github-mirrors/immich
1
0
Fork 0
mirror of https://github.com/immich-app/immich.git synced 2026-05-18 03:10:24 +03:00
Code Issues Packages Projects Releases Wiki Activity

feat: ocr (#18836)

Browse Source 
* feat: add OCR functionality and related configurations

* chore: update labeler configuration for machine learning files

* feat(i18n): enhance OCR model descriptions and add orientation classification and unwarping features

* chore: update Dockerfile to include ccache for improved build performance

* feat(ocr): enhance OCR model configuration with orientation classification and unwarping options, update PaddleOCR integration, and improve response structure

* refactor(ocr): remove OCR_CLEANUP job from enum and type definitions

* refactor(ocr): remove obsolete OCR entity and migration files, and update asset job status and schema to accommodate new OCR table structure

* refactor(ocr): update OCR schema and response structure to use individual coordinates instead of bounding box, and adjust related service and repository files

* feat: enhance OCR configuration and functionality

- Updated OCR settings to include minimum detection box score, minimum detection score, and minimum recognition score.
- Refactored PaddleOCRecognizer to utilize new scoring parameters.
- Introduced new database tables for asset OCR data and search functionality.
- Modified related services and repositories to support the new OCR features.
- Updated translations for improved clarity in settings UI.

* sql changes

* use rapidocr

* change dto

* update web

* update lock

* update api

* store positions as normalized floats

* match column order in db

* update admin ui settings descriptions

fix max resolution key

set min threshold to 0.1

fix bind

* apply config correctly, adjust defaults

* unnecessary model type

* unnecessary sources

* fix(ocr): switch RapidOCR lang type from LangDet to LangRec

* fix(ocr): expose lang_type (LangRec.CH) and font_path on OcrOptions for RapidOCR

* fix(ocr): make OCR text search case- and accent-insensitive using ILIKE + unaccent

* fix(ocr): add OCR search fields

* fix: Add OCR database migration and update ML prediction logic.

* trigrams are already case insensitive

* add tests

* format

* update migrations

* wrong uuid function

* linting

* maybe fix medium tests

* formatting

* fix weblate check

* openapi

* sql

* minor fixes

* maybe fix medium tests part 2

* passing medium tests

* format web

* readd sql

* format dart

* disabled in e2e

* chore: translation ordering

---------

Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com>
Co-authored-by: Alex Tran <alex.tran1502@gmail.com>
This commit is contained in:
Kang
2025-10-27 22:09:55 +08:00
committed by GitHub
parent c666dc6c67
commit 02b29046b3
90 changed files with 3610 additions and 1722 deletions
Download Patch File Download Diff File Expand all files Collapse all files
open-api/immich-openapi-specs.json
+72 -1
View File
@@ -5984,6 +5984,14 @@
"type": "string"
}
},
{
"name": "ocr",
"required": false,
"in": "query",
"schema": {
"type": "string"
}
},
{
"name": "personIds",
"required": false,
@@ -10408,6 +10416,9 @@
"notifications": {
"$ref": "#/components/schemas/JobStatusDto"
},
"ocr": {
"$ref": "#/components/schemas/JobStatusDto"
},
"search": {
"$ref": "#/components/schemas/JobStatusDto"
},
@@ -10437,6 +10448,7 @@
"metadataExtraction",
"migration",
"notifications",
"ocr",
"search",
"sidecar",
"smartSearch",
@@ -12108,7 +12120,8 @@
"sidecar",
"library",
"notifications",
"backupDatabase"
"backupDatabase",
"ocr"
],
"type": "string"
},
@@ -12678,6 +12691,9 @@
"nullable": true,
"type": "string"
},
"ocr": {
"type": "string"
},
"order": {
"allOf": [
{
@@ -12989,6 +13005,40 @@
],
"type": "string"
},
"OcrConfig": {
"properties": {
"enabled": {
"type": "boolean"
},
"maxResolution": {
"minimum": 1,
"type": "integer"
},
"minDetectionScore": {
"format": "double",
"maximum": 1,
"minimum": 0.1,
"type": "number"
},
"minRecognitionScore": {
"format": "double",
"maximum": 1,
"minimum": 0.1,
"type": "number"
},
"modelName": {
"type": "string"
}
},
"required": [
"enabled",
"maxResolution",
"minDetectionScore",
"minRecognitionScore",
"modelName"
],
"type": "object"
},
"OnThisDayDto": {
"properties": {
"year": {
@@ -13659,6 +13709,9 @@
"nullable": true,
"type": "string"
},
"ocr": {
"type": "string"
},
"personIds": {
"items": {
"format": "uuid",
@@ -14127,6 +14180,9 @@
"oauthAutoLaunch": {
"type": "boolean"
},
"ocr": {
"type": "boolean"
},
"passwordLogin": {
"type": "boolean"
},
@@ -14155,6 +14211,7 @@
"map",
"oauth",
"oauthAutoLaunch",
"ocr",
"passwordLogin",
"reverseGeocoding",
"search",
@@ -14762,6 +14819,9 @@
"nullable": true,
"type": "string"
},
"ocr": {
"type": "string"
},
"page": {
"minimum": 1,
"type": "number"
@@ -14967,6 +15027,9 @@
"nullable": true,
"type": "string"
},
"ocr": {
"type": "string"
},
"personIds": {
"items": {
"format": "uuid",
@@ -16416,6 +16479,9 @@
"notifications": {
"$ref": "#/components/schemas/JobSettingsDto"
},
"ocr": {
"$ref": "#/components/schemas/JobSettingsDto"
},
"search": {
"$ref": "#/components/schemas/JobSettingsDto"
},
@@ -16439,6 +16505,7 @@
"metadataExtraction",
"migration",
"notifications",
"ocr",
"search",
"sidecar",
"smartSearch",
@@ -16524,6 +16591,9 @@
"facialRecognition": {
"$ref": "#/components/schemas/FacialRecognitionConfig"
},
"ocr": {
"$ref": "#/components/schemas/OcrConfig"
},
"urls": {
"format": "uri",
"items": {
@@ -16540,6 +16610,7 @@
"duplicateDetection",
"enabled",
"facialRecognition",
"ocr",
"urls"
],
"type": "object"