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>
120 lines
2.7 KiB
TypeScript
120 lines
2.7 KiB
TypeScript
import { connectionMongo, getMongoModel } from '../../../common/mongo';
|
|
const { Schema, model, models } = connectionMongo;
|
|
import { type DatasetDataSchemaType } from '@fastgpt/global/core/dataset/type.d';
|
|
import {
|
|
TeamCollectionName,
|
|
TeamMemberCollectionName
|
|
} from '@fastgpt/global/support/user/team/constant';
|
|
import { DatasetCollectionName } from '../schema';
|
|
import { DatasetColCollectionName } from '../collection/schema';
|
|
import { DatasetDataIndexTypeEnum } from '@fastgpt/global/core/dataset/data/constants';
|
|
|
|
export const DatasetDataCollectionName = 'dataset_datas';
|
|
|
|
const DatasetDataSchema = new Schema({
|
|
teamId: {
|
|
type: Schema.Types.ObjectId,
|
|
ref: TeamCollectionName,
|
|
required: true
|
|
},
|
|
tmbId: {
|
|
type: Schema.Types.ObjectId,
|
|
ref: TeamMemberCollectionName,
|
|
required: true
|
|
},
|
|
datasetId: {
|
|
type: Schema.Types.ObjectId,
|
|
ref: DatasetCollectionName,
|
|
required: true
|
|
},
|
|
collectionId: {
|
|
type: Schema.Types.ObjectId,
|
|
ref: DatasetColCollectionName,
|
|
required: true
|
|
},
|
|
q: {
|
|
type: String,
|
|
required: true
|
|
},
|
|
a: {
|
|
type: String
|
|
},
|
|
history: {
|
|
type: [
|
|
{
|
|
q: String,
|
|
a: String,
|
|
updateTime: Date
|
|
}
|
|
]
|
|
},
|
|
indexes: {
|
|
type: [
|
|
{
|
|
// Abandon
|
|
defaultIndex: {
|
|
type: Boolean
|
|
},
|
|
type: {
|
|
type: String,
|
|
enum: Object.values(DatasetDataIndexTypeEnum),
|
|
default: DatasetDataIndexTypeEnum.custom
|
|
},
|
|
dataId: {
|
|
type: String,
|
|
required: true
|
|
},
|
|
text: {
|
|
type: String,
|
|
required: true
|
|
}
|
|
}
|
|
],
|
|
default: []
|
|
},
|
|
|
|
imageId: {
|
|
type: String
|
|
},
|
|
updateTime: {
|
|
type: Date,
|
|
default: () => new Date()
|
|
},
|
|
chunkIndex: {
|
|
type: Number,
|
|
default: 0
|
|
},
|
|
rebuilding: Boolean,
|
|
|
|
// Abandon
|
|
fullTextToken: String,
|
|
initFullText: Boolean,
|
|
initJieba: Boolean
|
|
});
|
|
|
|
try {
|
|
// list collection and count data; list data; delete collection(relate data)
|
|
DatasetDataSchema.index({
|
|
teamId: 1,
|
|
datasetId: 1,
|
|
collectionId: 1,
|
|
chunkIndex: 1,
|
|
updateTime: -1
|
|
});
|
|
// Recall vectors after data matching
|
|
DatasetDataSchema.index({ teamId: 1, datasetId: 1, collectionId: 1, 'indexes.dataId': 1 });
|
|
DatasetDataSchema.index({ updateTime: 1 });
|
|
// rebuild data
|
|
DatasetDataSchema.index({ rebuilding: 1, teamId: 1, datasetId: 1 });
|
|
|
|
// 为查询 initJieba 字段不存在的数据添加索引
|
|
DatasetDataSchema.index({ initJieba: 1, updateTime: 1 });
|
|
} catch (error) {
|
|
console.log(error);
|
|
}
|
|
|
|
export const MongoDatasetData = getMongoModel<DatasetDataSchemaType>(
|
|
DatasetDataCollectionName,
|
|
DatasetDataSchema
|
|
);
|