Minor extraction updates - #523
Conversation
There was a problem hiding this comment.
Pull request overview
Warning
Copilot couldn't run its full agentic review because it didn't start before the timeout. Make sure your repository has a runner available, or add a copilot-code-review.yml file specifying one with the runs-on attribute. See the docs for more details.
Forward additional extraction/conversion attributes into document output metadata to improve monitoring and observability.
Changes:
- Add several extraction/conversion-related fields to compiled document info output.
- Track and persist
num_features_extractedduring ordinance parsing flows. - Treat OpenAI
APIConnectionErroras retryable in GPT calls.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 6 comments.
| File | Description |
|---|---|
| compass/services/threaded.py | Adds more doc.attrs fields into the compiled doc info output payload for monitoring. |
| compass/services/openai.py | Expands retryable OpenAI exception set to include connection errors. |
| compass/plugin/ordinance.py | Computes and stores extracted feature counts in extraction_context.attrs during parsing. |
Codecov Report❌ Patch coverage is
❌ Your patch status has failed because the patch coverage (0.00%) is below the target coverage (80.00%). You can increase the patch coverage or adjust the target coverage. Additional details and impacted files@@ Coverage Diff @@
## main #523 +/- ##
==========================================
- Coverage 63.82% 63.78% -0.05%
==========================================
Files 78 78
Lines 7437 7445 +8
Branches 755 755
==========================================
+ Hits 4747 4749 +2
- Misses 2529 2536 +7
+ Partials 161 160 -1
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Harness. 🚀 New features to boost your workflow:
|
Forward some attributes into outputs for better extraction monitoring