chonkie and adaptive-chunking

The tools are complementary: chonkie provides a lightweight ingestion library for RAG pipelines, while adaptive-chunking offers a method to automatically select optimal chunking strategies, which could be integrated into the ingestion process that chonkie facilitates.

chonkie
83
Verified
adaptive-chunking
25
Experimental
Maintenance 25/25
Adoption 15/25
Maturity 25/25
Community 18/25
Maintenance 13/25
Adoption 3/25
Maturity 9/25
Community 0/25
Stars: 3,829
Forks: 256
Downloads:
Commits (30d): 53
Language: Python
License: MIT
Stars: 4
Forks:
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No risk flags
No Package No Dependents

About chonkie

chonkie-inc/chonkie

🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines

Provides pluggable chunking strategies—recursive, semantic, code-aware, and LLM-based—with composable pipeline workflows that chain multiple chunkers and refineries together. Integrates with 32+ tools across tokenizers (GPT-2, BPE), embeddings (OpenAI, Sentence Transformers), vector databases, and LLMs, while supporting 56 languages out-of-the-box through modular dependency installation.

About adaptive-chunking

ekimetrics/adaptive-chunking

Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.

Scores updated daily from GitHub, PyPI, and npm data. How scores work