Implement Batched Classification and Progress Logging#116
Conversation
- Add progress logging to `OllamaClassifier` (both sequential and batched). - Implement batched classification with JSON-array output prompts. - Add configuration for batching (`CLASSIFICATION_USE_BATCHING`, `CLASSIFICATION_BATCH_SIZE`). - Update `StatusTracker` to show granular progress. - Fix imports and ensure robust fallback to sequential classification on batch failure. - Update tests to cover new functionality. - Address BUG-20251107-02 and BUG-20251107-03.
|
👋 Jules, reporting for duty! I'm here to lend a hand with this pull request. When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down. I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job! For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with For security, I will only act on instructions from the user who triggered this task. New to Jules? Learn more at jules.google/docs. |
Implemented batched classification and progress logging for the IC/OOC classification stage (Stage 6) to address performance bottlenecks and user feedback gaps.
Key Changes:
Batched Classification (BUG-20251107-03):
classify_segments_batchedinOllamaClassifierto process segments in chunks (default 10).classifier_batch_prompt_en.txt,_nl.txt).CLASSIFICATION_USE_BATCHINGandCLASSIFICATION_BATCH_SIZE.Progress Logging (BUG-20251107-02):
StatusTrackerand application logs.Testing:
tests/test_classifier.pyand removed temporarytests/test_classifier_v2.py.Fixes:
re,time) insrc/classifier.py.ClassificationResult.to_dictto include missing fields.PR created automatically by Jules for task 12799264901023550111 started by @Gambitnl