dify/web/service/knowledge/use-create-dataset.ts
Wu Tianwei 2b2263a349
Feat/parent child retrieval (#12086)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: AkaraChen <akarachen@outlook.com>
Co-authored-by: nite-knite <nkCoding@gmail.com>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: Warren Chen <warren.chen830@gmail.com>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: Yi Xiao <54782454+YIXIAO0@users.noreply.github.com>
Co-authored-by: yihong <zouzou0208@gmail.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: KVOJJJin <jzongcode@gmail.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: JzoNgKVO <27049666+JzoNgKVO@users.noreply.github.com>
Co-authored-by: Charlie.Wei <luowei@cvte.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: huayaoyue6 <huayaoyue@163.com>
Co-authored-by: kurokobo <kuro664@gmail.com>
Co-authored-by: Matsuda <yiyth.fcb6@gmail.com>
Co-authored-by: shirochan <s.yusuke0711@gmail.com>
Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com>
Co-authored-by: Huỳnh Gia Bôi <boihuynh147@gmail.com>
Co-authored-by: Julian Huynh <julian.huynh@immersio.io>
Co-authored-by: Hash Brown <hi@xzd.me>
Co-authored-by: 非法操作 <hjlarry@163.com>
Co-authored-by: Kazuki Takamatsu <kazuki.takamatsu@chowagiken.co.jp>
Co-authored-by: Trey Dong <1346650911@qq.com>
Co-authored-by: VoidIsVoid <343750470@qq.com>
Co-authored-by: Gimling <huangjl@ruyi.ai>
Co-authored-by: xiandan-erizo <xiandan.erizo@gmail.com>
Co-authored-by: Muneyuki Noguchi <nogu.dev@gmail.com>
Co-authored-by: zhaobingshuang <1475195565@qq.com>
Co-authored-by: zhaobs <zhaobs@cailian.net>
Co-authored-by: suzuki.sh <s2terminal@users.noreply.github.com>
Co-authored-by: Yingchun Lai <laiyingchun@apache.org>
Co-authored-by: huanshare <huanshare@live.com>
Co-authored-by: huanshare <liuhuan101@longfor.com>
Co-authored-by: orangeclk <orangeclk@users.noreply.github.com>
Co-authored-by: 문정현 <120004247+JungHyunMoon@users.noreply.github.com>
Co-authored-by: barabicu <kztk533@gmail.com>
Co-authored-by: Wei Mingzhi <whistler_wmz@users.sf.net>
Co-authored-by: Paul van Oorschot <20116814+pvoo@users.noreply.github.com>
Co-authored-by: zkyTech <zhangkunyuan@hotmail.com>
Co-authored-by: zhangkunyuan <zhangkunyuan@cmhi.chinamobile.com>
Co-authored-by: Tommy <34446820+Asterovim@users.noreply.github.com>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: Novice <857526207@qq.com>
Co-authored-by: Novice Lee <novicelee@NovicedeMacBook-Pro.local>
Co-authored-by: Novice Lee <novicelee@NoviPro.local>
Co-authored-by: zxhlyh <16177003+zxhlyh@users.noreply.github.com>
Co-authored-by: liuzhenghua <1090179900@qq.com>
Co-authored-by: Jiang <65766008+AlwaysBluer@users.noreply.github.com>
Co-authored-by: jiangzhijie <jiangzhijie.jzj@alibaba-inc.com>
Co-authored-by: Joe <79627742+ZhouhaoJiang@users.noreply.github.com>
Co-authored-by: Alok Shrivastwa <alok.shrivastwa@gmail.com>
Co-authored-by: Alok Shrivastwa <Alok.Shrivastwa@microland.com>
Co-authored-by: JasonVV <jasonwangiii@outlook.com>
Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com>
Co-authored-by: Kevin9703 <51311316+Kevin9703@users.noreply.github.com>
Co-authored-by: NFish <douxc512@gmail.com>
Co-authored-by: Junyan Qin <1010553892@qq.com>
Co-authored-by: IWAI, Masaharu <iwaim.sub@gmail.com>
Co-authored-by: IWAI, Masaharu <iwai_masaharu@funkit.co.jp>
Co-authored-by: Bowen Liang <liangbowen@gf.com.cn>
Co-authored-by: luckylhb90 <luckylhb90@gmail.com>
Co-authored-by: hobo.l <hobo.l@binance.com>
Co-authored-by: douxc <7553076+douxc@users.noreply.github.com>
2024-12-25 18:17:15 +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,
})
}