feat(server): near-duplicate detection (#8228)

* duplicate detection job, entity, config

* queueing

* job panel, update api

* use embedding in db instead of fetching

* disable concurrency

* only queue visible assets

* handle multiple duplicateIds

* update concurrent queue check

* add provider

* add web placeholder, server endpoint, migration, various fixes

* update sql

* select embedding by default

* rename variable

* simplify

* remove separate entity, handle re-running with different threshold, set default back to 0.02

* fix tests

* add tests

* add index to entity

* formatting

* update asset mock

* fix `upsertJobStatus` signature

* update sql

* formatting

* default to 0.03

* optimize clustering

* use asset's `duplicateId` if present

* update sql

* update tests

* expose admin setting

* refactor

* formatting

* skip if ml is disabled

* debug trash e2e

* remove from web

* remove from sidebar

* test if ml is disabled

* update sql

* separate duplicate detection from clip in config, disable by default for now

* fix doc

* lower minimum `maxDistance`

* update api

* Add and Use Duplicate Detection Feature Flag (#9364)

* Add Duplicate Detection Flag

* Use Duplicate Detection Flag

* Attempt Fixes for Failing Checks

* lower minimum `maxDistance`

* fix tests

---------

Co-authored-by: mertalev <101130780+mertalev@users.noreply.github.com>

* chore: fixes and additions after rebase

* chore: update api (remove new Role enum)

* fix: left join smart search so getAll works without machine learning

* test: trash e2e go back to checking length of assets is zero

* chore: regen api after rebase

* test: fix tests after rebase

* redundant join

---------

Co-authored-by: Nicholas Flamy <30300649+NicholasFlamy@users.noreply.github.com>
Co-authored-by: Zack Pollard <zackpollard@ymail.com>
Co-authored-by: Zack Pollard <zack@futo.org>
This commit is contained in:
Mert 2024-05-16 13:08:37 -04:00 committed by GitHub
parent 673e97e71d
commit 64636c0618
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
61 changed files with 1254 additions and 61 deletions

View file

@ -40,6 +40,7 @@ export enum WithoutProperty {
ENCODED_VIDEO = 'encoded-video',
EXIF = 'exif',
SMART_SEARCH = 'smart-search',
DUPLICATE = 'duplicate',
OBJECT_TAGS = 'object-tags',
FACES = 'faces',
PERSON = 'person',
@ -60,6 +61,7 @@ export interface AssetBuilderOptions {
isArchived?: boolean;
isFavorite?: boolean;
isTrashed?: boolean;
isDuplicate?: boolean;
albumId?: string;
personId?: string;
userIds?: string[];
@ -143,6 +145,12 @@ export interface AssetDeltaSyncOptions {
limit: number;
}
export interface AssetUpdateDuplicateOptions {
targetDuplicateId: string | null;
assetIds: string[];
duplicateIds: string[];
}
export type AssetPathEntity = Pick<AssetEntity, 'id' | 'originalPath' | 'isOffline'>;
export const IAssetRepository = 'IAssetRepository';
@ -176,6 +184,7 @@ export interface IAssetRepository {
getAll(pagination: PaginationOptions, options?: AssetSearchOptions): Paginated<AssetEntity>;
getAllByDeviceId(userId: string, deviceId: string): Promise<string[]>;
updateAll(ids: string[], options: Partial<AssetUpdateAllOptions>): Promise<void>;
updateDuplicates(options: AssetUpdateDuplicateOptions): Promise<void>;
update(asset: AssetUpdateOptions): Promise<void>;
remove(asset: AssetEntity): Promise<void>;
softDeleteAll(ids: string[]): Promise<void>;
@ -186,9 +195,10 @@ export interface IAssetRepository {
getTimeBuckets(options: TimeBucketOptions): Promise<TimeBucketItem[]>;
getTimeBucket(timeBucket: string, options: TimeBucketOptions): Promise<AssetEntity[]>;
upsertExif(exif: Partial<ExifEntity>): Promise<void>;
upsertJobStatus(jobStatus: Partial<AssetJobStatusEntity>): Promise<void>;
upsertJobStatus(...jobStatus: Partial<AssetJobStatusEntity>[]): Promise<void>;
getAssetIdByCity(userId: string, options: AssetExploreFieldOptions): Promise<SearchExploreItem<string>>;
getAssetIdByTag(userId: string, options: AssetExploreFieldOptions): Promise<SearchExploreItem<string>>;
getDuplicates(options: AssetBuilderOptions): Promise<AssetEntity[]>;
getAllForUserFullSync(options: AssetFullSyncOptions): Promise<AssetEntity[]>;
getChangedDeltaSync(options: AssetDeltaSyncOptions): Promise<AssetEntity[]>;
}