docs: Pines archive digitization plan and field capture deliverables - #10
Closed
jagp wants to merge 1 commit into
Closed
docs: Pines archive digitization plan and field capture deliverables#10jagp wants to merge 1 commit into
jagp wants to merge 1 commit into
Conversation
Adds planning deliverables for digitizing the historical document collection at The Pines (Skaneateles Lake): - PLAN.md: four-phase roadmap (on-site capture, transcription, structured archive, RAG-based query layer) - CAPTURE-GUIDE.md: field procedure for the on-site capture week - capture-log.template.csv: document inventory template - metadata-schema.json: draft JSON Schema for per-document metadata Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PUtw33CL4QM8RbpfjZToXY
Owner
Author
|
Closing unmerged: The Pines project is getting its own repo, so these planning docs shouldn't land in dev-strap. The branch Generated by Claude Code |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Planning deliverables for digitizing the historical document collection at The Pines (Skaneateles Lake, NY) and building an AI-queryable family archive from it. These docs seed the real project, which will be started in its own repo/session — this PR parks the plan somewhere shareable in the meantime.
What's included
docs/pines/PLAN.md— four-phase roadmap: on-site capture week (the only time-critical phase), transcription (OCR + vision-LLM for handwriting), structured archive (metadata, entity registry, timeline, search index), and the LLM layer (RAG-first, with a reality check on why training a small model from scratch on a ~1M-token corpus isn't viable).docs/pines/CAPTURE-GUIDE.md— field procedure for the Mon–Fri on-site window: phone copy-stand rig, naming convention, per-document procedure, daily schedule, nightly 3-2-1 backups, and capturing oral provenance from relatives while they're reachable.docs/pines/capture-log.template.csv— document inventory template matching the naming convention.docs/pines/metadata-schema.json— draft JSON Schema for per-documentmeta.jsonused in the structuring phase.Generated by Claude Code