GraphCanon
Home/Data & Retrieval/chunktuner
chunktuner logo

chunktuner

shantanu-deshmukh/chunktuner

Benchmark and optimize chunking strategies for RAG corpus

GitHub Website

GraphCanon updated today · GitHub synced today

2
Stars
0
Forks
0
Open issues
0
Watchers
3w
Last push
Python MITCreated May 2, 2026

Trust & integrity

Full report
Maintenance
Active (20d since push)
As of today · Source: github_public_v1
Provenance
Not a fork · Personal account
As of today · Source: github_public_v1
Security (OSV)
2 low (2 low)
As of today · Source: mcp_manifest@v1

Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.

Overview

Provides a benchmarking suite to evaluate different chunking strategies on a retrieval-augmented generation (RAG) corpus. Includes tools for recommendation, evaluation, and optimization of configurations.

Capability facts

CLI
CLI entrypoint

Source: pyproject.toml:[project.scripts] · Jul 12, 2026

Languages
python

Source: github.language+pyproject.toml · Jul 12, 2026

Categories

Data & RetrievalEvaluation & Observability

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Jul 11, 2026)

pip install chunktuner
Source link

Tags

chunkingembeddingevaluationlangchainlitellmllamaindexllmoptimization

README

Install (pick one)

uv tool install chunktuner pip install chunktuner

See cost estimate before running anything

chunk-tune estimate ./my_docs --use-case rag_qa

Installation options

pip install chunktuner                 # CLI + library
uv add chunktuner                      # library
uv tool install chunktuner             # global CLI
uvx --from chunktuner chunk-tune …     # ephemeral CLI (no install)