martin/Alpha
1
0
Fork 0
Code Issues 15 Pull Requests Actions Packages Projects 1 Releases Wiki Activity

OCR on email attachments in Daily Digest #19

New Issue
Closed
opened 2026-03-21 00:13:01 +01:00 by martin · 0 comments
martin commented 2026-03-21 00:13:01 +01:00
Owner
Copy Link

Generalize the ingest pipeline: extract text from any PDF attachment in Daily Digest using FileWizard OCR. Produce richer embeddings, enable full-text retrieval on emailed documents.

Generalize the ingest pipeline: extract text from any PDF attachment in Daily Digest using FileWizard OCR. Produce richer embeddings, enable full-text retrieval on emailed documents.
martin added this to the Phase 5 — Generalization & Backlog milestone 2026-03-21 00:13:01 +01:00
martin added the workflowembeddingbacklog labels 2026-03-21 00:13:01 +01:00
martin added this to the Road to Pompeo project 2026-03-21 11:28:06 +01:00
martin moved this to In Progress in Road to Pompeo on 2026-03-21 11:28:17 +01:00
martin moved this to Done in Road to Pompeo on 2026-03-21 11:32:12 +01:00
martin added reference main 2026-03-21 11:43:49 +01:00
martin self-assigned this 2026-03-21 11:53:30 +01:00
martin added spent time 5 minutes 2026-03-21 11:53:39 +01:00
Sign in to join this conversation.
main
Branches Tags
Labels
Clear labels
agent
backlog
broker
embedding
infra
memory
voice
workflow
No Label backlog embedding workflow
Milestone
No items
No Milestone Phase 5 — Generalization & Backlog
Projects
Clear projects
No project Road to Pompeo
Assignees
Clear assignees
martin
No Assignees martin
1 Participants
Notifications
Total Time Spent: 5 minutes
martin
5 minutes
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: martin/Alpha#19
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?