space/clickthrough
1
0
Fork 0
Code Issues 5 Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ocr): add /ocr endpoint for text extraction #7

Merged
luna merged 2 commits from feat/ocr-endpoint-issue-1 into main 2026-04-06 13:53:01 +02:00
Conversation 1 Commits 2 Files Changed 5 +252 -3
luna commented 2026-04-06 13:48:48 +02:00
Collaborator
Copy Link

Summary

  • add endpoint with 3 input modes: full screen, explicit region, and provided image bytes (base64)
  • return deterministic JSON blocks sorted top-to-bottom then left-to-right
  • include text, confidence, and bounding boxes
  • support optional and filter
  • document in and README

Notes

  • uses Python binding
  • returns clear errors when OCR backend/binary is unavailable

closes #1

## Summary - add endpoint with 3 input modes: full screen, explicit region, and provided image bytes (base64) - return deterministic JSON blocks sorted top-to-bottom then left-to-right - include text, confidence, and bounding boxes - support optional and filter - document in and README ## Notes - uses Python binding - returns clear errors when OCR backend/binary is unavailable closes #1
luna added 1 commit 2026-04-06 13:48:48 +02:00
feat(ocr): add /ocr endpoint for screen, region, and image input
All checks were successful
python-syntax / syntax-check (push) Successful in 5s
Details
python-syntax / syntax-check (pull_request) Successful in 4s
Details
097c6a095c
luna commented 2026-04-06 13:49:08 +02:00
Author
Collaborator
Copy Link

Clean summary (formatting-safe):

  • Added POST /ocr endpoint with 3 input modes: screen, region, image_base64
  • Returns deterministic JSON blocks sorted top-to-bottom and left-to-right
  • Each block includes text, confidence, and bbox
  • Supports optional language_hint and min_confidence
  • Updated docs/API.md and README
  • Added pytesseract dependency

Closes #1

Clean summary (formatting-safe): - Added POST /ocr endpoint with 3 input modes: screen, region, image_base64 - Returns deterministic JSON blocks sorted top-to-bottom and left-to-right - Each block includes text, confidence, and bbox - Supports optional language_hint and min_confidence - Updated docs/API.md and README - Added pytesseract dependency Closes #1
luna added 1 commit 2026-04-06 13:50:37 +02:00
docs(skill): include OCR endpoint workflow guidance
All checks were successful
python-syntax / syntax-check (push) Successful in 4s
Details
python-syntax / syntax-check (pull_request) Successful in 10s
Details
a6d7e37beb
luna merged commit 89cf228d13 into main 2026-04-06 13:53:01 +02:00
Sign in to join this conversation.
Reviewers
No Reviewers
Labels
No items
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
luna space
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: space/clickthrough#7
Delete Branch "feat/ocr-endpoint-issue-1"

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?