# Install
uv tool install chunktuner

# Initialize workspace
chunk-tune init --provider openai

# See cost estimate before running anything
chunk-tune estimate ./my_docs --use-case rag_qa

# Get a recommendation
chunk-tune recommend ./my_docs --use-case rag_qa

from pathlib import Path
from chunktuner import FileIngestor, LiteLLMEmbeddingFunction, AutoTuner
from chunktuner import default_registry, Evaluator, ScoreCalculator

docs = FileIngestor().ingest_dir(Path("./my_docs"))
embedding_fn = LiteLLMEmbeddingFunction("text-embedding-3-small")
tuner = AutoTuner(
    strategies=default_registry,
    evaluator=Evaluator(embedding_fn),
    scorer=ScoreCalculator(use_case="rag_qa"),
)
result = tuner.recommend(docs, use_case="rag_qa")
print(result.best.config)

{
  "mcpServers": {
    "chunktuner": {
      "command": "uvx",
      "args": ["--from", "chunktuner[mcp]", "chunk-tune-mcp"],
      "env": {
        "CHUNK_TUNER_BASE_DIR": "/path/to/your/corpus"
      }
    }
  }
}

chunk-tune init       Bootstrap workspace config
chunk-tune analyze    Quick structural scan (no API cost)
chunk-tune estimate   Dry-run cost/token estimate
chunk-tune evaluate   Full evaluation across strategies
chunk-tune recommend  Evaluation + best config recommendation
chunk-tune compare    Side-by-side comparison of specific strategies
chunk-tune preview    Inspect how a strategy splits a document
chunk-tune cache      Manage embedding and chunk cache

uv add chunktuner                    # library
uv tool install chunktuner           # global CLI
uvx chunktuner                       # ephemeral, no install

# With optional extras
uv add "chunktuner[docling]"         # PDF/DOCX support
uv add "chunktuner[ragas]"           # generation metrics
uv add "chunktuner[semantic]"        # semantic chunking
uv add "chunktuner[code]"            # AST code chunking
uv add "chunktuner[all]"             # everything