mirror of
https://github.com/nextcloud/server.git
synced 2026-04-29 18:11:41 -04:00
feat(TaskProcessing): add agency audio-to-audio task type
Signed-off-by: Julien Veyssier <julien-nc@posteo.net>
This commit is contained in:
parent
58a37108da
commit
2da3f450fa
5 changed files with 124 additions and 3 deletions
|
|
@ -844,6 +844,7 @@ return array(
|
|||
'OCP\\TaskProcessing\\Task' => $baseDir . '/lib/public/TaskProcessing/Task.php',
|
||||
'OCP\\TaskProcessing\\TaskTypes\\AudioToAudioChat' => $baseDir . '/lib/public/TaskProcessing/TaskTypes/AudioToAudioChat.php',
|
||||
'OCP\\TaskProcessing\\TaskTypes\\AudioToText' => $baseDir . '/lib/public/TaskProcessing/TaskTypes/AudioToText.php',
|
||||
'OCP\\TaskProcessing\\TaskTypes\\ContextAgentAudioInteraction' => $baseDir . '/lib/public/TaskProcessing/TaskTypes/ContextAgentAudioInteraction.php',
|
||||
'OCP\\TaskProcessing\\TaskTypes\\ContextAgentInteraction' => $baseDir . '/lib/public/TaskProcessing/TaskTypes/ContextAgentInteraction.php',
|
||||
'OCP\\TaskProcessing\\TaskTypes\\ContextWrite' => $baseDir . '/lib/public/TaskProcessing/TaskTypes/ContextWrite.php',
|
||||
'OCP\\TaskProcessing\\TaskTypes\\GenerateEmoji' => $baseDir . '/lib/public/TaskProcessing/TaskTypes/GenerateEmoji.php',
|
||||
|
|
|
|||
|
|
@ -885,6 +885,7 @@ class ComposerStaticInit749170dad3f5e7f9ca158f5a9f04f6a2
|
|||
'OCP\\TaskProcessing\\Task' => __DIR__ . '/../../..' . '/lib/public/TaskProcessing/Task.php',
|
||||
'OCP\\TaskProcessing\\TaskTypes\\AudioToAudioChat' => __DIR__ . '/../../..' . '/lib/public/TaskProcessing/TaskTypes/AudioToAudioChat.php',
|
||||
'OCP\\TaskProcessing\\TaskTypes\\AudioToText' => __DIR__ . '/../../..' . '/lib/public/TaskProcessing/TaskTypes/AudioToText.php',
|
||||
'OCP\\TaskProcessing\\TaskTypes\\ContextAgentAudioInteraction' => __DIR__ . '/../../..' . '/lib/public/TaskProcessing/TaskTypes/ContextAgentAudioInteraction.php',
|
||||
'OCP\\TaskProcessing\\TaskTypes\\ContextAgentInteraction' => __DIR__ . '/../../..' . '/lib/public/TaskProcessing/TaskTypes/ContextAgentInteraction.php',
|
||||
'OCP\\TaskProcessing\\TaskTypes\\ContextWrite' => __DIR__ . '/../../..' . '/lib/public/TaskProcessing/TaskTypes/ContextWrite.php',
|
||||
'OCP\\TaskProcessing\\TaskTypes\\GenerateEmoji' => __DIR__ . '/../../..' . '/lib/public/TaskProcessing/TaskTypes/GenerateEmoji.php',
|
||||
|
|
|
|||
|
|
@ -590,6 +590,7 @@ class Manager implements IManager {
|
|||
\OCP\TaskProcessing\TaskTypes\TextToTextProofread::ID => \OCP\Server::get(\OCP\TaskProcessing\TaskTypes\TextToTextProofread::class),
|
||||
\OCP\TaskProcessing\TaskTypes\TextToSpeech::ID => \OCP\Server::get(\OCP\TaskProcessing\TaskTypes\TextToSpeech::class),
|
||||
\OCP\TaskProcessing\TaskTypes\AudioToAudioChat::ID => \OCP\Server::get(\OCP\TaskProcessing\TaskTypes\AudioToAudioChat::class),
|
||||
\OCP\TaskProcessing\TaskTypes\ContextAgentAudioInteraction::ID => \OCP\Server::get(\OCP\TaskProcessing\TaskTypes\ContextAgentAudioInteraction::class),
|
||||
];
|
||||
|
||||
foreach ($context->getTaskProcessingTaskTypes() as $providerServiceRegistration) {
|
||||
|
|
|
|||
|
|
@ -16,7 +16,7 @@ use OCP\TaskProcessing\ITaskType;
|
|||
use OCP\TaskProcessing\ShapeDescriptor;
|
||||
|
||||
/**
|
||||
* This is the task processing task type for text chat
|
||||
* This is the task processing task type for audio chat
|
||||
* @since 32.0.0
|
||||
*/
|
||||
class AudioToAudioChat implements ITaskType {
|
||||
|
|
@ -75,12 +75,12 @@ class AudioToAudioChat implements ITaskType {
|
|||
),
|
||||
'input' => new ShapeDescriptor(
|
||||
$this->l->t('Chat voice message'),
|
||||
$this->l->t('Describe a task that you want the assistant to do or ask a question'),
|
||||
$this->l->t('Describe a task that you want the assistant to do or ask a question.'),
|
||||
EShapeType::Audio
|
||||
),
|
||||
'history' => new ShapeDescriptor(
|
||||
$this->l->t('Chat history'),
|
||||
$this->l->t('The history of chat messages before the current message, starting with a message by the user'),
|
||||
$this->l->t('The history of chat messages before the current message, starting with a message by the user.'),
|
||||
EShapeType::ListOfTexts
|
||||
)
|
||||
];
|
||||
|
|
|
|||
|
|
@ -0,0 +1,118 @@
|
|||
<?php
|
||||
|
||||
declare(strict_types=1);
|
||||
|
||||
/**
|
||||
* SPDX-FileCopyrightText: 2025 Nextcloud GmbH and Nextcloud contributors
|
||||
* SPDX-License-Identifier: AGPL-3.0-or-later
|
||||
*/
|
||||
|
||||
namespace OCP\TaskProcessing\TaskTypes;
|
||||
|
||||
use OCP\IL10N;
|
||||
use OCP\L10N\IFactory;
|
||||
use OCP\TaskProcessing\EShapeType;
|
||||
use OCP\TaskProcessing\ITaskType;
|
||||
use OCP\TaskProcessing\ShapeDescriptor;
|
||||
|
||||
/**
|
||||
* This is the task processing task type for Context Agent interaction
|
||||
* @since 32.0.0
|
||||
*/
|
||||
class ContextAgentAudioInteraction implements ITaskType {
|
||||
public const ID = 'core:contextagent:audio-interaction';
|
||||
|
||||
private IL10N $l;
|
||||
|
||||
/**
|
||||
* @param IFactory $l10nFactory
|
||||
* @since 32.0.0
|
||||
*/
|
||||
public function __construct(
|
||||
IFactory $l10nFactory,
|
||||
) {
|
||||
$this->l = $l10nFactory->get('lib');
|
||||
}
|
||||
|
||||
/**
|
||||
* @inheritDoc
|
||||
* @since 32.0.0
|
||||
*/
|
||||
public function getName(): string {
|
||||
return 'ContextAgent audio'; // We do not translate this
|
||||
}
|
||||
|
||||
/**
|
||||
* @inheritDoc
|
||||
* @since 32.0.0
|
||||
*/
|
||||
public function getDescription(): string {
|
||||
return $this->l->t('Chat by voice with an agent');
|
||||
}
|
||||
|
||||
/**
|
||||
* @return string
|
||||
* @since 32.0.0
|
||||
*/
|
||||
public function getId(): string {
|
||||
return self::ID;
|
||||
}
|
||||
|
||||
/**
|
||||
* @return ShapeDescriptor[]
|
||||
* @since 32.0.0
|
||||
*/
|
||||
public function getInputShape(): array {
|
||||
return [
|
||||
'input' => new ShapeDescriptor(
|
||||
$this->l->t('Chat voice message'),
|
||||
$this->l->t('Describe a task that you want the agent to do or ask a question.'),
|
||||
EShapeType::Audio
|
||||
),
|
||||
'confirmation' => new ShapeDescriptor(
|
||||
$this->l->t('Confirmation'),
|
||||
$this->l->t('Whether to confirm previously requested actions: 0 for denial and 1 for confirmation.'),
|
||||
EShapeType::Number
|
||||
),
|
||||
'conversation_token' => new ShapeDescriptor(
|
||||
$this->l->t('Conversation token'),
|
||||
$this->l->t('A token representing the conversation.'),
|
||||
EShapeType::Text
|
||||
),
|
||||
];
|
||||
}
|
||||
|
||||
/**
|
||||
* @return ShapeDescriptor[]
|
||||
* @since 32.0.0
|
||||
*/
|
||||
public function getOutputShape(): array {
|
||||
return [
|
||||
'input_transcript' => new ShapeDescriptor(
|
||||
$this->l->t('Input transcript'),
|
||||
$this->l->t('Transcription of the audio input'),
|
||||
EShapeType::Text,
|
||||
),
|
||||
'output' => new ShapeDescriptor(
|
||||
$this->l->t('Response voice message'),
|
||||
$this->l->t('The generated voice response as part of the conversation'),
|
||||
EShapeType::Audio
|
||||
),
|
||||
'output_transcript' => new ShapeDescriptor(
|
||||
$this->l->t('Output transcript'),
|
||||
$this->l->t('Transcription of the audio output'),
|
||||
EShapeType::Text,
|
||||
),
|
||||
'conversation_token' => new ShapeDescriptor(
|
||||
$this->l->t('The new conversation token'),
|
||||
$this->l->t('Send this along with the next interaction.'),
|
||||
EShapeType::Text
|
||||
),
|
||||
'actions' => new ShapeDescriptor(
|
||||
$this->l->t('Requested actions by the agent'),
|
||||
$this->l->t('Actions that the agent would like to carry out in JSON format.'),
|
||||
EShapeType::Text
|
||||
),
|
||||
];
|
||||
}
|
||||
}
|
||||
Loading…
Reference in a new issue