Files
ragflow/web/src/hooks/use-knowledge-request.ts

715 lines
18 KiB
TypeScript
Raw Normal View History

import { useHandleFilterSubmit } from '@/components/list-filter-bar/use-handle-filter-submit';
import message from '@/components/ui/message';
import { ParseType } from '@/constants/knowledge';
import { ResponsePostType } from '@/interfaces/database/base';
import {
IDataset,
IDatasetListResult,
IKnowledgeGraph,
INextTestingResult,
IRenameTag,
ITestingResult,
} from '@/interfaces/database/dataset';
import { ITestRetrievalRequestBody } from '@/interfaces/request/knowledge';
import i18n from '@/locales/config';
import kbService, {
deleteKnowledgeGraph,
feat(api): add unified index API and dataset management endpoints (#14222) ### What problem does this PR solve? ## Summary Refactor the dataset API layer into a clean service/REST separation pattern, add a unified `/index` API for graph/raptor/mindmap operations, and introduce several new dataset management endpoints with full test coverage. ## Changes ### Service Layer (`dataset_api_service.py`) - Added `trace_index(dataset_id, tenant_id, index_type)` — unified trace function for all index types - Added `run_index`, `delete_index` service functions - Added `get_dataset`, `get_ingestion_summary`, `list_ingestion_logs`, `get_ingestion_log` - Added `run_embedding`, `list_tags`, `aggregate_tags`, `delete_tags`, `rename_tag` - Added `get_flattened_metadata`, `get_auto_metadata`, `update_auto_metadata` ### REST API Layer (`dataset_api.py`) **New unified routes:** | Method | Route | Description | |--------|-------|-------------| | POST | `/datasets/<id>/index?type=graph\|raptor\|mindmap` | Run index task | | GET | `/datasets/<id>/index?type=graph\|raptor\|mindmap` | Trace index task | | DELETE | `/datasets/<id>/<index_type>` | Delete index | | GET | `/datasets/<id>` | Get dataset details | | GET | `/datasets/<id>/ingestions/summary` | Ingestion summary | | GET | `/datasets/<id>/ingestions` | List ingestion logs | | GET | `/datasets/<id>/ingestions/<log_id>` | Get single ingestion log | | POST | `/datasets/<id>/embedding` | Run embedding | | GET | `/datasets/<id>/tags` | List tags | | GET | `/datasets/tags/aggregation` | Aggregate tags across datasets | | DELETE | `/datasets/<id>/tags` | Delete tags | | PUT | `/datasets/<id>/tags` | Rename tag | | GET | `/datasets/metadata/flattened` | Get flattened metadata | | GET/PUT | `/datasets/<id>/metadata/config` | New metadata config path | **Removed routes (replaced by unified `/index`):** - `POST /datasets/<id>/mindmap` - `GET /datasets/<id>/mindmap` **Preserved legacy routes (backward compatibility):** - `/run_graphrag`, `/trace_graphrag`, `/run_raptor`, `/trace_raptor` - `/auto_metadata` GET/PUT ### Test Suite - Updated `common.py` helpers: added `trace_index`, removed `run_mindmap`/`trace_mindmap` - Added 7 new test files with 39 test cases total: | Test File | Cases | |-----------|-------| | `test_get_dataset.py` | 4 | | `test_ingestion_summary.py` | 2 | | `test_ingestion_logs.py` | 5 | | `test_index_api.py` | 14 | | `test_embedding.py` | 2 | | `test_tags.py` | 8 | | `test_flattened_metadata.py` | 4 | - Deleted `test_mindmap_tasks.py` (covered by unified index tests) ## Design Decisions 1. **Unified `/index?type=...`** — single endpoint replaces 3 separate route pairs for graph/raptor/mindmap 2. **Backward compatibility** — old routes (`/run_graphrag`, `/run_raptor`, `/auto_metadata`) preserved alongside new paths 3. **`_VALID_INDEX_TYPES = {"graph", "raptor", "mindmap"}`** — input validation via constant set 4. **`_INDEX_TYPE_TO_TASK_ID_FIELD`** — maps index type to KB model task ID field for clean dispatch ## Files Changed - `api/apps/restful_apis/dataset_api.py` - `api/apps/services/dataset_api_service.py` - `sdk/python/ragflow_sdk/modules/dataset.py` - `test/testcases/test_http_api/common.py` - `test/testcases/test_http_api/test_dataset_management/` (7 new files) ### Type of change - [x] New Feature (non-breaking change which adds functionality) - [x] Refactoring --------- Signed-off-by: noob <yixiao121314@outlook.com>
2026-04-27 01:38:01 +00:00
getKbDetail,
getKnowledgeGraph,
listDataset,
listTag,
removeTag,
renameTag,
updateKb,
} from '@/services/knowledge-service';
import {
useIsMutating,
useMutation,
useMutationState,
useQuery,
useQueryClient,
} from '@tanstack/react-query';
import { useDebounce } from 'ahooks';
import { omit } from 'lodash';
import { useCallback, useMemo, useState } from 'react';
import { useParams, useSearchParams } from 'react-router';
import {
useGetPaginationWithRouter,
useHandleSearchChange,
} from './logic-hooks';
import { extractParserConfigExt } from './parser-config-utils';
import { useSetPaginationParams } from './route-hook';
export const enum KnowledgeApiAction {
FetchKnowledgeListByPage = 'fetchKnowledgeListByPage',
CreateKnowledge = 'createKnowledge',
DeleteKnowledge = 'deleteKnowledge',
SaveKnowledge = 'saveKnowledge',
FetchKnowledgeDetail = 'fetchKnowledgeDetail',
FetchKnowledgeGraph = 'fetchKnowledgeGraph',
FetchMetadata = 'fetchMetadata',
Feat/configurable metadata display (#13464) ### What problem does this PR solve? Currently, RAGFlow's Search and Chat interfaces display only raw vectorized text chunks during retrieval, without contextual information about their source documents. Users cannot see document titles, page numbers, upload dates, or custom metadata fields that would help them understand and trust the retrieved results. This PR introduces an **optional metadata display feature** that enriches retrieved chunks with document-level metadata in both the Search tab and Chatbot interface. **Key improvements:** - **Search results**: Display document metadata as styled badges beneath chunk snippets - **Chat citations**: Show metadata in citation popovers and reference lists for better source context - **LLM context**: Metadata is injected into the LLM prompt to enable more accurate, citation-aware responses - **External API support**: Applications using RAGFlow's SDK retrieval endpoints (`/v1/retrieval`, `/v1/searchbots/retrieval_test`) can opt-in via request parameters - **User control**: Multi-select dropdown UI allows users to choose which metadata fields to display **Implementation approach:** - ✅ Reuses existing `DocMetadataService` infrastructure (no new database tables or indices) - ✅ Settings stored in existing JSON configuration fields (`search_config.reference_metadata`, `prompt_config.reference_metadata`) - ✅ No database migrations required - ✅ Disabled by default (fully opt-in and backward-compatible) - ✅ Dynamic metadata field selection populated from actual document metadata keys - ✅ Fixed critical bug where Python's builtin `set()` was shadowed by a route handler function **Modified endpoints (all backward-compatible):** - `POST /v1/retrieval` (Public SDK) - `POST /v1/searchbots/retrieval_test` (Searchbots) - `POST /v1/chunk/retrieval_test` (UI/Internal) - Chat completions endpoints (via `extra_body.reference_metadata` or `prompt_config`) ### Type of change - [x] New Feature (non-breaking change which adds functionality) ###Images - <img width="879" height="1275" alt="image" src="https://github.com/user-attachments/assets/95b2d731-31ae-45a1-b081-bf5893f52aeb" /> <br><br> <br><br> <img width="1532" height="362" alt="image" src="https://github.com/user-attachments/assets/9cebc65b-b7a7-459f-b25e-3b13fa9b638e" /> <br><br> <br><br> <img width="2586" height="1320" alt="image" src="https://github.com/user-attachments/assets/2153d493-d899-461f-a7a9-041391e07776" /> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Attili-sys <Attili-sys@users.noreply.github.com> Co-authored-by: Ahmad Intisar <ahmadintisar@Ahmads-MacBook-M4-Pro.local>
2026-04-30 18:13:27 +03:00
FetchMetadataKeys = 'fetchMetadataKeys',
Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423) ### What problem does this PR solve? #9869 ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: jinhai <haijin.chn@gmail.com> Signed-off-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: chanx <1243304602@qq.com> Co-authored-by: balibabu <cike8899@users.noreply.github.com> Co-authored-by: Lynn <lynn_inf@hotmail.com> Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com> Co-authored-by: huangzl <huangzl@shinemo.com> Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com> Co-authored-by: Wilmer <33392318@qq.com> Co-authored-by: Adrian Weidig <adrianweidig@gmx.net> Co-authored-by: Zhichang Yu <yuzhichang@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Yongteng Lei <yongtengrey@outlook.com> Co-authored-by: Liu An <asiro@qq.com> Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com> Co-authored-by: BadwomanCraZY <511528396@qq.com> Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com> Co-authored-by: Russell Valentine <russ@coldstonelabs.org> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Billy Bao <newyorkupperbay@gmail.com> Co-authored-by: Zhedong Cen <cenzhedong2@126.com> Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com> Co-authored-by: TensorNull <tensor.null@gmail.com> Co-authored-by: TeslaZY <TeslaZY@outlook.com> Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com> Co-authored-by: AB <aj@Ajays-MacBook-Air.local> Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com> Co-authored-by: He Wang <wanghechn@qq.com> Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com> Co-authored-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com> Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box> Co-authored-by: Stephen Hu <stephenhu@seismic.com> Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com> Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com> Co-authored-by: mxc <mxc@example.com> Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com> Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com> Co-authored-by: mcoder6425 <mcoder64@gmail.com> Co-authored-by: lemsn <lemsn@msn.com> Co-authored-by: lemsn <lemsn@126.com> Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com> Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com> Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>
2025-10-09 12:36:19 +08:00
FetchKnowledgeList = 'fetchKnowledgeList',
RemoveKnowledgeGraph = 'removeKnowledgeGraph',
}
export const useKnowledgeBaseId = (): string => {
const { id } = useParams();
return (id as string) || '';
};
export const useTestRetrieval = () => {
const knowledgeBaseId = useKnowledgeBaseId();
const [values, setValues] = useState<ITestRetrievalRequestBody>();
const { filterValue, setFilterValue } = useHandleFilterSubmit();
const [page, setPage] = useState(1);
const [pageSize, setPageSize] = useState(10);
const queryParams = useMemo(() => {
return {
...values,
kb_id: values?.kb_id || knowledgeBaseId,
page,
size: pageSize,
doc_ids: filterValue.doc_ids,
highlight: true,
};
}, [filterValue, knowledgeBaseId, page, pageSize, values]);
const mutation = useMutation<INextTestingResult, Error, typeof queryParams>({
mutationFn: async (params) => {
const { data } = await kbService.retrievalTest(params);
const result = data?.data ?? {};
return { ...result, isRuned: true };
},
});
const refetch = useCallback(() => {
if (queryParams.question) {
mutation.mutate(queryParams);
}
}, [mutation, queryParams]);
const onPaginationChange = useCallback(
(newPage: number, newPageSize: number) => {
setPage(newPage);
setPageSize(newPageSize);
if (mutation.data && queryParams.question) {
const newParams = { ...queryParams, page: newPage, size: newPageSize };
mutation.mutate(newParams);
}
},
[mutation, queryParams],
);
const handleFilterSubmit = useCallback(
(value: { doc_ids?: string[] }) => {
setFilterValue(value);
setPage(1);
if (mutation.data && queryParams.question) {
const newParams = {
...queryParams,
doc_ids: value.doc_ids ?? [],
page: 1,
};
mutation.mutate(newParams);
}
},
[mutation, queryParams, setFilterValue],
);
const data = useMemo(
() =>
mutation.data ?? {
chunks: [],
doc_aggs: [],
total: 0,
isRuned: false,
},
[mutation.data],
);
return {
data,
loading: mutation.isPending,
setValues,
refetch,
onPaginationChange,
page,
pageSize,
handleFilterSubmit,
filterValue,
};
};
export const useFetchNextKnowledgeListByPage = () => {
const { searchString, handleInputChange } = useHandleSearchChange();
const { pagination, setPagination } = useGetPaginationWithRouter();
const debouncedSearchString = useDebounce(searchString, { wait: 500 });
const { filterValue, handleFilterSubmit } = useHandleFilterSubmit();
const { data, isFetching: loading } = useQuery<IDatasetListResult>({
queryKey: [
KnowledgeApiAction.FetchKnowledgeListByPage,
{
debouncedSearchString,
...pagination,
filterValue,
},
],
initialData: {
kbs: [],
total_datasets: 0,
},
gcTime: 0,
queryFn: async () => {
const { data } = await listDataset({
page_size: pagination.pageSize,
page: pagination.current,
ext: {
keywords: debouncedSearchString,
owner_ids: filterValue.owner as string[],
},
});
return { kbs: data?.data, total_datasets: data?.total_datasets };
},
});
const onInputChange: React.ChangeEventHandler<HTMLInputElement> = useCallback(
(e) => {
// setPagination({ page: 1 }); // TODO: This results in repeated requests
handleInputChange(e);
},
[handleInputChange],
);
return {
...data,
searchString,
handleInputChange: onInputChange,
pagination: { ...pagination, total: data?.total_datasets },
setPagination,
loading,
filterValue,
handleFilterSubmit,
};
};
export const useCreateKnowledge = () => {
const queryClient = useQueryClient();
const {
data,
isPending: loading,
mutateAsync,
} = useMutation({
mutationKey: [KnowledgeApiAction.CreateKnowledge],
mutationFn: async (params: {
id?: string;
name: string;
embedding_model?: string;
chunk_method?: string;
parseType?: ParseType;
pipeline_id?: string | null;
ext?: {
language?: string;
[key: string]: any;
};
}) => {
const { data = {} } = await kbService.createKb(params);
if (data.code === 0) {
message.success(
i18n.t(`message.${params?.id ? 'modified' : 'created'}`),
);
queryClient.invalidateQueries({ queryKey: ['fetchKnowledgeList'] });
}
return data;
},
});
return { data, loading, createKnowledge: mutateAsync };
};
export const useDeleteKnowledge = () => {
const queryClient = useQueryClient();
const {
data,
isPending: loading,
mutateAsync,
} = useMutation({
mutationKey: [KnowledgeApiAction.DeleteKnowledge],
mutationFn: async (id: string) => {
const { data } = await kbService.rmKb({ ids: [id] });
if (data.code === 0) {
message.success(i18n.t(`message.deleted`));
queryClient.invalidateQueries({
queryKey: [KnowledgeApiAction.FetchKnowledgeListByPage],
});
}
return data?.data ?? [];
},
});
return { data, loading, deleteKnowledge: mutateAsync };
};
export const useUpdateKnowledge = (shouldFetchList = false) => {
const knowledgeBaseId = useKnowledgeBaseId();
const queryClient = useQueryClient();
const {
data,
isPending: loading,
mutateAsync,
} = useMutation({
mutationKey: [KnowledgeApiAction.SaveKnowledge],
mutationFn: async (params: {
kb_id?: string;
name?: string;
embedding_model?: string;
chunk_method?: string;
pipeline_id?: string | null;
avatar?: string | null;
description?: string;
permission?: string;
pagerank?: number;
parser_config?: Record<string, any>;
[key: string]: any;
}) => {
const kbId = params?.kb_id || knowledgeBaseId;
const {
embedding_model,
chunk_method,
pipeline_id,
avatar,
description,
permission,
pagerank,
parser_config,
...ext
} = params;
const requestBody: Record<string, any> = {
name,
embedding_model,
chunk_method,
pipeline_id,
avatar,
description,
permission,
pagerank,
parser_config: extractParserConfigExt(parser_config),
...omit(ext, ['kb_id']),
};
const { data = {} } = await updateKb(kbId, requestBody);
if (data.code === 0) {
message.success(i18n.t(`message.updated`));
if (shouldFetchList) {
queryClient.invalidateQueries({
queryKey: [KnowledgeApiAction.FetchKnowledgeListByPage],
});
} else {
queryClient.invalidateQueries({ queryKey: ['fetchKnowledgeDetail'] });
}
}
return data;
},
});
return { data, loading, saveKnowledgeConfiguration: mutateAsync };
};
Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423) ### What problem does this PR solve? #9869 ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: jinhai <haijin.chn@gmail.com> Signed-off-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: chanx <1243304602@qq.com> Co-authored-by: balibabu <cike8899@users.noreply.github.com> Co-authored-by: Lynn <lynn_inf@hotmail.com> Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com> Co-authored-by: huangzl <huangzl@shinemo.com> Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com> Co-authored-by: Wilmer <33392318@qq.com> Co-authored-by: Adrian Weidig <adrianweidig@gmx.net> Co-authored-by: Zhichang Yu <yuzhichang@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Yongteng Lei <yongtengrey@outlook.com> Co-authored-by: Liu An <asiro@qq.com> Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com> Co-authored-by: BadwomanCraZY <511528396@qq.com> Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com> Co-authored-by: Russell Valentine <russ@coldstonelabs.org> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Billy Bao <newyorkupperbay@gmail.com> Co-authored-by: Zhedong Cen <cenzhedong2@126.com> Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com> Co-authored-by: TensorNull <tensor.null@gmail.com> Co-authored-by: TeslaZY <TeslaZY@outlook.com> Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com> Co-authored-by: AB <aj@Ajays-MacBook-Air.local> Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com> Co-authored-by: He Wang <wanghechn@qq.com> Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com> Co-authored-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com> Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box> Co-authored-by: Stephen Hu <stephenhu@seismic.com> Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com> Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com> Co-authored-by: mxc <mxc@example.com> Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com> Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com> Co-authored-by: mcoder6425 <mcoder64@gmail.com> Co-authored-by: lemsn <lemsn@msn.com> Co-authored-by: lemsn <lemsn@126.com> Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com> Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com> Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>
2025-10-09 12:36:19 +08:00
export const useFetchKnowledgeBaseConfiguration = (props?: {
isEdit?: boolean;
}) => {
const { isEdit = true } = props || { isEdit: true };
const { id } = useParams();
const [searchParams] = useSearchParams();
const knowledgeBaseId = searchParams.get('id') || id;
const { data, isFetching: loading } = useQuery<IDataset>({
queryKey: [KnowledgeApiAction.FetchKnowledgeDetail, knowledgeBaseId],
initialData: {} as IDataset,
gcTime: 0,
enabled: !!knowledgeBaseId && isEdit,
queryFn: async () => {
feat(api): add unified index API and dataset management endpoints (#14222) ### What problem does this PR solve? ## Summary Refactor the dataset API layer into a clean service/REST separation pattern, add a unified `/index` API for graph/raptor/mindmap operations, and introduce several new dataset management endpoints with full test coverage. ## Changes ### Service Layer (`dataset_api_service.py`) - Added `trace_index(dataset_id, tenant_id, index_type)` — unified trace function for all index types - Added `run_index`, `delete_index` service functions - Added `get_dataset`, `get_ingestion_summary`, `list_ingestion_logs`, `get_ingestion_log` - Added `run_embedding`, `list_tags`, `aggregate_tags`, `delete_tags`, `rename_tag` - Added `get_flattened_metadata`, `get_auto_metadata`, `update_auto_metadata` ### REST API Layer (`dataset_api.py`) **New unified routes:** | Method | Route | Description | |--------|-------|-------------| | POST | `/datasets/<id>/index?type=graph\|raptor\|mindmap` | Run index task | | GET | `/datasets/<id>/index?type=graph\|raptor\|mindmap` | Trace index task | | DELETE | `/datasets/<id>/<index_type>` | Delete index | | GET | `/datasets/<id>` | Get dataset details | | GET | `/datasets/<id>/ingestions/summary` | Ingestion summary | | GET | `/datasets/<id>/ingestions` | List ingestion logs | | GET | `/datasets/<id>/ingestions/<log_id>` | Get single ingestion log | | POST | `/datasets/<id>/embedding` | Run embedding | | GET | `/datasets/<id>/tags` | List tags | | GET | `/datasets/tags/aggregation` | Aggregate tags across datasets | | DELETE | `/datasets/<id>/tags` | Delete tags | | PUT | `/datasets/<id>/tags` | Rename tag | | GET | `/datasets/metadata/flattened` | Get flattened metadata | | GET/PUT | `/datasets/<id>/metadata/config` | New metadata config path | **Removed routes (replaced by unified `/index`):** - `POST /datasets/<id>/mindmap` - `GET /datasets/<id>/mindmap` **Preserved legacy routes (backward compatibility):** - `/run_graphrag`, `/trace_graphrag`, `/run_raptor`, `/trace_raptor` - `/auto_metadata` GET/PUT ### Test Suite - Updated `common.py` helpers: added `trace_index`, removed `run_mindmap`/`trace_mindmap` - Added 7 new test files with 39 test cases total: | Test File | Cases | |-----------|-------| | `test_get_dataset.py` | 4 | | `test_ingestion_summary.py` | 2 | | `test_ingestion_logs.py` | 5 | | `test_index_api.py` | 14 | | `test_embedding.py` | 2 | | `test_tags.py` | 8 | | `test_flattened_metadata.py` | 4 | - Deleted `test_mindmap_tasks.py` (covered by unified index tests) ## Design Decisions 1. **Unified `/index?type=...`** — single endpoint replaces 3 separate route pairs for graph/raptor/mindmap 2. **Backward compatibility** — old routes (`/run_graphrag`, `/run_raptor`, `/auto_metadata`) preserved alongside new paths 3. **`_VALID_INDEX_TYPES = {"graph", "raptor", "mindmap"}`** — input validation via constant set 4. **`_INDEX_TYPE_TO_TASK_ID_FIELD`** — maps index type to KB model task ID field for clean dispatch ## Files Changed - `api/apps/restful_apis/dataset_api.py` - `api/apps/services/dataset_api_service.py` - `sdk/python/ragflow_sdk/modules/dataset.py` - `test/testcases/test_http_api/common.py` - `test/testcases/test_http_api/test_dataset_management/` (7 new files) ### Type of change - [x] New Feature (non-breaking change which adds functionality) - [x] Refactoring --------- Signed-off-by: noob <yixiao121314@outlook.com>
2026-04-27 01:38:01 +00:00
const { data } = await getKbDetail(knowledgeBaseId || '');
return data?.data ?? {};
},
});
return { data, loading };
};
export function useFetchKnowledgeGraph() {
const knowledgeBaseId = useKnowledgeBaseId();
const { data, isFetching: loading } = useQuery<IKnowledgeGraph>({
queryKey: [KnowledgeApiAction.FetchKnowledgeGraph, knowledgeBaseId],
initialData: { graph: {}, mind_map: {} } as IKnowledgeGraph,
enabled: !!knowledgeBaseId,
gcTime: 0,
queryFn: async () => {
const { data } = await getKnowledgeGraph(knowledgeBaseId);
return data?.data;
},
});
return { data, loading };
}
export function useFetchKnowledgeMetadata(kbIds: string[] = []) {
const { data, isFetching: loading } = useQuery<
Record<string, Record<string, string[]>>
>({
queryKey: [KnowledgeApiAction.FetchMetadata, kbIds],
initialData: {},
enabled: kbIds.length > 0,
gcTime: 0,
queryFn: async () => {
feat(api): add unified index API and dataset management endpoints (#14222) ### What problem does this PR solve? ## Summary Refactor the dataset API layer into a clean service/REST separation pattern, add a unified `/index` API for graph/raptor/mindmap operations, and introduce several new dataset management endpoints with full test coverage. ## Changes ### Service Layer (`dataset_api_service.py`) - Added `trace_index(dataset_id, tenant_id, index_type)` — unified trace function for all index types - Added `run_index`, `delete_index` service functions - Added `get_dataset`, `get_ingestion_summary`, `list_ingestion_logs`, `get_ingestion_log` - Added `run_embedding`, `list_tags`, `aggregate_tags`, `delete_tags`, `rename_tag` - Added `get_flattened_metadata`, `get_auto_metadata`, `update_auto_metadata` ### REST API Layer (`dataset_api.py`) **New unified routes:** | Method | Route | Description | |--------|-------|-------------| | POST | `/datasets/<id>/index?type=graph\|raptor\|mindmap` | Run index task | | GET | `/datasets/<id>/index?type=graph\|raptor\|mindmap` | Trace index task | | DELETE | `/datasets/<id>/<index_type>` | Delete index | | GET | `/datasets/<id>` | Get dataset details | | GET | `/datasets/<id>/ingestions/summary` | Ingestion summary | | GET | `/datasets/<id>/ingestions` | List ingestion logs | | GET | `/datasets/<id>/ingestions/<log_id>` | Get single ingestion log | | POST | `/datasets/<id>/embedding` | Run embedding | | GET | `/datasets/<id>/tags` | List tags | | GET | `/datasets/tags/aggregation` | Aggregate tags across datasets | | DELETE | `/datasets/<id>/tags` | Delete tags | | PUT | `/datasets/<id>/tags` | Rename tag | | GET | `/datasets/metadata/flattened` | Get flattened metadata | | GET/PUT | `/datasets/<id>/metadata/config` | New metadata config path | **Removed routes (replaced by unified `/index`):** - `POST /datasets/<id>/mindmap` - `GET /datasets/<id>/mindmap` **Preserved legacy routes (backward compatibility):** - `/run_graphrag`, `/trace_graphrag`, `/run_raptor`, `/trace_raptor` - `/auto_metadata` GET/PUT ### Test Suite - Updated `common.py` helpers: added `trace_index`, removed `run_mindmap`/`trace_mindmap` - Added 7 new test files with 39 test cases total: | Test File | Cases | |-----------|-------| | `test_get_dataset.py` | 4 | | `test_ingestion_summary.py` | 2 | | `test_ingestion_logs.py` | 5 | | `test_index_api.py` | 14 | | `test_embedding.py` | 2 | | `test_tags.py` | 8 | | `test_flattened_metadata.py` | 4 | - Deleted `test_mindmap_tasks.py` (covered by unified index tests) ## Design Decisions 1. **Unified `/index?type=...`** — single endpoint replaces 3 separate route pairs for graph/raptor/mindmap 2. **Backward compatibility** — old routes (`/run_graphrag`, `/run_raptor`, `/auto_metadata`) preserved alongside new paths 3. **`_VALID_INDEX_TYPES = {"graph", "raptor", "mindmap"}`** — input validation via constant set 4. **`_INDEX_TYPE_TO_TASK_ID_FIELD`** — maps index type to KB model task ID field for clean dispatch ## Files Changed - `api/apps/restful_apis/dataset_api.py` - `api/apps/services/dataset_api_service.py` - `sdk/python/ragflow_sdk/modules/dataset.py` - `test/testcases/test_http_api/common.py` - `test/testcases/test_http_api/test_dataset_management/` (7 new files) ### Type of change - [x] New Feature (non-breaking change which adds functionality) - [x] Refactoring --------- Signed-off-by: noob <yixiao121314@outlook.com>
2026-04-27 01:38:01 +00:00
const { data } = await kbService.getMeta({
dataset_ids: kbIds.join(','),
});
return data?.data ?? {};
},
});
return { data, loading };
}
Feat/configurable metadata display (#13464) ### What problem does this PR solve? Currently, RAGFlow's Search and Chat interfaces display only raw vectorized text chunks during retrieval, without contextual information about their source documents. Users cannot see document titles, page numbers, upload dates, or custom metadata fields that would help them understand and trust the retrieved results. This PR introduces an **optional metadata display feature** that enriches retrieved chunks with document-level metadata in both the Search tab and Chatbot interface. **Key improvements:** - **Search results**: Display document metadata as styled badges beneath chunk snippets - **Chat citations**: Show metadata in citation popovers and reference lists for better source context - **LLM context**: Metadata is injected into the LLM prompt to enable more accurate, citation-aware responses - **External API support**: Applications using RAGFlow's SDK retrieval endpoints (`/v1/retrieval`, `/v1/searchbots/retrieval_test`) can opt-in via request parameters - **User control**: Multi-select dropdown UI allows users to choose which metadata fields to display **Implementation approach:** - ✅ Reuses existing `DocMetadataService` infrastructure (no new database tables or indices) - ✅ Settings stored in existing JSON configuration fields (`search_config.reference_metadata`, `prompt_config.reference_metadata`) - ✅ No database migrations required - ✅ Disabled by default (fully opt-in and backward-compatible) - ✅ Dynamic metadata field selection populated from actual document metadata keys - ✅ Fixed critical bug where Python's builtin `set()` was shadowed by a route handler function **Modified endpoints (all backward-compatible):** - `POST /v1/retrieval` (Public SDK) - `POST /v1/searchbots/retrieval_test` (Searchbots) - `POST /v1/chunk/retrieval_test` (UI/Internal) - Chat completions endpoints (via `extra_body.reference_metadata` or `prompt_config`) ### Type of change - [x] New Feature (non-breaking change which adds functionality) ###Images - <img width="879" height="1275" alt="image" src="https://github.com/user-attachments/assets/95b2d731-31ae-45a1-b081-bf5893f52aeb" /> <br><br> <br><br> <img width="1532" height="362" alt="image" src="https://github.com/user-attachments/assets/9cebc65b-b7a7-459f-b25e-3b13fa9b638e" /> <br><br> <br><br> <img width="2586" height="1320" alt="image" src="https://github.com/user-attachments/assets/2153d493-d899-461f-a7a9-041391e07776" /> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Attili-sys <Attili-sys@users.noreply.github.com> Co-authored-by: Ahmad Intisar <ahmadintisar@Ahmads-MacBook-M4-Pro.local>
2026-04-30 18:13:27 +03:00
export function useFetchKnowledgeMetadataKeys(kbIds: string[] = []) {
const sortedKbIds = useMemo(() => [...kbIds].sort(), [kbIds]);
const { data, isFetching: loading } = useQuery<string[]>({
queryKey: [KnowledgeApiAction.FetchMetadataKeys, sortedKbIds],
initialData: [],
enabled: sortedKbIds.length > 0,
gcTime: 0,
queryFn: async () => {
const { data } = await kbService.getMetaKeys({
kb_ids: sortedKbIds.join(','),
});
return data?.data ?? [];
},
});
return { data, loading };
}
export const useRemoveKnowledgeGraph = () => {
const knowledgeBaseId = useKnowledgeBaseId();
const queryClient = useQueryClient();
const {
data,
isPending: loading,
mutateAsync,
} = useMutation({
mutationKey: [KnowledgeApiAction.RemoveKnowledgeGraph],
mutationFn: async () => {
const { data } = await deleteKnowledgeGraph(knowledgeBaseId);
if (data.code === 0) {
message.success(i18n.t(`message.deleted`));
queryClient.invalidateQueries({
queryKey: [KnowledgeApiAction.FetchKnowledgeGraph],
});
}
return data?.code;
},
});
return { data, loading, removeKnowledgeGraph: mutateAsync };
};
Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423) ### What problem does this PR solve? #9869 ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: jinhai <haijin.chn@gmail.com> Signed-off-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: chanx <1243304602@qq.com> Co-authored-by: balibabu <cike8899@users.noreply.github.com> Co-authored-by: Lynn <lynn_inf@hotmail.com> Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com> Co-authored-by: huangzl <huangzl@shinemo.com> Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com> Co-authored-by: Wilmer <33392318@qq.com> Co-authored-by: Adrian Weidig <adrianweidig@gmx.net> Co-authored-by: Zhichang Yu <yuzhichang@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Yongteng Lei <yongtengrey@outlook.com> Co-authored-by: Liu An <asiro@qq.com> Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com> Co-authored-by: BadwomanCraZY <511528396@qq.com> Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com> Co-authored-by: Russell Valentine <russ@coldstonelabs.org> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Billy Bao <newyorkupperbay@gmail.com> Co-authored-by: Zhedong Cen <cenzhedong2@126.com> Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com> Co-authored-by: TensorNull <tensor.null@gmail.com> Co-authored-by: TeslaZY <TeslaZY@outlook.com> Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com> Co-authored-by: AB <aj@Ajays-MacBook-Air.local> Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com> Co-authored-by: He Wang <wanghechn@qq.com> Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com> Co-authored-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com> Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box> Co-authored-by: Stephen Hu <stephenhu@seismic.com> Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com> Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com> Co-authored-by: mxc <mxc@example.com> Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com> Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com> Co-authored-by: mcoder6425 <mcoder64@gmail.com> Co-authored-by: lemsn <lemsn@msn.com> Co-authored-by: lemsn <lemsn@126.com> Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com> Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com> Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>
2025-10-09 12:36:19 +08:00
export const useFetchKnowledgeList = (
shouldFilterListWithoutDocument: boolean = false,
keywords = '',
Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423) ### What problem does this PR solve? #9869 ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: jinhai <haijin.chn@gmail.com> Signed-off-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: chanx <1243304602@qq.com> Co-authored-by: balibabu <cike8899@users.noreply.github.com> Co-authored-by: Lynn <lynn_inf@hotmail.com> Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com> Co-authored-by: huangzl <huangzl@shinemo.com> Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com> Co-authored-by: Wilmer <33392318@qq.com> Co-authored-by: Adrian Weidig <adrianweidig@gmx.net> Co-authored-by: Zhichang Yu <yuzhichang@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Yongteng Lei <yongtengrey@outlook.com> Co-authored-by: Liu An <asiro@qq.com> Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com> Co-authored-by: BadwomanCraZY <511528396@qq.com> Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com> Co-authored-by: Russell Valentine <russ@coldstonelabs.org> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Billy Bao <newyorkupperbay@gmail.com> Co-authored-by: Zhedong Cen <cenzhedong2@126.com> Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com> Co-authored-by: TensorNull <tensor.null@gmail.com> Co-authored-by: TeslaZY <TeslaZY@outlook.com> Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com> Co-authored-by: AB <aj@Ajays-MacBook-Air.local> Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com> Co-authored-by: He Wang <wanghechn@qq.com> Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com> Co-authored-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com> Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box> Co-authored-by: Stephen Hu <stephenhu@seismic.com> Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com> Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com> Co-authored-by: mxc <mxc@example.com> Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com> Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com> Co-authored-by: mcoder6425 <mcoder64@gmail.com> Co-authored-by: lemsn <lemsn@msn.com> Co-authored-by: lemsn <lemsn@126.com> Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com> Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com> Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>
2025-10-09 12:36:19 +08:00
): {
list: IDataset[];
Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423) ### What problem does this PR solve? #9869 ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: jinhai <haijin.chn@gmail.com> Signed-off-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: chanx <1243304602@qq.com> Co-authored-by: balibabu <cike8899@users.noreply.github.com> Co-authored-by: Lynn <lynn_inf@hotmail.com> Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com> Co-authored-by: huangzl <huangzl@shinemo.com> Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com> Co-authored-by: Wilmer <33392318@qq.com> Co-authored-by: Adrian Weidig <adrianweidig@gmx.net> Co-authored-by: Zhichang Yu <yuzhichang@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Yongteng Lei <yongtengrey@outlook.com> Co-authored-by: Liu An <asiro@qq.com> Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com> Co-authored-by: BadwomanCraZY <511528396@qq.com> Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com> Co-authored-by: Russell Valentine <russ@coldstonelabs.org> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Billy Bao <newyorkupperbay@gmail.com> Co-authored-by: Zhedong Cen <cenzhedong2@126.com> Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com> Co-authored-by: TensorNull <tensor.null@gmail.com> Co-authored-by: TeslaZY <TeslaZY@outlook.com> Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com> Co-authored-by: AB <aj@Ajays-MacBook-Air.local> Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com> Co-authored-by: He Wang <wanghechn@qq.com> Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com> Co-authored-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com> Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box> Co-authored-by: Stephen Hu <stephenhu@seismic.com> Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com> Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com> Co-authored-by: mxc <mxc@example.com> Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com> Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com> Co-authored-by: mcoder6425 <mcoder64@gmail.com> Co-authored-by: lemsn <lemsn@msn.com> Co-authored-by: lemsn <lemsn@126.com> Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com> Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com> Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>
2025-10-09 12:36:19 +08:00
loading: boolean;
} => {
const { data, isFetching: loading } = useQuery({
queryKey: [
KnowledgeApiAction.FetchKnowledgeList,
shouldFilterListWithoutDocument,
keywords,
],
Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423) ### What problem does this PR solve? #9869 ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: jinhai <haijin.chn@gmail.com> Signed-off-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: chanx <1243304602@qq.com> Co-authored-by: balibabu <cike8899@users.noreply.github.com> Co-authored-by: Lynn <lynn_inf@hotmail.com> Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com> Co-authored-by: huangzl <huangzl@shinemo.com> Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com> Co-authored-by: Wilmer <33392318@qq.com> Co-authored-by: Adrian Weidig <adrianweidig@gmx.net> Co-authored-by: Zhichang Yu <yuzhichang@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Yongteng Lei <yongtengrey@outlook.com> Co-authored-by: Liu An <asiro@qq.com> Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com> Co-authored-by: BadwomanCraZY <511528396@qq.com> Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com> Co-authored-by: Russell Valentine <russ@coldstonelabs.org> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Billy Bao <newyorkupperbay@gmail.com> Co-authored-by: Zhedong Cen <cenzhedong2@126.com> Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com> Co-authored-by: TensorNull <tensor.null@gmail.com> Co-authored-by: TeslaZY <TeslaZY@outlook.com> Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com> Co-authored-by: AB <aj@Ajays-MacBook-Air.local> Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com> Co-authored-by: He Wang <wanghechn@qq.com> Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com> Co-authored-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com> Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box> Co-authored-by: Stephen Hu <stephenhu@seismic.com> Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com> Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com> Co-authored-by: mxc <mxc@example.com> Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com> Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com> Co-authored-by: mcoder6425 <mcoder64@gmail.com> Co-authored-by: lemsn <lemsn@msn.com> Co-authored-by: lemsn <lemsn@126.com> Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com> Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com> Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>
2025-10-09 12:36:19 +08:00
initialData: [],
gcTime: 0, // https://tanstack.com/query/latest/docs/framework/react/guides/caching?from=reactQueryV3
queryFn: async () => {
const { data } = await listDataset(
keywords
? {
ext: {
keywords,
},
}
: undefined,
);
const list = data?.data ?? [];
Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423) ### What problem does this PR solve? #9869 ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: jinhai <haijin.chn@gmail.com> Signed-off-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: chanx <1243304602@qq.com> Co-authored-by: balibabu <cike8899@users.noreply.github.com> Co-authored-by: Lynn <lynn_inf@hotmail.com> Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com> Co-authored-by: huangzl <huangzl@shinemo.com> Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com> Co-authored-by: Wilmer <33392318@qq.com> Co-authored-by: Adrian Weidig <adrianweidig@gmx.net> Co-authored-by: Zhichang Yu <yuzhichang@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Yongteng Lei <yongtengrey@outlook.com> Co-authored-by: Liu An <asiro@qq.com> Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com> Co-authored-by: BadwomanCraZY <511528396@qq.com> Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com> Co-authored-by: Russell Valentine <russ@coldstonelabs.org> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Billy Bao <newyorkupperbay@gmail.com> Co-authored-by: Zhedong Cen <cenzhedong2@126.com> Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com> Co-authored-by: TensorNull <tensor.null@gmail.com> Co-authored-by: TeslaZY <TeslaZY@outlook.com> Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com> Co-authored-by: AB <aj@Ajays-MacBook-Air.local> Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com> Co-authored-by: He Wang <wanghechn@qq.com> Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com> Co-authored-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com> Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box> Co-authored-by: Stephen Hu <stephenhu@seismic.com> Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com> Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com> Co-authored-by: mxc <mxc@example.com> Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com> Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com> Co-authored-by: mcoder6425 <mcoder64@gmail.com> Co-authored-by: lemsn <lemsn@msn.com> Co-authored-by: lemsn <lemsn@126.com> Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com> Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com> Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>
2025-10-09 12:36:19 +08:00
return shouldFilterListWithoutDocument
? list.filter((x: IDataset) => x.chunk_count > 0)
Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423) ### What problem does this PR solve? #9869 ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: jinhai <haijin.chn@gmail.com> Signed-off-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: chanx <1243304602@qq.com> Co-authored-by: balibabu <cike8899@users.noreply.github.com> Co-authored-by: Lynn <lynn_inf@hotmail.com> Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com> Co-authored-by: huangzl <huangzl@shinemo.com> Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com> Co-authored-by: Wilmer <33392318@qq.com> Co-authored-by: Adrian Weidig <adrianweidig@gmx.net> Co-authored-by: Zhichang Yu <yuzhichang@gmail.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Yongteng Lei <yongtengrey@outlook.com> Co-authored-by: Liu An <asiro@qq.com> Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com> Co-authored-by: BadwomanCraZY <511528396@qq.com> Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com> Co-authored-by: Russell Valentine <russ@coldstonelabs.org> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Billy Bao <newyorkupperbay@gmail.com> Co-authored-by: Zhedong Cen <cenzhedong2@126.com> Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com> Co-authored-by: TensorNull <tensor.null@gmail.com> Co-authored-by: TeslaZY <TeslaZY@outlook.com> Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com> Co-authored-by: AB <aj@Ajays-MacBook-Air.local> Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com> Co-authored-by: He Wang <wanghechn@qq.com> Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com> Co-authored-by: Jin Hai <haijin.chn@gmail.com> Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com> Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box> Co-authored-by: Stephen Hu <stephenhu@seismic.com> Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com> Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com> Co-authored-by: mxc <mxc@example.com> Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com> Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com> Co-authored-by: mcoder6425 <mcoder64@gmail.com> Co-authored-by: lemsn <lemsn@msn.com> Co-authored-by: lemsn <lemsn@126.com> Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com> Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com> Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>
2025-10-09 12:36:19 +08:00
: list;
},
});
return { list: data, loading };
};
export const useSelectKnowledgeOptions = () => {
const { list } = useFetchKnowledgeList();
const options = list?.map((item) => ({
label: item.name,
value: item.id,
}));
return options;
};
//#region tags
export const useRenameTag = () => {
const knowledgeBaseId = useKnowledgeBaseId();
const queryClient = useQueryClient();
const {
data,
isPending: loading,
mutateAsync,
} = useMutation({
mutationKey: ['renameTag'],
mutationFn: async (params: IRenameTag) => {
const { data } = await renameTag(knowledgeBaseId, params);
if (data.code === 0) {
message.success(i18n.t(`message.modified`));
queryClient.invalidateQueries({
queryKey: ['fetchTagList'],
});
}
return data?.data ?? [];
},
});
return { data, loading, renameTag: mutateAsync };
};
export const useTagIsRenaming = () => {
return useIsMutating({ mutationKey: ['renameTag'] }) > 0;
};
export const useFetchTagListByKnowledgeIds = () => {
const [knowledgeIds, setKnowledgeIds] = useState<string[]>([]);
const { data, isFetching: loading } = useQuery<Array<[string, number]>>({
2026-05-26 20:24:22 +08:00
queryKey: ['fetchTagListByKnowledgeIds', knowledgeIds],
enabled: knowledgeIds.length > 0,
initialData: [],
gcTime: 0, // https://tanstack.com/query/latest/docs/framework/react/guides/caching?from=reactQueryV3
queryFn: async () => {
const { data } = await kbService.listTagByKnowledgeIds({
feat(api): add unified index API and dataset management endpoints (#14222) ### What problem does this PR solve? ## Summary Refactor the dataset API layer into a clean service/REST separation pattern, add a unified `/index` API for graph/raptor/mindmap operations, and introduce several new dataset management endpoints with full test coverage. ## Changes ### Service Layer (`dataset_api_service.py`) - Added `trace_index(dataset_id, tenant_id, index_type)` — unified trace function for all index types - Added `run_index`, `delete_index` service functions - Added `get_dataset`, `get_ingestion_summary`, `list_ingestion_logs`, `get_ingestion_log` - Added `run_embedding`, `list_tags`, `aggregate_tags`, `delete_tags`, `rename_tag` - Added `get_flattened_metadata`, `get_auto_metadata`, `update_auto_metadata` ### REST API Layer (`dataset_api.py`) **New unified routes:** | Method | Route | Description | |--------|-------|-------------| | POST | `/datasets/<id>/index?type=graph\|raptor\|mindmap` | Run index task | | GET | `/datasets/<id>/index?type=graph\|raptor\|mindmap` | Trace index task | | DELETE | `/datasets/<id>/<index_type>` | Delete index | | GET | `/datasets/<id>` | Get dataset details | | GET | `/datasets/<id>/ingestions/summary` | Ingestion summary | | GET | `/datasets/<id>/ingestions` | List ingestion logs | | GET | `/datasets/<id>/ingestions/<log_id>` | Get single ingestion log | | POST | `/datasets/<id>/embedding` | Run embedding | | GET | `/datasets/<id>/tags` | List tags | | GET | `/datasets/tags/aggregation` | Aggregate tags across datasets | | DELETE | `/datasets/<id>/tags` | Delete tags | | PUT | `/datasets/<id>/tags` | Rename tag | | GET | `/datasets/metadata/flattened` | Get flattened metadata | | GET/PUT | `/datasets/<id>/metadata/config` | New metadata config path | **Removed routes (replaced by unified `/index`):** - `POST /datasets/<id>/mindmap` - `GET /datasets/<id>/mindmap` **Preserved legacy routes (backward compatibility):** - `/run_graphrag`, `/trace_graphrag`, `/run_raptor`, `/trace_raptor` - `/auto_metadata` GET/PUT ### Test Suite - Updated `common.py` helpers: added `trace_index`, removed `run_mindmap`/`trace_mindmap` - Added 7 new test files with 39 test cases total: | Test File | Cases | |-----------|-------| | `test_get_dataset.py` | 4 | | `test_ingestion_summary.py` | 2 | | `test_ingestion_logs.py` | 5 | | `test_index_api.py` | 14 | | `test_embedding.py` | 2 | | `test_tags.py` | 8 | | `test_flattened_metadata.py` | 4 | - Deleted `test_mindmap_tasks.py` (covered by unified index tests) ## Design Decisions 1. **Unified `/index?type=...`** — single endpoint replaces 3 separate route pairs for graph/raptor/mindmap 2. **Backward compatibility** — old routes (`/run_graphrag`, `/run_raptor`, `/auto_metadata`) preserved alongside new paths 3. **`_VALID_INDEX_TYPES = {"graph", "raptor", "mindmap"}`** — input validation via constant set 4. **`_INDEX_TYPE_TO_TASK_ID_FIELD`** — maps index type to KB model task ID field for clean dispatch ## Files Changed - `api/apps/restful_apis/dataset_api.py` - `api/apps/services/dataset_api_service.py` - `sdk/python/ragflow_sdk/modules/dataset.py` - `test/testcases/test_http_api/common.py` - `test/testcases/test_http_api/test_dataset_management/` (7 new files) ### Type of change - [x] New Feature (non-breaking change which adds functionality) - [x] Refactoring --------- Signed-off-by: noob <yixiao121314@outlook.com>
2026-04-27 01:38:01 +00:00
dataset_ids: knowledgeIds.join(','),
});
2026-05-26 20:24:22 +08:00
const list = (data?.data || []) as Array<
[string, number] | { value?: string; count?: number }
>;
return list.flatMap((tag): Array<[string, number]> => {
if (Array.isArray(tag)) {
return [tag];
}
return tag.value ? [[tag.value, tag.count ?? 0]] : [];
});
},
});
return { list: data, loading, setKnowledgeIds };
};
export const useFetchTagList = () => {
const knowledgeBaseId = useKnowledgeBaseId();
const { data, isFetching: loading } = useQuery<Array<[string, number]>>({
queryKey: ['fetchTagList'],
initialData: [],
gcTime: 0, // https://tanstack.com/query/latest/docs/framework/react/guides/caching?from=reactQueryV3
queryFn: async () => {
const { data } = await listTag(knowledgeBaseId);
const list = data?.data || [];
return list;
},
});
return { list: data, loading };
};
export const useDeleteTag = () => {
const knowledgeBaseId = useKnowledgeBaseId();
const queryClient = useQueryClient();
const {
data,
isPending: loading,
mutateAsync,
} = useMutation({
mutationKey: ['deleteTag'],
mutationFn: async (tags: string[]) => {
const { data } = await removeTag(knowledgeBaseId, tags);
if (data.code === 0) {
message.success(i18n.t(`message.deleted`));
queryClient.invalidateQueries({
queryKey: ['fetchTagList'],
});
}
return data?.data ?? [];
},
});
return { data, loading, deleteTag: mutateAsync };
};
// #endregion
//#region Retrieval testing
export const useTestChunkRetrieval = (): ResponsePostType<ITestingResult> & {
testChunk: (...params: any[]) => void;
} => {
const knowledgeBaseId = useKnowledgeBaseId();
const { page, size: pageSize } = useSetPaginationParams();
const {
data,
isPending: loading,
mutateAsync,
} = useMutation({
mutationKey: ['testChunk'], // This method is invalid
gcTime: 0,
mutationFn: async (values: any) => {
const { data } = await kbService.retrievalTest({
...values,
kb_id: values.kb_id ?? knowledgeBaseId,
page,
size: pageSize,
});
if (data.code === 0) {
const res = data.data;
return {
...res,
documents: res.doc_aggs,
};
}
return (
data?.data ?? {
chunks: [],
documents: [],
total: 0,
}
);
},
});
return {
data: data ?? { chunks: [], documents: [], total: 0 },
loading,
testChunk: mutateAsync,
};
};
export const useTestChunkAllRetrieval = (): ResponsePostType<ITestingResult> & {
testChunkAll: (...params: any[]) => void;
} => {
const knowledgeBaseId = useKnowledgeBaseId();
const { page, size: pageSize } = useSetPaginationParams();
const {
data,
isPending: loading,
mutateAsync,
} = useMutation({
mutationKey: ['testChunkAll'], // This method is invalid
gcTime: 0,
mutationFn: async (values: any) => {
const { data } = await kbService.retrievalTest({
...values,
kb_id: values.kb_id ?? knowledgeBaseId,
doc_ids: [],
page,
size: pageSize,
});
if (data.code === 0) {
const res = data.data;
return {
...res,
documents: res.doc_aggs,
};
}
return (
data?.data ?? {
chunks: [],
documents: [],
total: 0,
}
);
},
});
return {
data: data ?? { chunks: [], documents: [], total: 0 },
loading,
testChunkAll: mutateAsync,
};
};
export const useChunkIsTesting = () => {
return useIsMutating({ mutationKey: ['testChunk'] }) > 0;
};
export const useSelectTestingResult = (): ITestingResult => {
const data = useMutationState({
filters: { mutationKey: ['testChunk'] },
select: (mutation) => {
return mutation.state.data;
},
});
return (data.at(-1) ?? {
chunks: [],
documents: [],
total: 0,
}) as ITestingResult;
};
export const useSelectIsTestingSuccess = () => {
const status = useMutationState({
filters: { mutationKey: ['testChunk'] },
select: (mutation) => {
return mutation.state.status;
},
});
return status.at(-1) === 'success';
};
export const useAllTestingSuccess = () => {
const status = useMutationState({
filters: { mutationKey: ['testChunkAll'] },
select: (mutation) => {
return mutation.state.status;
},
});
return status.at(-1) === 'success';
};
export const useAllTestingResult = (): ITestingResult => {
const data = useMutationState({
filters: { mutationKey: ['testChunkAll'] },
select: (mutation) => {
return mutation.state.data;
},
});
return (data.at(-1) ?? {
chunks: [],
documents: [],
total: 0,
}) as ITestingResult;
};
//#endregion