> ## Documentation Index > Fetch the complete documentation index at: https://docs.dify.ai/llms.txt > Use this file to discover all available pages before exploring further. # List Research Task Results > Lists the results a research task has written so far, in ascending `sequence`. A task writes at most two results: a retrieval checkpoint when available, followed by a final result. Check the last result for `answer`. A task that stops early may have no results. For the plan, create, poll, and read flow, see [Run a Research Task](/en/api-reference/guides/knowledge-base#run-a-research-task). ## OpenAPI ````yaml /en/api-reference/openapi_service.json get /knowledge-fs/spaces/{knowledge_base_id}/research-tasks/{research_task_id}/partials openapi: 3.0.1 info: description: >- REST API for Dify applications and knowledge bases. Application endpoints authenticate with an app API key; knowledge endpoints authenticate with a dataset API key. title: Dify Service API version: 1.0.0 servers: - description: >- Base URL of the Dify Service API. For self-hosted deployments, replace it with your own API base URL. url: https://{api_base_url} variables: api_base_url: default: api.dify.ai/v1 description: Host and path of the API base URL, without the `https://` prefix. security: - ApiKeyAuth: [] tags: - description: Operations related to chat messages and interactions. name: Chat Messages - description: File upload and preview operations. name: Files - description: Operations related to end user information. name: End Users - description: User feedback operations. name: Feedback - description: Operations related to managing conversations. name: Conversations - description: Text-to-Speech and Speech-to-Text operations. name: Audio - description: Operations to retrieve application settings and information. name: Applications - description: Operations related to managing annotations for direct replies. name: Annotations - description: Endpoints for resuming paused workflows that require human input. name: Human Input - description: Operations for executing and managing workflows. name: Workflow Runs - description: Operations related to text generation and completion. name: Completion Messages - description: >- Operations for managing knowledge bases, including creation, configuration, and retrieval. name: Knowledge Bases - description: >- Operations for creating, updating, and managing documents within a knowledge base. name: Documents - description: Operations for managing document chunks and child chunks. name: Chunks - description: >- Operations for managing knowledge base metadata fields and document metadata values. name: Metadata - description: Operations for managing knowledge base tags and tag bindings. name: Tags - description: Operations for retrieving available models. name: Models - description: >- Operations for managing and running knowledge pipelines, including datasource plugins and pipeline execution. name: Knowledge Pipeline - description: Ask a knowledge base a question and stream the answer. name: Queries - description: Inspect what a query retrieved and why. name: Query Records - description: Run a research question in the background and collect its results. name: Research Tasks - description: >- Read the documents in a knowledge base, their files, revisions, and chunks; label documents with metadata. name: Documents and Chunks - description: >- Follow, cancel, or retry indexing, and list the knowledge base's background tasks. name: Indexing Tasks - description: >- Follow the deletion of a document file, a batch of files, or a source until it finishes. name: Deletion Jobs - description: >- Manage the sources that feed a knowledge base, their sync schedules, and their connections. name: Sources - description: >- Sync a source now, import website pages or provider items, and follow, cancel, or retry the runs. name: Source Syncs and Imports - description: >- Read and change the knowledge base's models and retrieval settings, and follow the migration a change starts. name: Settings paths: /knowledge-fs/spaces/{knowledge_base_id}/research-tasks/{research_task_id}/partials: get: tags: - Research Tasks summary: List Research Task Results description: >- Lists the results a research task has written so far, in ascending `sequence`. A task writes at most two results: a retrieval checkpoint when available, followed by a final result. Check the last result for `answer`. A task that stops early may have no results. For the plan, create, poll, and read flow, see [Run a Research Task](/en/api-reference/guides/knowledge-base#run-a-research-task). operationId: listResearchTaskResults parameters: - description: >- Knowledge base ID: the last segment of the Service API endpoint shown in the knowledge base's **API Access** dialog (`…/knowledge-fs/spaces/`), and the segment after `/datasets/new/` in the address bar. in: path name: knowledge_base_id required: true schema: format: uuid type: string - description: >- Research task ID. From [Create Research Task](/en/api-reference/research-tasks/create-research-task). in: path name: research_task_id required: true schema: format: uuid type: string - description: 'Opaque cursor: send the previous page''s `next_cursor` unchanged.' in: query name: cursor required: false schema: maxLength: 1000 minLength: 1 type: string - description: Entries per page. in: query name: limit required: false schema: default: 25 maximum: 100 minimum: 1 type: integer responses: '200': content: application/json: examples: success: summary: Response Example value: data: - answer: null evidence_bundle: createdAt: '2026-09-06T08:00:10.000Z' id: 9a8b7c6d-5e4f-4a3b-8c2d-1e0f9a8b7c6d items: - citations: - documentAssetId: a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d documentVersion: 1 pageNumber: 2 sectionPath: - Policies - Refunds conflicts: [] freshness: sourceUpdatedAt: '2026-08-30T09:12:00.000Z' status: fresh metadata: {} nodeId: 5d4c3b2a-1f0e-4d9c-8b7a-6f5e4d3c2b1a score: 0.82 scores: final: 0.82 rerank: 0.85 retrieval: 0.71 text: >- From 1 March 2025, refunds are issued within 14 days of the return being received. The previous window was 30 days. - citations: - documentAssetId: a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d documentVersion: 1 pageNumber: 3 sectionPath: - Policies - Refunds - Regional exceptions conflicts: [] freshness: sourceUpdatedAt: '2026-08-30T09:12:00.000Z' status: fresh metadata: {} nodeId: c3b2a1f0-e9d8-4c7b-8a6f-5e4d3c2b1a09 score: 0.77 scores: final: 0.77 rerank: 0.8 retrieval: 0.66 text: >- The 14-day window applies to orders shipped to the EU and the UK. Other regions keep the 30-day window until further notice. missingEvidence: [] query: >- What changed in the 2025 refund policy, and which regions are affected? state: partial knowledge_space_id: b2f1d3a4-5e6c-4a7b-8c9d-0e1f2a3b4c5d research_task_job_id: e4d1b7a2-3c5f-4d8e-9a0b-1c2d3e4f5a6b sequence: 1 - answer: >- The 2025 policy shortened the refund window from 30 days to 14 days after the return is received, effective 1 March 2025. The change applies to orders shipped to the EU and the UK; other regions keep the 30-day window. evidence_bundle: createdAt: '2026-09-06T08:00:41.000Z' id: 1f2e3d4c-5b6a-4978-8a7b-6c5d4e3f2a1b items: - citations: - artifactHash: >- 9f86d081884c7d659a2feaa0c55ad015a3bf4f1b2b0b822cd15d6c15b0f00a08 documentAssetId: a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d documentVersion: 1 endOffset: 1978 pageNumber: 2 sectionPath: - Policies - Refunds startOffset: 1840 conflicts: - reason: >- States a 14-day window while another chunk keeps 30 days for some regions. severity: info withNodeId: c3b2a1f0-e9d8-4c7b-8a6f-5e4d3c2b1a09 freshness: observedAt: '2026-09-06T08:00:12.000Z' sourceUpdatedAt: '2026-08-30T09:12:00.000Z' status: fresh metadata: {} nodeId: 5d4c3b2a-1f0e-4d9c-8b7a-6f5e4d3c2b1a score: 0.82 scores: final: 0.82 freshness: 0.9 rerank: 0.85 retrieval: 0.71 text: >- From 1 March 2025, refunds are issued within 14 days of the return being received. The previous window was 30 days. - citations: - documentAssetId: a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d documentVersion: 1 pageNumber: 3 sectionPath: - Policies - Refunds - Regional exceptions conflicts: [] freshness: observedAt: '2026-09-06T08:00:12.000Z' sourceUpdatedAt: '2026-08-30T09:12:00.000Z' status: fresh metadata: {} nodeId: c3b2a1f0-e9d8-4c7b-8a6f-5e4d3c2b1a09 score: 0.77 scores: final: 0.77 freshness: 0.9 rerank: 0.8 retrieval: 0.66 text: >- The 14-day window applies to orders shipped to the EU and the UK. Other regions keep the 30-day window until further notice. missingEvidence: - expectedEvidenceId: 7e6d5c4b-3a29-4180-9f8e-7d6c5b4a3928 metadata: {} reason: not-retrieved text: >- No chunk lists the effective date for regions outside the EU and the UK. query: >- What changed in the 2025 refund policy, and which regions are affected? retrievalQuery: >- 2025 refund policy changes refund window regions affected state: answerable knowledge_space_id: b2f1d3a4-5e6c-4a7b-8c9d-0e1f2a3b4c5d research_task_job_id: e4d1b7a2-3c5f-4d8e-9a0b-1c2d3e4f5a6b sequence: 2 next_cursor: null schema: properties: data: description: Results in ascending `sequence`. items: properties: answer: description: >- The task's answer. Set only on the final result, and `null` on the retrieval checkpoint. nullable: true type: string evidence_bundle: description: >- Retrieved chunks the task had collected when this result was written. An item whose document file was deleted after retrieval comes back as a placeholder: - `text` is `Evidence deleted or unavailable`. - `citations[]` keep only `documentAssetId`, `documentVersion`, and an empty `sectionPath`. - `conflicts` is empty. - `freshness.status` is `unknown`. - `metadata.traceEvidenceAvailability` is `{"status": "unavailable", "reason": "document-deleted-or-unavailable"}`. properties: createdAt: description: ISO 8601 timestamp when the bundle was written. type: string id: description: ID of this bundle of retrieved chunks. type: string items: description: >- Retrieved chunks with their scores and citations, best first. items: properties: citations: description: >- Where the chunk comes from. At least one per item. items: description: >- Offsets refer to the parsed document text. They are not positions in the original file or the answer. properties: artifactHash: description: >- SHA-256 of the document file the citation points to. Absent when not recorded. type: string documentAssetId: description: >- Document file ID. Read the file's name with [Get Document File](/en/api-reference/documents-and-chunks/get-document-file). To find its document, pass it with `documentVersion` to [Get Document by File](/en/api-reference/documents-and-chunks/get-document-by-file). type: string documentVersion: description: >- The document file's `version` at retrieval time. type: integer endOffset: description: >- Zero-based UTF-8 byte offset in the parsed document text. Exclusive end. Omitted when unavailable. type: integer pageNumber: description: >- Page number, starting at 1, when the source provides page information. Omitted otherwise. type: integer sectionPath: description: >- Section headings from the document root to the cited section. items: type: string type: array startOffset: description: >- Zero-based UTF-8 byte offset in the parsed document text. Inclusive start. Omitted when unavailable. type: integer type: object type: array conflicts: description: >- Disagreements between this chunk and other retrieved chunks. Empty when none. items: properties: reason: description: What the conflict is about. type: string severity: description: '`info`, `warning`, or `blocking`.' type: string withNodeId: description: >- `nodeId` of the chunk this one conflicts with. Absent when the conflict is not tied to one chunk. type: string type: object type: array freshness: description: How current the cited content is. properties: observedAt: description: >- ISO 8601 timestamp when the content was last seen. Absent when unknown. type: string sourceUpdatedAt: description: >- ISO 8601 timestamp of the source's last update. Absent when unknown. type: string status: description: '`fresh`, `stale`, or `unknown`.' type: string type: object metadata: description: >- Additional item details. Carries `traceEvidenceAvailability` on placeholder items. type: object nodeId: description: ID of the retrieved chunk. type: string score: description: >- Overall relevance from `0` to `1`. The same value as `scores.final`. type: number scores: description: Score breakdown, each from `0` to `1`. properties: final: description: Combined score used for ranking. type: number freshness: description: >- Score for how recent the source is. Absent when not computed. type: number rerank: description: >- Score from the rerank model. Absent when reranking did not run. type: number retrieval: description: Score from vector and keyword search. type: number type: object text: description: Chunk text. type: string type: object type: array missingEvidence: description: >- Chunks the run expected but could not use. Empty when none. items: properties: expectedEvidenceId: description: ID of the expected chunk, when known. type: string metadata: description: Additional details. type: object reason: description: >- `not-retrieved`, `permission-filtered`, `stale`, `conflict`, or `unknown`. type: string text: description: What was missing. type: string type: object type: array query: description: The research question. type: string retrievalQuery: description: >- The query text actually sent to retrieval when it differs from `query`. Absent otherwise. type: string state: description: >- How well the retrieved chunks support an answer: `partial` (the retrieval checkpoint, before analysis runs), `answerable`, `not-enough-evidence`, `conflict` (sources disagree), or `permission-limited` (permissions kept some chunks out). type: string traceId: description: >- ID of the run that produced the bundle, when one was recorded. A research task is not recorded as a query record, so [Get Query Record](/en/api-reference/query-records/get-query-record) does not take this ID. type: string type: object knowledge_space_id: description: >- Internal ID of the knowledge base. Not the knowledge base ID in the path. type: string research_task_job_id: description: The research task ID. type: string sequence: description: >- Position of the result within the task, starting at `1`. type: integer type: object type: array next_cursor: description: >- Cursor for the next page, or `null` on the last page. Send it back as `cursor`. nullable: true type: string type: object description: One page of results. '400': content: application/json: examples: knowledge_fs_invalid_request: summary: knowledge_fs_invalid_request (validation) value: code: knowledge_fs_invalid_request message: Agent Knowledge Base request is invalid. status: 400 violations: - field: - limit type: less_than_equal knowledge_fs_invalid_request_path: summary: knowledge_fs_invalid_request (path ID) value: code: knowledge_fs_invalid_request message: Agent Knowledge Base request is invalid. status: 400 description: >- - `knowledge_fs_invalid_request`: the request failed validation. `violations` names each failing field. - `knowledge_fs_invalid_request`: the query string carries a parameter this operation does not accept. - `knowledge_fs_invalid_request`: `research_task_id` is malformed. '401': content: application/json: examples: knowledge_fs_invalid_credential: summary: knowledge_fs_invalid_credential value: code: knowledge_fs_invalid_credential message: Invalid Agent Knowledge Base service credential. status: 401 unauthorized: summary: unauthorized value: code: unauthorized message: Access token is invalid status: 401 description: >- - `unauthorized`: the `Authorization` header is missing, or the key is unknown or not a knowledge base API key. - `knowledge_fs_invalid_credential`: the key is valid, but no knowledge base with this ID exists in the key's workspace, or the key is not tied to a workspace. '403': content: application/json: examples: forbidden: summary: forbidden (rate limit) value: code: forbidden message: >- Sorry, you have reached the knowledge base request rate limit of your subscription. status: 403 knowledge_fs_access_denied: summary: knowledge_fs_access_denied (key scope) value: code: knowledge_fs_access_denied message: Agent Knowledge Base operation is not allowed. status: 403 knowledge_fs_access_denied_2: summary: knowledge_fs_access_denied (other knowledge base) value: code: knowledge_fs_access_denied failure: action: contact_admin category: authorization code: KNOWLEDGE_FS_ACCESS_DENIED message: >- You do not have permission to perform this Agent Knowledge Base operation. retryPolicy: never traceId: 602b9b60-6564-4ba7-8b59-54312d41377c message: >- You do not have permission to perform this Agent Knowledge Base operation. status: 403 description: >- - `knowledge_fs_access_denied`: the key is scoped to other knowledge bases, **API access** is off for this knowledge base, or the knowledge base is not active. - `knowledge_fs_access_denied`: the task belongs to a different knowledge base than the one in the path. - `forbidden`: on Dify Cloud, the workspace has reached the knowledge base request rate limit of its subscription. Every call counts, reads included. '404': content: application/json: examples: knowledge_fs_resource_not_found: summary: knowledge_fs_resource_not_found value: code: knowledge_fs_resource_not_found failure: category: not_found code: KNOWLEDGE_FS_NOT_FOUND message: >- The requested Agent Knowledge Base resource was not found. retryPolicy: never traceId: ca5eb2d9-4242-4950-877c-6c5207b1441e message: The requested Agent Knowledge Base resource was not found. status: 404 not_found: summary: not_found (feature off) value: code: not_found message: >- The requested URL was not found on the server. If you entered the URL manually please check your spelling and try again. status: 404 description: >- - `knowledge_fs_resource_not_found`: the task does not exist, belongs to another workspace, or its knowledge base is being deleted. - `not_found`: the Agent Knowledge Base feature is turned off on this deployment. '502': content: application/json: examples: knowledge_fs_upstream_unavailable: summary: knowledge_fs_upstream_unavailable value: code: knowledge_fs_upstream_unavailable message: Agent Knowledge Base is unavailable. status: 502 description: >- - `knowledge_fs_upstream_unavailable`: no answer came back in time, or the answer couldn't be read. Retry after a pause. '503': content: application/json: examples: knowledge_fs_operation_unavailable: summary: knowledge_fs_operation_unavailable value: code: knowledge_fs_operation_unavailable message: Agent Knowledge Base operation is not available. status: 503 knowledge_fs_operation_unavailable_upstream: summary: knowledge_fs_operation_unavailable (temporary) value: code: knowledge_fs_operation_unavailable failure: action: retry category: dependency code: KNOWLEDGE_FS_UNAVAILABLE message: >- A service required by Agent Knowledge Base is temporarily unavailable. retryPolicy: manual traceId: 5e2a9c17-3b4d-4f60-8a1b-2c3d4e5f6a7b message: >- A service required by Agent Knowledge Base is temporarily unavailable. status: 503 description: >- - `knowledge_fs_operation_unavailable`: the Agent Knowledge Base feature is not set up for this workspace, this operation is not available on the deployment, or the key's access to this knowledge base changed while the request was being authorized. - `knowledge_fs_operation_unavailable`: the request can't be served right now. Follow `failure.retryPolicy`. - `knowledge_fs_operation_unavailable`: the knowledge base was upgraded from a classic knowledge base and is still disabling the documents that were disabled or archived there. Retry later. components: securitySchemes: ApiKeyAuth: bearerFormat: API_KEY description: >- Every request authenticates with an API key: `Authorization: Bearer {API_KEY}`. App endpoints take an app API key; knowledge endpoints take a knowledge base API key ([Get Started](/en/api-reference/guides/get-started)). Keep keys server-side; never embed them in client code. Requests with a missing or invalid key fail with HTTP `401` (`unauthorized`). scheme: bearer type: http ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.