"Chunklet: A text chunking library with sentence/token limits and multilingual support"
https://github.com/Speedyk-005/chunklet
What it does:
- Splits text into chunks using both sentence and token limits
- Preserves context through adjustable overlap
- Supports 36+ languages with automatic detection
- Processes batches of documents efficiently
"Chunklet: A text chunking library with sentence/token limits and multilingual support"
https://github.com/Speedyk-005/chunklet
What it does: