Configuration

Configuration

Ragmir reads .ragmir/config.json from the current directory or an ancestor. Start with rgr setup and edit JSON only for a concrete need.

{
  "sources": ["docs/**/*.md", "src", "!docs/archive/**"],
  "privacyProfile": "private",
  "retrievalProfile": "balanced",
  "embeddingProvider": "local-hash"
}

Common fields

Field	Default	Why change it
sources	[]	Add paths, globs, and ! exclusions
privacyProfile	private	Use strict for the strongest local floor
retrievalProfile	balanced	Choose fast, quality, or an explicit custom budget
embeddingProvider	local-hash	Select transformers only after an explicit preload
topK	8	Change the default passage count
mcpMaxOutputBytes	32768	Bound each MCP retrieval result
chunkSize / chunkOverlap	1200 / 200	Tune chunking, then rebuild
includeExtensions	[]	Add safe custom text extensions

Changing an embedding provider, model, or chunking field requires rgr ingest --rebuild.

Privacy profiles

• private disables remote model loading during normal retrieval and keeps redaction enabled.
• strict also bounds MCP output and disables external extractors.
• trusted and custom are explicit operator choices for different controls.

The privacy profile is a safety floor, separate from retrieval quality.

Local extractors

rgr ocr doctor
rgr ocr setup --language eng+fra

OCR is optional and page-aware. Custom extractor commands must be JSON argument arrays. They execute without a shell and must print text to stdout.

Use RAGMIR_* environment variables for local experiments, then run rgr status --json to inspect the effective configuration.

Canonical source: docs/configuration.md.