Files
immich/server/src/schema/migrations/1758705789125-CreateOCRSearchTable.ts
Kang 02b29046b3 feat: ocr (#18836)
* 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>
2025-10-27 14:09:55 +00:00

21 lines
1.1 KiB
TypeScript

import { Kysely, sql } from 'kysely';
export async function up(db: Kysely<any>): Promise<void> {
await sql`CREATE TABLE "ocr_search" ("assetId" uuid NOT NULL, "text" text NOT NULL);`.execute(db);
await sql`ALTER TABLE "ocr_search" ADD CONSTRAINT "ocr_search_pkey" PRIMARY KEY ("assetId");`.execute(db);
await sql`ALTER TABLE "ocr_search" ADD CONSTRAINT "ocr_search_assetId_fkey" FOREIGN KEY ("assetId") REFERENCES "asset" ("id") ON UPDATE CASCADE ON DELETE CASCADE;`.execute(
db,
);
await sql`CREATE INDEX "idx_ocr_search_text" ON "ocr_search" USING gin (f_unaccent("text") gin_trgm_ops);`.execute(
db,
);
await sql`INSERT INTO "migration_overrides" ("name", "value") VALUES ('index_idx_ocr_search_text', '{"type":"index","name":"idx_ocr_search_text","sql":"CREATE INDEX \\"idx_ocr_search_text\\" ON \\"ocr_search\\" USING gin (f_unaccent(\\"text\\") gin_trgm_ops);"}'::jsonb);`.execute(
db,
);
}
export async function down(db: Kysely<any>): Promise<void> {
await sql`DROP TABLE "ocr_search";`.execute(db);
await sql`DELETE FROM "migration_overrides" WHERE "name" = 'index_idx_ocr_search_text';`.execute(db);
}