mirror of
https://github.com/labring/FastGPT.git
synced 2025-10-17 16:45:02 +00:00

* perf: introduce BullMQ for website sync (#4403) * perf: introduce BullMQ for website sync * feat: new redis module * fix: remove graceful shutdown * perf: improve UI in dataset detail - Updated the "change" icon SVG file. - Modified i18n strings. - Added new i18n string "immediate_sync". - Improved UI in dataset detail page, including button icons and background colors. * refactor: Add chunkSettings to DatasetSchema * perf: website sync ux * env template * fix: clean up website dataset when updating chunk settings (#4420) * perf: check setting updated * perf: worker currency * feat: init script for website sync refactor (#4425) * website feature doc --------- Co-authored-by: a.e. <49438478+I-Info@users.noreply.github.com>
81 lines
2.3 KiB
TypeScript
81 lines
2.3 KiB
TypeScript
import { Processor } from 'bullmq';
|
|
import { getQueue, getWorker, QueueNames } from '../../../common/bullmq';
|
|
import { DatasetStatusEnum } from '@fastgpt/global/core/dataset/constants';
|
|
|
|
export type WebsiteSyncJobData = {
|
|
datasetId: string;
|
|
};
|
|
|
|
export const websiteSyncQueue = getQueue<WebsiteSyncJobData>(QueueNames.websiteSync, {
|
|
defaultJobOptions: {
|
|
attempts: 3, // retry 3 times
|
|
backoff: {
|
|
type: 'exponential',
|
|
delay: 1000 // delay 1 second between retries
|
|
}
|
|
}
|
|
});
|
|
export const getWebsiteSyncWorker = (processor: Processor<WebsiteSyncJobData>) => {
|
|
return getWorker<WebsiteSyncJobData>(QueueNames.websiteSync, processor, {
|
|
removeOnFail: {
|
|
age: 15 * 24 * 60 * 60, // Keep up to 15 days
|
|
count: 1000 // Keep up to 1000 jobs
|
|
},
|
|
concurrency: 1 // Set worker to process only 1 job at a time
|
|
});
|
|
};
|
|
|
|
export const addWebsiteSyncJob = (data: WebsiteSyncJobData) => {
|
|
const datasetId = String(data.datasetId);
|
|
// deduplication: make sure only 1 job
|
|
return websiteSyncQueue.add(datasetId, data, { deduplication: { id: datasetId } });
|
|
};
|
|
|
|
export const getWebsiteSyncDatasetStatus = async (datasetId: string) => {
|
|
const jobId = await websiteSyncQueue.getDeduplicationJobId(datasetId);
|
|
if (!jobId) {
|
|
return DatasetStatusEnum.active;
|
|
}
|
|
const job = await websiteSyncQueue.getJob(jobId);
|
|
if (!job) {
|
|
return DatasetStatusEnum.active;
|
|
}
|
|
|
|
const jobState = await job.getState();
|
|
|
|
if (['waiting-children', 'waiting'].includes(jobState)) {
|
|
return DatasetStatusEnum.waiting;
|
|
}
|
|
if (jobState === 'active') {
|
|
return DatasetStatusEnum.syncing;
|
|
}
|
|
|
|
return DatasetStatusEnum.active;
|
|
};
|
|
|
|
// Scheduler setting
|
|
const repeatDuration = 24 * 60 * 60 * 1000; // every day
|
|
export const upsertWebsiteSyncJobScheduler = (data: WebsiteSyncJobData, startDate?: number) => {
|
|
const datasetId = String(data.datasetId);
|
|
|
|
return websiteSyncQueue.upsertJobScheduler(
|
|
datasetId,
|
|
{
|
|
every: repeatDuration,
|
|
startDate: startDate || new Date().getTime() + repeatDuration // First run tomorrow
|
|
},
|
|
{
|
|
name: datasetId,
|
|
data
|
|
}
|
|
);
|
|
};
|
|
|
|
export const getWebsiteSyncJobScheduler = (datasetId: string) => {
|
|
return websiteSyncQueue.getJobScheduler(String(datasetId));
|
|
};
|
|
|
|
export const removeWebsiteSyncJobScheduler = (datasetId: string) => {
|
|
return websiteSyncQueue.removeJobScheduler(String(datasetId));
|
|
};
|