mirror of
https://github.com/labring/FastGPT.git
synced 2025-07-23 13:03:50 +00:00

* Feat: Images dataset collection (#4941) * New pic (#4858) * 更新数据集相关类型,添加图像文件ID和预览URL支持;优化数据集导入功能,新增图像数据集处理组件;修复部分国际化文本;更新文件上传逻辑以支持新功能。 * 与原先代码的差别 * 新增 V4.9.10 更新说明,支持 PG 设置`systemEnv.hnswMaxScanTuples`参数,优化 LLM stream 调用超时,修复全文检索多知识库排序问题。同时更新数据集索引,移除 datasetId 字段以简化查询。 * 更换成fileId_image逻辑,并增加训练队列匹配的逻辑 * 新增图片集合判断逻辑,优化预览URL生成流程,确保仅在数据集为图片集合时生成预览URL,并添加相关日志输出以便调试。 * Refactor Docker Compose configuration to comment out exposed ports for production environments, update image versions for pgvector, fastgpt, and mcp_server, and enhance Redis service with a health check. Additionally, standardize dataset collection labels in constants and improve internationalization strings across multiple languages. * Enhance TrainingStates component by adding internationalization support for the imageParse training mode and update defaultCounts to include imageParse mode in trainingDetail API. * Enhance dataset import context by adding additional steps for image dataset import process and improve internationalization strings for modal buttons in the useEditTitle hook. * Update DatasetImportContext to conditionally render MyStep component based on data source type, improving the import process for non-image datasets. * Refactor image dataset handling by improving internationalization strings, enhancing error messages, and streamlining the preview URL generation process. * 图片上传到新建的 dataset_collection_images 表,逻辑跟随更改 * 修改了除了controller的其他部分问题 * 把图片数据集的逻辑整合到controller里面 * 补充i18n * 补充i18n * resolve评论:主要是上传逻辑的更改和组件复用 * 图片名称的图标显示 * 修改编译报错的命名问题 * 删除不需要的collectionid部分 * 多余文件的处理和改动一个删除按钮 * 除了loading和统一的imageId,其他都resolve掉的 * 处理图标报错 * 复用了MyPhotoView并采用全部替换的方式将imageFileId变成imageId * 去除不必要文件修改 * 报错和字段修改 * 增加上传成功后删除临时文件的逻辑以及回退一些修改 * 删除path字段,将图片保存到gridfs内,并修改增删等操作的代码 * 修正编译错误 --------- Co-authored-by: archer <545436317@qq.com> * perf: image dataset * feat: insert image * perf: image icon * fix: training state --------- Co-authored-by: Zhuangzai fa <143257420+ctrlz526@users.noreply.github.com> * fix: ts (#4948) * Thirddatasetmd (#4942) * add thirddataset.md * fix thirddataset.md * fix * delete wrong png --------- Co-authored-by: dreamer6680 <146868355@qq.com> * perf: api dataset code * perf: log * add secondary.tsx (#4946) * add secondary.tsx * fix --------- Co-authored-by: dreamer6680 <146868355@qq.com> * perf: multiple menu * perf: i18n * feat: parse queue (#4960) * feat: parse queue * feat: sync parse queue * fix thirddataset.md (#4962) * fix thirddataset-4.png (#4963) * feat: Dataset template import (#4934) * 模版导入部分除了文档还没写 * 修复模版导入的 build 错误 * Document production * compress pictures * Change some constants to variables --------- Co-authored-by: Archer <545436317@qq.com> * perf: template import * doc * llm pargraph * bocha tool * fix: del collection --------- Co-authored-by: Zhuangzai fa <143257420+ctrlz526@users.noreply.github.com> Co-authored-by: dreamer6680 <1468683855@qq.com> Co-authored-by: dreamer6680 <146868355@qq.com>
167 lines
4.4 KiB
TypeScript
167 lines
4.4 KiB
TypeScript
import { addMinutes } from 'date-fns';
|
|
import { bucketName, MongoDatasetImageSchema } from './schema';
|
|
import { connectionMongo, Types } from '../../../common/mongo';
|
|
import fs from 'fs';
|
|
import type { FileType } from '../../../common/file/multer';
|
|
import fsp from 'fs/promises';
|
|
import { computeGridFsChunSize } from '../../../common/file/gridfs/utils';
|
|
import { setCron } from '../../../common/system/cron';
|
|
import { checkTimerLock } from '../../../common/system/timerLock/utils';
|
|
import { TimerIdEnum } from '../../../common/system/timerLock/constants';
|
|
import { addLog } from '../../../common/system/log';
|
|
|
|
const getGridBucket = () => {
|
|
return new connectionMongo.mongo.GridFSBucket(connectionMongo.connection.db!, {
|
|
bucketName: bucketName
|
|
});
|
|
};
|
|
|
|
export const createDatasetImage = async ({
|
|
teamId,
|
|
datasetId,
|
|
file,
|
|
expiredTime = addMinutes(new Date(), 30)
|
|
}: {
|
|
teamId: string;
|
|
datasetId: string;
|
|
file: FileType;
|
|
expiredTime?: Date;
|
|
}): Promise<{ imageId: string; previewUrl: string }> => {
|
|
const path = file.path;
|
|
const gridBucket = getGridBucket();
|
|
const metadata = {
|
|
teamId: String(teamId),
|
|
datasetId: String(datasetId),
|
|
expiredTime
|
|
};
|
|
|
|
const stats = await fsp.stat(path);
|
|
if (!stats.isFile()) return Promise.reject(`${path} is not a file`);
|
|
|
|
const readStream = fs.createReadStream(path, {
|
|
highWaterMark: 256 * 1024
|
|
});
|
|
const chunkSizeBytes = computeGridFsChunSize(stats.size);
|
|
|
|
const stream = gridBucket.openUploadStream(file.originalname, {
|
|
metadata,
|
|
contentType: file.mimetype,
|
|
chunkSizeBytes
|
|
});
|
|
|
|
// save to gridfs
|
|
await new Promise((resolve, reject) => {
|
|
readStream
|
|
.pipe(stream as any)
|
|
.on('finish', resolve)
|
|
.on('error', reject);
|
|
});
|
|
|
|
return {
|
|
imageId: String(stream.id),
|
|
previewUrl: ''
|
|
};
|
|
};
|
|
|
|
export const getDatasetImageReadData = async (imageId: string) => {
|
|
// Get file metadata to get contentType
|
|
const fileInfo = await MongoDatasetImageSchema.findOne({
|
|
_id: new Types.ObjectId(imageId)
|
|
}).lean();
|
|
if (!fileInfo) {
|
|
return Promise.reject('Image not found');
|
|
}
|
|
|
|
const gridBucket = getGridBucket();
|
|
return {
|
|
stream: gridBucket.openDownloadStream(new Types.ObjectId(imageId)),
|
|
fileInfo
|
|
};
|
|
};
|
|
export const getDatasetImageBase64 = async (imageId: string) => {
|
|
// Get file metadata to get contentType
|
|
const fileInfo = await MongoDatasetImageSchema.findOne({
|
|
_id: new Types.ObjectId(imageId)
|
|
}).lean();
|
|
if (!fileInfo) {
|
|
return Promise.reject('Image not found');
|
|
}
|
|
|
|
// Get image stream from GridFS
|
|
const { stream } = await getDatasetImageReadData(imageId);
|
|
|
|
// Convert stream to buffer
|
|
const chunks: Buffer[] = [];
|
|
|
|
return new Promise<string>((resolve, reject) => {
|
|
stream.on('data', (chunk: Buffer) => {
|
|
chunks.push(chunk);
|
|
});
|
|
|
|
stream.on('end', () => {
|
|
// Combine all chunks into a single buffer
|
|
const buffer = Buffer.concat(chunks);
|
|
// Convert buffer to base64 string
|
|
const base64 = buffer.toString('base64');
|
|
const dataUrl = `data:${fileInfo.contentType || 'image/jpeg'};base64,${base64}`;
|
|
resolve(dataUrl);
|
|
});
|
|
|
|
stream.on('error', reject);
|
|
});
|
|
};
|
|
|
|
export const deleteDatasetImage = async (imageId: string) => {
|
|
const gridBucket = getGridBucket();
|
|
|
|
try {
|
|
await gridBucket.delete(new Types.ObjectId(imageId));
|
|
} catch (error: any) {
|
|
const msg = error?.message;
|
|
if (msg.includes('File not found')) {
|
|
addLog.warn('Delete dataset image error', error);
|
|
return;
|
|
} else {
|
|
return Promise.reject(error);
|
|
}
|
|
}
|
|
};
|
|
|
|
export const clearExpiredDatasetImageCron = async () => {
|
|
const gridBucket = getGridBucket();
|
|
const clearExpiredDatasetImages = async () => {
|
|
addLog.debug('Clear expired dataset image start');
|
|
|
|
const data = await MongoDatasetImageSchema.find(
|
|
{
|
|
'metadata.expiredTime': { $lt: new Date() }
|
|
},
|
|
'_id'
|
|
).lean();
|
|
|
|
for (const item of data) {
|
|
try {
|
|
await gridBucket.delete(item._id);
|
|
} catch (error) {
|
|
addLog.error('Delete expired dataset image error', error);
|
|
}
|
|
}
|
|
addLog.debug('Clear expired dataset image end');
|
|
};
|
|
|
|
setCron('*/10 * * * *', async () => {
|
|
if (
|
|
await checkTimerLock({
|
|
timerId: TimerIdEnum.clearExpiredDatasetImage,
|
|
lockMinuted: 9
|
|
})
|
|
) {
|
|
try {
|
|
await clearExpiredDatasetImages();
|
|
} catch (error) {
|
|
addLog.error('clearExpiredDatasetImageCron error', error);
|
|
}
|
|
}
|
|
});
|
|
};
|