Skip to content

feat: Implement AI Watermarking #5206

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
marcelklehr wants to merge 1 commit into
base: main
Choose a base branch
from
+29 −12
Open

feat: Implement AI Watermarking #5206

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions lib/Service/DocumentGenerationService.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@
use OCA\Richdocuments\AppInfo\Application;
use OCA\Richdocuments\TaskProcessing\TextToDocumentProvider;
use OCA\Richdocuments\TaskProcessing\TextToSpreadsheetProvider;
use OCP\IL10N;
use OCP\TaskProcessing\Exception\Exception;
use OCP\TaskProcessing\Exception\PreConditionNotMetException;
use OCP\TaskProcessing\Exception\UnauthorizedException;
Expand Down Expand Up @@ -37,15 +38,17 @@ class DocumentGenerationService {
public function __construct(
private IManager $taskProcessingManager,
private RemoteService $remoteService,
private IL10N $l10n,
) {
}

public function generateTextDocument(?string $userId, string $description, string $targetFormat = TextToDocumentProvider::DEFAULT_TARGET_FORMAT) {
public function generateTextDocument(?string $userId, string $description, string $targetFormat = TextToDocumentProvider::DEFAULT_TARGET_FORMAT, bool $includeWatermark = true) {
$prompt = self::TEXT_PROMPT;
$taskInput = $prompt . "\n\n" . $description;
$markdownContent = $this->runTextToTextTask($taskInput, $userId);
$converter = new GithubFlavoredMarkdownConverter();
$htmlContent = $converter->convert($markdownContent)->getContent();
$markdownContentWithAiNote = $includeWatermark ? $markdownContent . "\n\n" . $this->l10n->t('This document was generated using Artificial Intelligence') : $markdownContent;
$htmlContent = $converter->convert($markdownContentWithAiNote)->getContent();
$htmlStream = $this->stringToStream($htmlContent);
$docxContent = $this->remoteService->convertTo('document.html', $htmlStream, $targetFormat);

Expand Down
18 changes: 15 additions & 3 deletions lib/Service/SlideDeckService.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@
use OCA\Richdocuments\TaskProcessing\Presentation\Slides\TitleSlide;
use OCA\Richdocuments\TemplateManager;
use OCP\IConfig;
use OCP\IL10N;
use OCP\TaskProcessing\Exception\Exception;
use OCP\TaskProcessing\Exception\PreConditionNotMetException;
use OCP\TaskProcessing\Exception\UnauthorizedException;
Expand Down Expand Up @@ -70,17 +71,18 @@ public function __construct(
private TemplateManager $templateManager,
private RemoteService $remoteService,
private IConfig $config,
private IL10N $l10n,
) {
}

public function generateSlideDeck(?string $userId, string $presentationText) {
public function generateSlideDeck(?string $userId, string $presentationText, bool $includeWatermark = true) {
$rawModelOutput = $this->runLLMQuery($userId, $presentationText);

$ooxml = $this->config->getAppValue(Application::APPNAME, 'doc_format', 'ooxml') === 'ooxml';
$format = $ooxml ? 'pptx' : 'odp';

try {
[$presentationStyle, $parsedStructure] = $this->parseModelJSON($rawModelOutput);
[$presentationStyle, $parsedStructure] = $this->parseModelJSON($rawModelOutput, $includeWatermark);
} catch (\JsonException) {
throw new RuntimeException('LLM generated faulty JSON data');
}
Expand Down Expand Up @@ -108,7 +110,7 @@ public function generateSlideDeck(?string $userId, string $presentationText) {
* @param string $jsonString
* @return array
*/
private function parseModelJSON(string $jsonString): array {
private function parseModelJSON(string $jsonString, bool $includeWatermark = true): array {
$jsonString = trim($jsonString, "` \n\r\t\v\0");
$modelJSON = json_decode(
$jsonString,
Expand Down Expand Up @@ -148,9 +150,19 @@ private function parseModelJSON(string $jsonString): array {
$presentation->addSlide($slide);
}

if ($includeWatermark) {
// Add a final slide with a note that this was generated by AI
$this->addAiComment(isset($index) ? $index + 1 : 0, $presentation);
}

return [$presentation->getStyle(), $presentation->getSlideCommands()];
}

private function addAiComment(int $index, Presentation $presentation) : void {
$slide = new TitleContentSlide($index, '', $this->l10n->t('Generated using Artificial Intelligence'));
$presentation->addSlide($slide);
}

/**
* Creates a presentation file in memory
*
Expand Down
9 changes: 5 additions & 4 deletions lib/TaskProcessing/SlideDeckGenerationProvider.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,9 +11,9 @@
use OCA\Richdocuments\AppInfo\Application;
use OCA\Richdocuments\Service\SlideDeckService;
use OCP\IL10N;
use OCP\TaskProcessing\ISynchronousProvider;
use OCP\TaskProcessing\ISynchronousWatermarkingProvider;

class SlideDeckGenerationProvider implements ISynchronousProvider {
class SlideDeckGenerationProvider implements ISynchronousWatermarkingProvider {

public function __construct(
private SlideDeckService $slideDeckService,
Expand Down Expand Up @@ -71,7 +71,7 @@ public function getOptionalOutputShapeEnumValues(): array {
/**
* @inheritDoc
*/
public function process(?string $userId, array $input, callable $reportProgress): array {
public function process(?string $userId, array $input, callable $reportProgress, bool $includeWatermark = true): array {
if ($userId === null) {
throw new \RuntimeException('User ID is required to process the prompt.');
}
Expand All @@ -80,10 +80,11 @@ public function process(?string $userId, array $input, callable $reportProgress)
throw new \RuntimeException('Invalid input, expected "text" key with string value');
}

$response = $this->withRetry(function () use ($userId, $input) {
$response = $this->withRetry(function () use ($userId, $input, $includeWatermark) {
return $this->slideDeckService->generateSlideDeck(
$userId,
$input['text'],
$includeWatermark,
);
});

Expand Down
7 changes: 4 additions & 3 deletions lib/TaskProcessing/TextToDocumentProvider.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,11 +12,11 @@
use OCA\Richdocuments\Service\DocumentGenerationService;
use OCP\IL10N;
use OCP\TaskProcessing\EShapeType;
use OCP\TaskProcessing\ISynchronousProvider;
use OCP\TaskProcessing\ISynchronousWatermarkingProvider;
use OCP\TaskProcessing\ShapeDescriptor;
use OCP\TaskProcessing\ShapeEnumValue;

class TextToDocumentProvider implements ISynchronousProvider {
class TextToDocumentProvider implements ISynchronousWatermarkingProvider {
public const DEFAULT_TARGET_FORMAT = 'docx';

public function __construct(
Expand Down Expand Up @@ -89,7 +89,7 @@ public function getOptionalOutputShapeEnumValues(): array {
/**
* @inheritDoc
*/
public function process(?string $userId, array $input, callable $reportProgress): array {
public function process(?string $userId, array $input, callable $reportProgress, bool $includeWatermark = true): array {
if ($userId === null) {
throw new \RuntimeException('User ID is required to process the prompt.');
}
Expand All @@ -108,6 +108,7 @@ public function process(?string $userId, array $input, callable $reportProgress)
$userId,
$input['text'],
$targetFormat,
$includeWatermark
);

return [
Expand Down
Loading