codex-legal-doc-processor

Convert legal document collections into AI-ready JSONL datasets using the bundled legal-doc-processor project. Use when Codex needs to run or adapt the legal-doc-processor workflow for PDF, DOCX, PPTX, EML, MSG, or TXT legal files; classify documents as caselaw, published, private, or uncertain; remove PII from private documents; create RAG chunks and fine-tuning records; generate provenance manifests; review PII flags; or run adversarial re-identification and second-pass redaction.

Convert legal documents (PDF, DOCX, PPTX, EML, MSG) into AI/LLM-ready JSONL datasets. Strips PII from private documents using Presidio + Faker. Produces RAG-chunked output for case law and fine-tuning records for private/client docs. Includes provenance manifest for dataset buyers.