[recipes] Apple Notes import via macOS automation#184
Conversation
- Two-file pipeline: JXA extractor → Python importer - HTML→Markdown via markdownify, web URL + note-to-note link extraction - Heading-based chunking with optional LLM distillation - Sync log + SHA-256 content fingerprint dedup - Full OB1 PR gate compliance checklist Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- 8-task TDD plan: scaffold → JXA extractor → parser → chunking/fingerprint → CLI importer → embed/insert → README → PR - Covers secret scan, sync log, dry-run, --no-llm flag, exponential backoff - Complete code in every step, no placeholders Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
… report - Add _with_retry() with exponential backoff for 429/5xx errors - Add get_embedding() via OpenRouter embeddings endpoint - Add classify_type() via gpt-4o-mini JSON-mode classification - Add insert_thought() with duplicate fingerprint detection - Add live_import() orchestrating embed → classify → insert per chunk - Add _maybe_distil_with_llm() for chunks over 1000 words - Add _write_report() producing import-report.md summary - Replace Task 6 stub in main() with live_import() call
|
Hey @DavidROliverBA — welcome to Open Brain Source! 👋 Thanks for submitting your first PR. The automated review will run shortly and check things like metadata, folder structure, and README completeness. If anything needs fixing, the review comment will tell you exactly what. Once the automated checks pass, a human admin will review for quality and clarity. Expect a response within a few days. If you have questions, check out CONTRIBUTING.md or open an issue. |
…acking Remove accidentally committed __pycache__ .pyc files from git index and add a recipe-level .gitignore covering __pycache__, *.pyc/pyo, and runtime files (.env, notes-export.json, apple-notes-sync-log.json, import-report.md). Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
Thanks for the contribution, and welcome. The Apple Notes recipe itself is solid — JXA extraction with no manual export step, HTML-to-Markdown with heading-boundary chunking, a One scope thing before this is ready: the PR also includes two files under — Alan (community reviewer; non-binding) |
What this does
Imports Apple Notes directly into Open Brain using JXA (JavaScript for Automation) — no manual export step. Notes are converted from HTML to Markdown, chunked at heading boundaries, and ingested with embeddings and metadata including web URLs and note-to-note links.
What it requires
Tested on
I have tested this on my own Open Brain instance.