feat: async batching for classification to improve pipeline performance#8
Conversation
|
Important Review skippedToo many files! This PR contains 299 files, which is 149 over the limit of 150. ⚙️ Run configurationConfiguration used: Path: .coderabbit.yaml Review profile: ASSERTIVE Plan: Pro Run ID: ⛔ Files ignored due to path filters (1)
📒 Files selected for processing (299)
You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment Tip You can customize the high-level summary generated by CodeRabbit.Configure the |
|
Hi maintainers 👋 This PR introduces async batching to significantly improve pipeline performance. Previously, classification was sequential and slow (~1 hour+). With this change, processing is parallelized and much faster. I would love feedback and suggestions for further improvements 🙏 |
🚀 Summary
This PR improves the performance of the asset generation pipeline by introducing async + batch processing for classification prompts.
🔥 Problem
Previously, classification prompts were processed sequentially, leading to very long execution times (~1+ hour).
✅ Solution
⚡ Impact
🧪 Testing
📂 Changes
knowledge_utils.py🙏 Notes
This PR intentionally excludes generated assets and focuses only on core pipeline improvements.