	benchmarks.time_database_connection_help
1.92±0.01s	1.93±0.01s	1.01	benchmarks.time_infer_help
1.92±0s	1.94±0.01s	1.01	benchmarks.time_prepare_help
1.93±0.02s	1.94±0.02s	1.01	benchmarks.time_rebuild_manifest_help
1.93±0.01s	1.94±0.01s	1.01	benchmarks.time_visualize_help
5.84±0s	5.90±0s	1.01	vector_db_benchmarks.VectorDBInsertBenchmarks.time_load_vector_db(2048, 'chromadb')

Click here to view all benchmarks.

[mtauraso]

LGTM