Improve Sentence Splitting#1
Open
geraldaddey wants to merge 5 commits into
Open
Conversation
Refactored the OpenAI API key loading logic into a single, reusable function in 'utils.py'.\n\nThis removes code duplication from five different scripts, making future key management simpler and more robust. The new 'load_api_key' function intelligently finds the '.env' file in the project root.
Replace the regex-based sentence splitting in 'caveman_compress.py' with spaCy's more robust sentence segmentation. This improves accuracy by correctly handling cases like abbreviations (e.g., "Mr. Smith") and other complex sentence structures that the previous implementation missed. Adds 'spacy' to the requirements.
Centralize API key handling
- Add caveman_compress_mlm.py: Predictability-aware compression using masked language models - Uses RoBERTa to score token predictability and remove top-k most predictable tokens - Achieves 20-30% token reduction with high accuracy retention - Free, offline, no API required - Update README with MLM installation, usage, and comparison - Add embedding similarity metrics to LLM-based compressor 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Replaced the regex-based sentence splitting in 'caveman_compress.py' with spaCy's more robust sentence segmentation.
This improves accuracy by correctly handling cases like abbreviations (e.g., "Mr. Smith") and other complex sentence structures that the previous implementation missed.
Adds 'spacy' to the requirements.