mirror of
https://github.com/labring/FastGPT.git
synced 2025-07-29 01:40:51 +00:00

* feat: org CRUD (#3380) * feat: add org schema * feat: org manage UI * feat: OrgInfoModal * feat: org tree view * feat: org management * fix: init root org * feat: org permission for app * feat: org support for dataset * fix: disable org role control * styles: opt type signatures * fix: remove unused permission * feat: delete org collaborator * perf: Team org ui (#3499) * perf: org ui * perf: org ui * feat: org auth for app & dataset (#3498) * feat: auth org resource permission * feat: org auth support for app & dataset * perf: org permission check (#3500) * i18n (#3501) * name * i18n * feat: support dataset changeOwner (#3483) * feat: support dataset changeOwner * chore: update dataset change owner api * feat: permission manage UI for org (#3503) * perf: password check;perf: image upload check;perf: sso login check (#3509) * perf: password check * perf: image upload check * perf: sso login check * force show update notification modal & fix login page text (#3512) * fix login page English text * update notification modal * perf: notify account (#3515) * perf(plugin): improve searXNG empty result handling and documentation (#3507) * perf(plugin): improve searXNG empty result handling and documentation * 修改了文档和代码部分无搜索的结果的反馈 * refactor: org pathId (#3516) * optimize payment process (#3517) * feat: support wecom sso (#3518) * feat: support wecom sso * chore: remove unused wecom js-sdk dependency * fix qrcode script (#3520) * fix qrcode script * i18n * perf: full text collection and search code;perf: rename function (#3519) * perf: full text collection and search code * perf: rename function * perf: notify modal * remove invalid code * perf: sso login * perf: pay process * 4.8.18 test (#3524) * perf: remove local token * perf: index * perf: file encoding;perf: leave team code;@c121914yu perf: full text search code (#3528) * perf: text encoding * perf: leave team code * perf: full text search code * fix: http status * perf: embedding search and vector avatar * perf: async read file (#3531) * refactor: team permission manager (#3535) * perf: classify org, group and member * refactor: team per manager * fix: missing functions * 4.8.18 test (#3543) * perf: login check * doc * perf: llm model config * perf: team clb config * fix: MemberModal UI (#3553) * fix: adapt MemberModal title and icon * fix: adapt member modal * fix: search input placeholder * fix: add button text * perf: org permission (#3556) * docs:用户答疑的官方文档补充 (#3540) * docs:用户答疑的官方文档补充 * 问题回答的内容修补 * share link random avatar (#3541) * share link random avatar * fix * delete unused code * share page avatar (#3558) * feat: init 4818 * share page avatar * feat: tmp upgrade code (#3559) * feat: tmp upgrade code * fulltext search test * update action * full text tmp code (#3561) * full text tmp code * fix: init * fix: init * remove tmp code * remove tmp code * 4818-alpha * 4.8.18 test (#3562) * full text tmp code * fix: init * upgrade code * account log * account log * perf: dockerfile * upgrade code * chore: update docs app template submission (#3564) --------- Co-authored-by: a.e. <49438478+I-Info@users.noreply.github.com> Co-authored-by: Finley Ge <32237950+FinleyGe@users.noreply.github.com> Co-authored-by: heheer <heheer@sealos.io> Co-authored-by: Jiangween <145003935+Jiangween@users.noreply.github.com>
256 lines
6.2 KiB
TypeScript
256 lines
6.2 KiB
TypeScript
import { Types, connectionMongo, ReadPreference } from '../../mongo';
|
|
import { BucketNameEnum } from '@fastgpt/global/common/file/constants';
|
|
import fsp from 'fs/promises';
|
|
import fs from 'fs';
|
|
import { DatasetFileSchema } from '@fastgpt/global/core/dataset/type';
|
|
import { MongoChatFileSchema, MongoDatasetFileSchema } from './schema';
|
|
import { detectFileEncoding, detectFileEncodingByPath } from '@fastgpt/global/common/file/tools';
|
|
import { CommonErrEnum } from '@fastgpt/global/common/error/code/common';
|
|
import { MongoRawTextBuffer } from '../../buffer/rawText/schema';
|
|
import { readRawContentByFileBuffer } from '../read/utils';
|
|
import { gridFsStream2Buffer, stream2Encoding } from './utils';
|
|
import { addLog } from '../../system/log';
|
|
import { readFromSecondary } from '../../mongo/utils';
|
|
import { parseFileExtensionFromUrl } from '@fastgpt/global/common/string/tools';
|
|
import { Readable } from 'stream';
|
|
|
|
export function getGFSCollection(bucket: `${BucketNameEnum}`) {
|
|
MongoDatasetFileSchema;
|
|
MongoChatFileSchema;
|
|
|
|
return connectionMongo.connection.db.collection(`${bucket}.files`);
|
|
}
|
|
export function getGridBucket(bucket: `${BucketNameEnum}`) {
|
|
return new connectionMongo.mongo.GridFSBucket(connectionMongo.connection.db, {
|
|
bucketName: bucket,
|
|
// @ts-ignore
|
|
readPreference: ReadPreference.SECONDARY_PREFERRED // Read from secondary node
|
|
});
|
|
}
|
|
|
|
/* crud file */
|
|
export async function uploadFile({
|
|
bucketName,
|
|
teamId,
|
|
uid,
|
|
path,
|
|
filename,
|
|
contentType,
|
|
metadata = {}
|
|
}: {
|
|
bucketName: `${BucketNameEnum}`;
|
|
teamId: string;
|
|
uid: string; // tmbId / outLinkUId
|
|
path: string;
|
|
filename: string;
|
|
contentType?: string;
|
|
metadata?: Record<string, any>;
|
|
}) {
|
|
if (!path) return Promise.reject(`filePath is empty`);
|
|
if (!filename) return Promise.reject(`filename is empty`);
|
|
|
|
const stats = await fsp.stat(path);
|
|
if (!stats.isFile()) return Promise.reject(`${path} is not a file`);
|
|
|
|
const readStream = fs.createReadStream(path);
|
|
|
|
// Add default metadata
|
|
metadata.teamId = teamId;
|
|
metadata.uid = uid;
|
|
metadata.encoding = await detectFileEncodingByPath(path);
|
|
|
|
// create a gridfs bucket
|
|
const bucket = getGridBucket(bucketName);
|
|
|
|
const stream = bucket.openUploadStream(filename, {
|
|
metadata,
|
|
contentType
|
|
});
|
|
|
|
// save to gridfs
|
|
await new Promise((resolve, reject) => {
|
|
readStream
|
|
.pipe(stream as any)
|
|
.on('finish', resolve)
|
|
.on('error', reject);
|
|
});
|
|
|
|
return String(stream.id);
|
|
}
|
|
export async function uploadFileFromBase64Img({
|
|
bucketName,
|
|
teamId,
|
|
tmbId,
|
|
base64,
|
|
filename,
|
|
metadata = {}
|
|
}: {
|
|
bucketName: `${BucketNameEnum}`;
|
|
teamId: string;
|
|
tmbId: string;
|
|
base64: string;
|
|
filename: string;
|
|
metadata?: Record<string, any>;
|
|
}) {
|
|
if (!base64) return Promise.reject(`filePath is empty`);
|
|
if (!filename) return Promise.reject(`filename is empty`);
|
|
|
|
const base64Data = base64.split(',')[1];
|
|
const contentType = base64.split(',')?.[0]?.split?.(':')?.[1];
|
|
const buffer = Buffer.from(base64Data, 'base64');
|
|
const readableStream = new Readable({
|
|
read() {
|
|
this.push(buffer);
|
|
this.push(null);
|
|
}
|
|
});
|
|
|
|
const { stream: readStream, encoding } = await stream2Encoding(readableStream);
|
|
|
|
// Add default metadata
|
|
metadata.teamId = teamId;
|
|
metadata.tmbId = tmbId;
|
|
metadata.encoding = encoding;
|
|
|
|
// create a gridfs bucket
|
|
const bucket = getGridBucket(bucketName);
|
|
|
|
const stream = bucket.openUploadStream(filename, {
|
|
metadata,
|
|
contentType
|
|
});
|
|
|
|
// save to gridfs
|
|
await new Promise((resolve, reject) => {
|
|
readStream
|
|
.pipe(stream as any)
|
|
.on('finish', resolve)
|
|
.on('error', reject);
|
|
});
|
|
|
|
return String(stream.id);
|
|
}
|
|
|
|
export async function getFileById({
|
|
bucketName,
|
|
fileId
|
|
}: {
|
|
bucketName: `${BucketNameEnum}`;
|
|
fileId: string;
|
|
}) {
|
|
const db = getGFSCollection(bucketName);
|
|
const file = await db.findOne<DatasetFileSchema>({
|
|
_id: new Types.ObjectId(fileId)
|
|
});
|
|
|
|
// if (!file) {
|
|
// return Promise.reject('File not found');
|
|
// }
|
|
|
|
return file || undefined;
|
|
}
|
|
|
|
export async function delFileByFileIdList({
|
|
bucketName,
|
|
fileIdList,
|
|
retry = 3
|
|
}: {
|
|
bucketName: `${BucketNameEnum}`;
|
|
fileIdList: string[];
|
|
retry?: number;
|
|
}): Promise<any> {
|
|
try {
|
|
const bucket = getGridBucket(bucketName);
|
|
|
|
for await (const fileId of fileIdList) {
|
|
await bucket.delete(new Types.ObjectId(fileId));
|
|
}
|
|
} catch (error) {
|
|
if (retry > 0) {
|
|
return delFileByFileIdList({ bucketName, fileIdList, retry: retry - 1 });
|
|
}
|
|
}
|
|
}
|
|
|
|
export async function getDownloadStream({
|
|
bucketName,
|
|
fileId
|
|
}: {
|
|
bucketName: `${BucketNameEnum}`;
|
|
fileId: string;
|
|
}) {
|
|
const bucket = getGridBucket(bucketName);
|
|
|
|
return bucket.openDownloadStream(new Types.ObjectId(fileId));
|
|
}
|
|
|
|
export const readFileContentFromMongo = async ({
|
|
teamId,
|
|
bucketName,
|
|
fileId,
|
|
isQAImport = false
|
|
}: {
|
|
teamId: string;
|
|
bucketName: `${BucketNameEnum}`;
|
|
fileId: string;
|
|
isQAImport?: boolean;
|
|
}): Promise<{
|
|
rawText: string;
|
|
filename: string;
|
|
}> => {
|
|
// read buffer
|
|
const fileBuffer = await MongoRawTextBuffer.findOne({ sourceId: fileId }, undefined, {
|
|
...readFromSecondary
|
|
}).lean();
|
|
if (fileBuffer) {
|
|
return {
|
|
rawText: fileBuffer.rawText,
|
|
filename: fileBuffer.metadata?.filename || ''
|
|
};
|
|
}
|
|
|
|
const [file, fileStream] = await Promise.all([
|
|
getFileById({ bucketName, fileId }),
|
|
getDownloadStream({ bucketName, fileId })
|
|
]);
|
|
if (!file) {
|
|
return Promise.reject(CommonErrEnum.fileNotFound);
|
|
}
|
|
|
|
const extension = parseFileExtensionFromUrl(file?.filename);
|
|
|
|
const start = Date.now();
|
|
const fileBuffers = await gridFsStream2Buffer(fileStream);
|
|
addLog.debug('get file buffer', { time: Date.now() - start });
|
|
|
|
const encoding = file?.metadata?.encoding || detectFileEncoding(fileBuffers);
|
|
|
|
// Get raw text
|
|
const { rawText } = await readRawContentByFileBuffer({
|
|
extension,
|
|
isQAImport,
|
|
teamId,
|
|
buffer: fileBuffers,
|
|
encoding,
|
|
metadata: {
|
|
relatedId: fileId
|
|
}
|
|
});
|
|
|
|
// < 14M
|
|
if (fileBuffers.length < 14 * 1024 * 1024 && rawText.trim()) {
|
|
MongoRawTextBuffer.create({
|
|
sourceId: fileId,
|
|
rawText,
|
|
metadata: {
|
|
filename: file.filename
|
|
}
|
|
});
|
|
}
|
|
|
|
return {
|
|
rawText,
|
|
filename: file.filename
|
|
};
|
|
};
|