Files
dify/web/service/knowledge/use-create-dataset.ts
Yeuoly 899df30bf6 Plugin/merge main to plugin/beta 20250122 (#12962)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: kurokobo <kuro664@gmail.com>
Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com>
Co-authored-by: NFish <douxc512@gmail.com>
Co-authored-by: Gen Sato <52241300+halogen22@users.noreply.github.com>
Co-authored-by: eux <euxuuu@gmail.com>
Co-authored-by: huangzhuo1949 <167434202+huangzhuo1949@users.noreply.github.com>
Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com>
Co-authored-by: lotsik <lotsik@mail.ru>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com>
Co-authored-by: nite-knite <nkCoding@gmail.com>
Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: gakkiyomi <gakkiyomi@aliyun.com>
Co-authored-by: CN-P5 <heibai2006@gmail.com>
Co-authored-by: CN-P5 <heibai2006@qq.com>
Co-authored-by: Chuehnone <1897025+chuehnone@users.noreply.github.com>
Co-authored-by: yihong <zouzou0208@gmail.com>
Co-authored-by: Kevin9703 <51311316+Kevin9703@users.noreply.github.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: Boris Feld <lothiraldan@gmail.com>
Co-authored-by: mbo <himabo@gmail.com>
Co-authored-by: mabo <mabo@aeyes.ai>
Co-authored-by: Warren Chen <warren.chen830@gmail.com>
Co-authored-by: KVOJJJin <jzongcode@gmail.com>
Co-authored-by: JzoNgKVO <27049666+JzoNgKVO@users.noreply.github.com>
Co-authored-by: jiandanfeng <chenjh3@wangsu.com>
Co-authored-by: zhu-an <70234959+xhdd123321@users.noreply.github.com>
Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com>
Co-authored-by: 海狸大師 <86974027+yenslife@users.noreply.github.com>
Co-authored-by: Xu Song <xusong.vip@gmail.com>
Co-authored-by: rayshaw001 <396301947@163.com>
Co-authored-by: Ding Jiatong <dingjiatong@gmail.com>
Co-authored-by: Bowen Liang <liangbowen@gf.com.cn>
Co-authored-by: JasonVV <jasonwangiii@outlook.com>
Co-authored-by: le0zh <newlight@qq.com>
Co-authored-by: zhuxinliang <zhuxinliang@didiglobal.com>
Co-authored-by: k-zaku <zaku99@outlook.jp>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: luckylhb90 <luckylhb90@gmail.com>
Co-authored-by: hobo.l <hobo.l@binance.com>
Co-authored-by: jiangbo721 <365065261@qq.com>
Co-authored-by: 刘江波 <jiangbo721@163.com>
Co-authored-by: Shun Miyazawa <34241526+miya@users.noreply.github.com>
Co-authored-by: EricPan <30651140+Egfly@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: sino <sino2322@gmail.com>
Co-authored-by: Jhvcc <37662342+Jhvcc@users.noreply.github.com>
Co-authored-by: lowell <lowell.hu@zkteco.in>
2025-01-23 14:48:16 +08:00

224 lines
6.1 KiB
TypeScript

import groupBy from 'lodash-es/groupBy'
import type { MutationOptions } from '@tanstack/react-query'
import { useMutation } from '@tanstack/react-query'
import { createDocument, createFirstDocument, fetchDefaultProcessRule, fetchFileIndexingEstimate } from '../datasets'
import type { IndexingType } from '@/app/components/datasets/create/step-two'
import type { ChunkingMode, CrawlOptions, CrawlResultItem, CreateDocumentReq, CustomFile, DataSourceType, FileIndexingEstimateResponse, IndexingEstimateParams, NotionInfo, ProcessRule, ProcessRuleResponse, createDocumentResponse } from '@/models/datasets'
import type { DataSourceProvider, NotionPage } from '@/models/common'
export const getNotionInfo = (
notionPages: NotionPage[],
) => {
const workspacesMap = groupBy(notionPages, 'workspace_id')
const workspaces = Object.keys(workspacesMap).map((workspaceId) => {
return {
workspaceId,
pages: workspacesMap[workspaceId],
}
})
return workspaces.map((workspace) => {
return {
workspace_id: workspace.workspaceId,
pages: workspace.pages.map((page) => {
const { page_id, page_name, page_icon, type } = page
return {
page_id,
page_name,
page_icon,
type,
}
}),
}
}) as NotionInfo[]
}
export const getWebsiteInfo = (
opts: {
websiteCrawlProvider: DataSourceProvider
websiteCrawlJobId: string
websitePages: CrawlResultItem[]
crawlOptions?: CrawlOptions
},
) => {
const { websiteCrawlProvider, websiteCrawlJobId, websitePages, crawlOptions } = opts
return {
provider: websiteCrawlProvider,
job_id: websiteCrawlJobId,
urls: websitePages.map(page => page.source_url),
only_main_content: crawlOptions?.only_main_content,
}
}
type GetFileIndexingEstimateParamsOptionBase = {
docForm: ChunkingMode
docLanguage: string
indexingTechnique: IndexingType
processRule: ProcessRule
dataset_id: string
}
type GetFileIndexingEstimateParamsOptionFile = GetFileIndexingEstimateParamsOptionBase & {
dataSourceType: DataSourceType.FILE
files: CustomFile[]
}
const getFileIndexingEstimateParamsForFile = ({
docForm,
docLanguage,
dataSourceType,
files,
indexingTechnique,
processRule,
dataset_id,
}: GetFileIndexingEstimateParamsOptionFile): IndexingEstimateParams => {
return {
info_list: {
data_source_type: dataSourceType,
file_info_list: {
file_ids: files.map(file => file.id) as string[],
},
},
indexing_technique: indexingTechnique,
process_rule: processRule,
doc_form: docForm,
doc_language: docLanguage,
dataset_id,
}
}
export const useFetchFileIndexingEstimateForFile = (
options: GetFileIndexingEstimateParamsOptionFile,
mutationOptions: MutationOptions<FileIndexingEstimateResponse> = {},
) => {
return useMutation({
mutationFn: async () => {
return fetchFileIndexingEstimate(getFileIndexingEstimateParamsForFile(options))
},
...mutationOptions,
})
}
type GetFileIndexingEstimateParamsOptionNotion = GetFileIndexingEstimateParamsOptionBase & {
dataSourceType: DataSourceType.NOTION
notionPages: NotionPage[]
}
const getFileIndexingEstimateParamsForNotion = ({
docForm,
docLanguage,
dataSourceType,
notionPages,
indexingTechnique,
processRule,
dataset_id,
}: GetFileIndexingEstimateParamsOptionNotion): IndexingEstimateParams => {
return {
info_list: {
data_source_type: dataSourceType,
notion_info_list: getNotionInfo(notionPages),
},
indexing_technique: indexingTechnique,
process_rule: processRule,
doc_form: docForm,
doc_language: docLanguage,
dataset_id,
}
}
export const useFetchFileIndexingEstimateForNotion = (
options: GetFileIndexingEstimateParamsOptionNotion,
mutationOptions: MutationOptions<FileIndexingEstimateResponse> = {},
) => {
return useMutation({
mutationFn: async () => {
return fetchFileIndexingEstimate(getFileIndexingEstimateParamsForNotion(options))
},
...mutationOptions,
})
}
type GetFileIndexingEstimateParamsOptionWeb = GetFileIndexingEstimateParamsOptionBase & {
dataSourceType: DataSourceType.WEB
websitePages: CrawlResultItem[]
crawlOptions?: CrawlOptions
websiteCrawlProvider: DataSourceProvider
websiteCrawlJobId: string
}
const getFileIndexingEstimateParamsForWeb = ({
docForm,
docLanguage,
dataSourceType,
websitePages,
crawlOptions,
websiteCrawlProvider,
websiteCrawlJobId,
indexingTechnique,
processRule,
dataset_id,
}: GetFileIndexingEstimateParamsOptionWeb): IndexingEstimateParams => {
return {
info_list: {
data_source_type: dataSourceType,
website_info_list: getWebsiteInfo({
websiteCrawlProvider,
websiteCrawlJobId,
websitePages,
crawlOptions,
}),
},
indexing_technique: indexingTechnique,
process_rule: processRule,
doc_form: docForm,
doc_language: docLanguage,
dataset_id,
}
}
export const useFetchFileIndexingEstimateForWeb = (
options: GetFileIndexingEstimateParamsOptionWeb,
mutationOptions: MutationOptions<FileIndexingEstimateResponse> = {},
) => {
return useMutation({
mutationFn: async () => {
return fetchFileIndexingEstimate(getFileIndexingEstimateParamsForWeb(options))
},
...mutationOptions,
})
}
export const useCreateFirstDocument = (
mutationOptions: MutationOptions<createDocumentResponse, Error, CreateDocumentReq> = {},
) => {
return useMutation({
mutationFn: async (createDocumentReq: CreateDocumentReq,
) => {
return createFirstDocument({ body: createDocumentReq })
},
...mutationOptions,
})
}
export const useCreateDocument = (
datasetId: string,
mutationOptions: MutationOptions<createDocumentResponse, Error, CreateDocumentReq> = {},
) => {
return useMutation({
mutationFn: async (req: CreateDocumentReq) => {
return createDocument({ datasetId, body: req })
},
...mutationOptions,
})
}
export const useFetchDefaultProcessRule = (
mutationOptions: MutationOptions<ProcessRuleResponse, Error, string> = {},
) => {
return useMutation({
mutationFn: async (url: string) => {
return fetchDefaultProcessRule({ url })
},
...mutationOptions,
})
}