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

@ -9,6 +9,7 @@ import { MediaService } from 'src/services/media.service';
import { MetadataService } from 'src/services/metadata.service';
import { NotificationService } from 'src/services/notification.service';
import { PersonService } from 'src/services/person.service';
import { SearchService } from 'src/services/search.service';
import { SessionService } from 'src/services/session.service';
import { SmartInfoService } from 'src/services/smart-info.service';
import { StorageTemplateService } from 'src/services/storage-template.service';
@ -35,6 +36,7 @@ export class MicroservicesService {
private storageTemplateService: StorageTemplateService,
private storageService: StorageService,
private userService: UserService,
private searchService: SearchService,
) {}
async init() {
@ -53,6 +55,8 @@ export class MicroservicesService {
[JobName.USER_SYNC_USAGE]: () => this.userService.handleUserSyncUsage(),
[JobName.QUEUE_SMART_SEARCH]: (data) => this.smartInfoService.handleQueueEncodeClip(data),
[JobName.SMART_SEARCH]: (data) => this.smartInfoService.handleEncodeClip(data),
[JobName.QUEUE_DUPLICATE_DETECTION]: (data) => this.searchService.handleQueueSearchDuplicates(data),
[JobName.DUPLICATE_DETECTION]: (data) => this.searchService.handleSearchDuplicates(data),
[JobName.STORAGE_TEMPLATE_MIGRATION]: () => this.storageTemplateService.handleMigration(),
[JobName.STORAGE_TEMPLATE_MIGRATION_SINGLE]: (data) => this.storageTemplateService.handleMigrationSingle(data),
[JobName.QUEUE_MIGRATION]: () => this.mediaService.handleQueueMigration(),