microsoft / promptflow

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
https://microsoft.github.io/promptflow/
MIT License
8.43k stars 725 forks source link

[Draft] Add EvaluationContext for joining evaluation spans #2892

Closed thy09 closed 3 weeks ago

thy09 commented 1 month ago

Description

This pull request introduces several changes to the src/promptflow-tracing package, particularly to the promptflow/tracing/_eval_context.py, promptflow/tracing/_experimental/__init__.py, and promptflow/tracing/_trace.py files. The changes mainly focus on enhancing the tracing functionality by adding an EvaluationContext class and a LastSpanExporter class, and modifying the wrapped function. A test for the EvaluationContext class has also been added.

Enhancements to tracing functionality:

Test addition:

General Guidelines and Best Practices

Testing Guidelines

github-actions[bot] commented 1 month ago

promptflow-core test result

0 tests   0 :white_check_mark:  0s :stopwatch: 0 suites  0 :zzz: 0 files    0 :x:

Results for commit a4438d8e.

github-actions[bot] commented 1 month ago

promptflow-tracing test result

 12 files   12 suites   7m 17s :stopwatch:  19 tests  19 :white_check_mark: 0 :zzz: 0 :x: 228 runs  228 :white_check_mark: 0 :zzz: 0 :x:

Results for commit a4438d8e.

:recycle: This comment has been updated with latest results.

github-actions[bot] commented 1 month ago

SDK CLI Global Config Test Result heta/add-eval-context

4 tests   4 :white_check_mark:  1m 8s :stopwatch: 1 suites  0 :zzz: 1 files    0 :x:

Results for commit a4438d8e.

github-actions[bot] commented 1 month ago

Executor Unit Test Result heta/add-eval-context

779 tests   779 :white_check_mark:  3m 43s :stopwatch:   1 suites    0 :zzz:   1 files      0 :x:

Results for commit a4438d8e.

github-actions[bot] commented 1 month ago

Executor E2E Test Result heta/add-eval-context

238 tests   232 :white_check_mark:  5m 11s :stopwatch:   1 suites    5 :zzz:   1 files      1 :x:

For more details on these failures, see this check.

Results for commit a4438d8e.

github-actions[bot] commented 1 month ago

SDK CLI Test Result heta/add-eval-context

    4 files      4 suites   1h 6m 7s :stopwatch:   666 tests   638 :white_check_mark:  27 :zzz: 1 :x: 2 664 runs  2 555 :white_check_mark: 108 :zzz: 1 :x:

For more details on these failures, see this check.

Results for commit a4438d8e.

github-actions[bot] commented 1 month ago

promptflow SDK CLI Azure E2E Test Result heta/add-eval-context

  3 files    3 suites   4m 7s :stopwatch: 231 tests 202 :white_check_mark: 29 :zzz: 0 :x: 693 runs  606 :white_check_mark: 87 :zzz: 0 :x:

Results for commit a4438d8e.

github-actions[bot] commented 4 weeks ago

Hi, thank you for your interest in helping to improve the prompt flow experience and for your contribution. We've noticed that there hasn't been recent engagement on this pull request. If this is still an active work stream, please let us know by pushing some changes or leaving a comment.

github-actions[bot] commented 3 weeks ago

Hi, thank you for your contribution. Since there has not been recent engagement, we are going to close this out. Feel free to reopen if you'd like to continue working on these changes. Please be sure to remove the no-recent-activity label; otherwise, this is likely to be closed again with the next cleanup pass.