enrich

fialr enrich <target> [options]

Extract text from files and run local LLM inference via Ollama to generate structured metadata: filename tokens, semantic tags, a one-sentence summary, and a confidence score. Tier 1 files are always skipped.

---

Arguments

Argument	Description
target	Directory to enrich (required)

Options

Option	Description
--execute	Apply enrichment metadata (not just report)
--jobs-dir PATH	Directory for job artifacts (default: .fialr/jobs)
--sensitivity-rules PATH	Path to sensitivity.yaml (default: config/sensitivity.yaml)

---

Prerequisites

Enrichment requires:

1. Ollama running locally at http://localhost:11434 (configurable in fialr.toml)
2. A pulled model (default: llama3.2, configurable under [enrichment].model)

---

What it does

Tier restrictions

Sensitivity tiers gate access to the enrichment pipeline:

Tier	Access
1 (RESTRICTED)	Never enters the pipeline. This is enforced, not advisory.
2 (SENSITIVE)	Local LLM on extracted text only. No raw file content sent to inference.
3 (INTERNAL)	Full local enrichment.

Text extraction

fialr extracts text from files using format-specific tools:

Format	Extraction method
Scanned PDF	ocrmypdf + Tesseract OCR
Native PDF	pypdfium2
Photos	piexif (EXIF metadata)
Audio	mutagen (ID3 tags)
Office documents	python-docx, openpyxl

Inference

Extracted text is sent to Ollama running on localhost. The inference layer is abstracted behind inference.py — cloud endpoints cannot be configured. The LLM returns structured JSON:

• Date — document subject date
• Entity — primary subject or organization
• Descriptor — semantic description
• Tags — semantic tags
• Summary — one-sentence summary
• Confidence — 0.0 to 1.0 score

Confidence routing

The confidence threshold (default: 0.7, configurable in fialr.toml under [enrichment].confidence_threshold) determines what happens with inference results:

• Above threshold — metadata is auto-applied to XATTRs and SQLite
• Below threshold — file is sent to the review queue with the LLM suggestion attached as a hint for manual review

---

Output

Dry-run:

enrich ~/Documents

────────────────────────────────────────────────────────
   enriched  623
     review  89
    skipped  135 (tier 1: 12, no text: 123)
     errors  0

---

Examples

# Dry-run enrichment
fialr enrich ~/Documents

# Apply enrichment metadata
fialr enrich ~/Documents --execute

---

See also

• Enrichment guide — walkthrough of the enrichment process
• Sensitivity Tiers — how tiers control enrichment access
• classify — check sensitivity tiers before enrichment