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

@ -14,6 +14,7 @@ class SystemConfigMachineLearningDto {
/// Returns a new [SystemConfigMachineLearningDto] instance.
SystemConfigMachineLearningDto({
required this.clip,
required this.duplicateDetection,
required this.enabled,
required this.facialRecognition,
required this.url,
@ -21,6 +22,8 @@ class SystemConfigMachineLearningDto {
CLIPConfig clip;
DuplicateDetectionConfig duplicateDetection;
bool enabled;
RecognitionConfig facialRecognition;
@ -30,6 +33,7 @@ class SystemConfigMachineLearningDto {
@override
bool operator ==(Object other) => identical(this, other) || other is SystemConfigMachineLearningDto &&
other.clip == clip &&
other.duplicateDetection == duplicateDetection &&
other.enabled == enabled &&
other.facialRecognition == facialRecognition &&
other.url == url;
@ -38,16 +42,18 @@ class SystemConfigMachineLearningDto {
int get hashCode =>
// ignore: unnecessary_parenthesis
(clip.hashCode) +
(duplicateDetection.hashCode) +
(enabled.hashCode) +
(facialRecognition.hashCode) +
(url.hashCode);
@override
String toString() => 'SystemConfigMachineLearningDto[clip=$clip, enabled=$enabled, facialRecognition=$facialRecognition, url=$url]';
String toString() => 'SystemConfigMachineLearningDto[clip=$clip, duplicateDetection=$duplicateDetection, enabled=$enabled, facialRecognition=$facialRecognition, url=$url]';
Map<String, dynamic> toJson() {
final json = <String, dynamic>{};
json[r'clip'] = this.clip;
json[r'duplicateDetection'] = this.duplicateDetection;
json[r'enabled'] = this.enabled;
json[r'facialRecognition'] = this.facialRecognition;
json[r'url'] = this.url;
@ -63,6 +69,7 @@ class SystemConfigMachineLearningDto {
return SystemConfigMachineLearningDto(
clip: CLIPConfig.fromJson(json[r'clip'])!,
duplicateDetection: DuplicateDetectionConfig.fromJson(json[r'duplicateDetection'])!,
enabled: mapValueOfType<bool>(json, r'enabled')!,
facialRecognition: RecognitionConfig.fromJson(json[r'facialRecognition'])!,
url: mapValueOfType<String>(json, r'url')!,
@ -114,6 +121,7 @@ class SystemConfigMachineLearningDto {
/// The list of required keys that must be present in a JSON.
static const requiredKeys = <String>{
'clip',
'duplicateDetection',
'enabled',
'facialRecognition',
'url',