List Documents

Lists the documents in a knowledge base, oldest first, with each document’s status, custom metadata, active revision, and latest indexing task.

Disabled documents are listed with enabled: false. Documents being deleted, or whose file or source is being deleted, are left out.

A page can hold fewer than limit documents, so follow next_cursor until it is null.

For how document IDs and document file IDs relate, see Browse Documents and Chunks.

1 min read

get/knowledge-fs/spaces/{knowledge_base_id}/logical-documents

Request example

curl --request GET \
  --url https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/logical-documents \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/logical-documents"
headers = {
    "Authorization": "Bearer <token>",
}

response = requests.request("GET", url, headers=headers)

print(response.text)

const response = await fetch('https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/logical-documents', {
  method: 'GET',
  headers: {
    'Authorization': 'Bearer <token>'
  }
});

const data = await response.json();
console.log(data);

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => 'https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/logical-documents',
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_CUSTOMREQUEST => 'GET',
  CURLOPT_HTTPHEADER => [
    'Authorization: Bearer <token>',
  ],
]);

$response = curl_exec($curl);
curl_close($curl);

echo $response;

package main

import (
	"fmt"
	"io"
	"net/http"
)

func main() {
	url := "https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/logical-documents"

	req, _ := http.NewRequest("GET", url, nil)
	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)
	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))
}

HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/logical-documents"))
    .header("Authorization", "Bearer <token>")
    .method("GET", HttpRequest.BodyPublishers.noBody())
    .build();

HttpResponse<String> response = HttpClient.newHttpClient()
    .send(request, HttpResponse.BodyHandlers.ofString());

System.out.println(response.body());

require 'uri'
require 'net/http'

url = URI('https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/logical-documents')

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = url.scheme == 'https'

request = Net::HTTP::Get.new(url)
request['Authorization'] = 'Bearer <token>'

response = http.request(request)
puts response.read_body

Response

{
  "data": [
    {
      "active": {
        "activated_at": "2026-10-20T08:16:05Z",
        "content_hash": "4f7c2d9a1b3e5f60718293a4b5c6d7e8f9a0b1c2d3e4f5a6b7c8d9e0f1a2b3c4",
        "created_at": "2026-10-20T08:15:42Z",
        "document_asset_id": "6ec0bd7f-11c0-43da-975e-2a8ad9ebae0b",
        "document_asset_version": 1,
        "document_id": "2f6b8d1a-7c3e-4a5b-9d0e-1f2a3b4c5d6e",
        "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
        "mime_type": "application/pdf",
        "revision": 2,
        "size_bytes": 482113,
        "state": "active"
      },
      "active_revision": 2,
      "created_at": "2026-09-03T10:02:11Z",
      "disabled_at": null,
      "disabled_by_subject_id": null,
      "enabled": true,
      "id": "2f6b8d1a-7c3e-4a5b-9d0e-1f2a3b4c5d6e",
      "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
      "latest_task": {
        "can_cancel": false,
        "can_retry": false,
        "completed_at": "2026-10-20T08:16:05Z",
        "created_at": "2026-10-20T08:15:42Z",
        "document_id": "2f6b8d1a-7c3e-4a5b-9d0e-1f2a3b4c5d6e",
        "document_revision": 2,
        "document_title": null,
        "error_code": null,
        "error_message": null,
        "failure": null,
        "failures": null,
        "id": "c4e8a2f6-1b3d-4e5f-8a9b-0c1d2e3f4a5b",
        "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
        "operation": "document_processing",
        "progress_completed": 1,
        "progress_failed": 0,
        "progress_percent": 100,
        "progress_total": 1,
        "semantic_enrichment": {
          "error_code": null,
          "error_message": null,
          "failure": null,
          "nodes_completed": 0,
          "nodes_total": null,
          "provider_calls": null,
          "provider_calls_maximum": null,
          "state": "disabled",
          "updated_at": null
        },
        "source_id": null,
        "source_title": null,
        "state": "completed",
        "task_kind": "document",
        "updated_at": "2026-10-20T08:16:05Z"
      },
      "provider_item_id": null,
      "row_version": 4,
      "source_id": null,
      "status": "ready",
      "title": "handbook.pdf",
      "updated_at": "2026-10-20T08:16:05Z",
      "user_metadata": {
        "owner": "support-team",
        "product_line": "billing",
        "review_date": "2026-12-01T00:00:00Z"
      }
    },
    {
      "active": {
        "activated_at": "2026-10-19T03:04:51Z",
        "content_hash": "9c1e5b7d3f2a4c6e8b0d1f3a5c7e9b2d4f6a8c0e1b3d5f7a9c2e4b6d8f0a1c3e",
        "created_at": "2026-10-19T03:04:12Z",
        "document_asset_id": "7d2e4f6a-8b0c-4d1e-9f3a-5b7c9d1e3f5a",
        "document_asset_version": 1,
        "document_id": "3a7e9c1b-5d2f-4e8a-9b0c-1d2e3f4a5b6c",
        "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
        "mime_type": "text/markdown",
        "revision": 1,
        "size_bytes": 18342,
        "state": "active"
      },
      "active_revision": 1,
      "created_at": "2026-10-19T03:04:12Z",
      "disabled_at": null,
      "disabled_by_subject_id": null,
      "enabled": true,
      "id": "3a7e9c1b-5d2f-4e8a-9b0c-1d2e3f4a5b6c",
      "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
      "latest_task": null,
      "provider_item_id": "5e0f9a6c2b8d4e1f7a3c9b5d1e7f3a9c5b1d7e3f9a5c1b7d3e9f5a1c7b3d9e5f",
      "row_version": 1,
      "source_id": "6f1c2b0e-3d0b-4a5e-9f4c-1c0e6a7b8d90",
      "status": "ready",
      "title": "Pricing | Docs site",
      "updated_at": "2026-10-19T03:04:51Z",
      "user_metadata": {}
    }
  ],
  "next_cursor": null
}

{
  "code": "knowledge_fs_invalid_request",
  "message": "Agent Knowledge Base request is invalid.",
  "status": 400,
  "violations": [
    {
      "field": [
        "limit"
      ],
      "type": "less_than_equal"
    }
  ]
}

{
  "code": "knowledge_fs_invalid_request",
  "failure": {
    "category": "validation",
    "code": "KNOWLEDGE_FS_INVALID_REQUEST",
    "message": "The Agent Knowledge Base request is invalid.",
    "retryPolicy": "never",
    "traceId": "7f3c1a90-2e64-4b7d-8a51-6c0d9e2f4b83"
  },
  "message": "The Agent Knowledge Base request is invalid.",
  "status": 400
}

{
  "code": "knowledge_fs_invalid_credential",
  "message": "Invalid Agent Knowledge Base service credential.",
  "status": 401
}

{
  "code": "unauthorized",
  "message": "Access token is invalid",
  "status": 401
}

{
  "code": "forbidden",
  "message": "Sorry, you have reached the knowledge base request rate limit of your subscription.",
  "status": 403
}

{
  "code": "knowledge_fs_access_denied",
  "message": "Agent Knowledge Base operation is not allowed.",
  "status": 403
}

{
  "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": "7f3c1a90-2e64-4b7d-8a51-6c0d9e2f4b83"
  },
  "message": "You do not have permission to perform this Agent Knowledge Base operation.",
  "status": 403
}

{
  "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
}

{
  "code": "knowledge_fs_upstream_unavailable",
  "failure": {
    "action": "contact_admin",
    "category": "internal",
    "code": "KNOWLEDGE_FS_INTERNAL_ERROR",
    "message": "Agent Knowledge Base could not complete the operation. Try again, or contact an administrator with the error reference.",
    "retryPolicy": "manual",
    "traceId": "5e2a9c17-3b4d-4f60-8a1b-2c3d4e5f6a7b"
  },
  "message": "Agent Knowledge Base could not complete the operation. Try again, or contact an administrator with the error reference.",
  "status": 502
}

{
  "code": "knowledge_fs_upstream_unavailable",
  "message": "Agent Knowledge Base is unavailable.",
  "status": 502
}

{
  "code": "knowledge_fs_operation_unavailable",
  "message": "Agent Knowledge Base operation is not available.",
  "status": 503
}

{
  "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
}

get/knowledge-fs/spaces/{knowledge_base_id}/logical-documents

Authorization

Authorizationstringheaderrequired#

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).

Keep keys server-side; never embed them in client code. Requests with a missing or invalid key fail with HTTP 401 (unauthorized).

Path parameters

knowledge_base_idstringrequired#

Knowledge base ID: the last segment of the Service API endpoint shown in the knowledge base's API Access dialog (…/knowledge-fs/spaces/<knowledge base ID>), and the segment after /datasets/new/ in the address bar.

Query parameters

cursorstring#

Cursor from the previous page's next_cursor.

Length: 1–1000

limitinteger#

Documents per page.

Default: 50

Range: 1–100

Responses

application/json

One page of documents.

dataobject[]#

One page of documents, oldest first.

Show child attributes

activeobject#

The active revision: the content the knowledge base serves. Pass its revision to List Chunks and its document_asset_id to Get Document File. null while no revision is active.

Show child attributes

activated_atstring#

When the revision became active, ISO 8601. null for a revision that never became active.

content_hashstring#

SHA-256 hash of the content, hex-encoded.

created_atstring#

When the revision was created, ISO 8601.

document_asset_idstring#

ID of the document file behind this revision. Use it with Get Document File.

document_asset_versioninteger#

The document file's version when this revision was created.

document_idstring#

Document ID: the id of Get Document.

knowledge_space_idstring#

Internal ID of the knowledge base. Not the knowledge base ID in the path.

mime_typestring#

MIME type of the document file.

revisioninteger#

Revision number, starting at 1. The revision path value for List Chunks.

size_bytesinteger#

Size of the document file in bytes.

statestring#

candidate while the revision is being indexed, active for the revision the knowledge base serves, superseded after a newer revision became active, failed when indexing failed.

active_revisioninteger#

Number of the active revision. null while none is active.

created_atstring#

When the document was created, ISO 8601.

disabled_atstring#

When the document was disabled in Dify, ISO 8601.

disabled_by_subject_idstring#

Internal ID of whoever disabled the document. Not needed to call this API.

enabledboolean#

false after the document is disabled in Dify. Re-index Documents skips disabled documents.

idstring#

Document ID. It stays the same when the document's content is updated.

knowledge_space_idstring#

Internal ID of the knowledge base. Not the knowledge base ID in the path.

latest_taskobject#

The newest indexing task behind the document's revisions, with task_kind: document. Follow it with Get Document Indexing Task using its id. null when there is none, and always null in the Update Document Metadata response.

Show child attributes

can_cancelboolean#

Whether the task can be canceled now. For task_kind: document, cancel it with Cancel Indexing Task using id. A bulk task has no cancel operation in this API, even when can_cancel is true.

can_retryboolean#

Whether the task can be retried now. For task_kind: document, retry it with Retry Indexing Task using id.

completed_atstring#

When the task ended, ISO 8601. null while it runs.

created_atstring#

When the task was created, ISO 8601.

document_idstring#

Document ID of an indexing task. For a bulk task, set only when it has one document.

document_revisioninteger#

Revision an indexing task builds.

document_titlestring#

Document title, set only for a bulk task with one document.

error_codestring#

Error code when state is failed.

error_messagestring#

The message for error_code. Can differ from failure.message.

failureobject#

Error details when state is failed. null otherwise.

Show child attributes

actionstring#

Suggested next step, when there is one: configure_model, configure_parser, configure_source, contact_admin, reupload, or retry. null when not applicable; omitted from HTTP error bodies.

categorystring#

Kind of failure: authorization, canceled, configuration, conflict, dependency, internal, not_found, rate_limit, timeout, or validation.

codestring#

Stable error code in upper snake case, for example KNOWLEDGE_FS_CONFLICT or SOURCE_CREDENTIAL_TEST_FAILED.

messagestring#

Public message for the error code or failure category. Provider error details are not exposed.

parametersobject#

Up to 8 values that qualify the failure, with keys among attempt, currentRowVersion, documentCount, expectedRowVersion, fileSizeBytes, limit, maxFileSizeBytes, maxItems, modelType, providerKind, retryAfterSeconds, and status. null when there are none; omitted from HTTP error bodies.

retryPolicystring#

Whether a retry can help: automatic (the service retries on its own), manual (retry yourself), after_configuration (fix the knowledge base's setup in Dify first), or never (change the request).

stagestring#

Stage the failure belongs to, for example query_generation or credential-test. null when not applicable; omitted from HTTP error bodies.

traceIdstring#

Reference to quote when contacting an administrator. May be null in a successful response containing failure details, or omitted from an HTTP error body.

failuresobject[]#

For a bulk task, one entry per document that failed. null for other kinds.

Show child attributes

document_idstring#

Document ID.

document_titlestring#

Document title.

error_codestring#

Error code of the failure.

error_messagestring#

The message for error_code.

failureobject#

Show child attributes

actionstring#

Suggested next step, when there is one: configure_model, configure_parser, configure_source, contact_admin, reupload, or retry. null when not applicable; omitted from HTTP error bodies.

categorystring#

Kind of failure: authorization, canceled, configuration, conflict, dependency, internal, not_found, rate_limit, timeout, or validation.

codestring#

Stable error code in upper snake case, for example KNOWLEDGE_FS_CONFLICT or SOURCE_CREDENTIAL_TEST_FAILED.

messagestring#

Public message for the error code or failure category. Provider error details are not exposed.

parametersobject#

retryPolicystring#

stagestring#

Stage the failure belongs to, for example query_generation or credential-test. null when not applicable; omitted from HTTP error bodies.

traceIdstring#

Reference to quote when contacting an administrator. May be null in a successful response containing failure details, or omitted from an HTTP error body.

job_idstring#

ID of the document's task, when there is one.

idstring#

Task ID: an indexing task ID for task_kind: document, a bulk task ID for document_bulk, or a source run ID for source. For a document_delete task from Delete Document, it's the deletion job ID: poll Get Deletion Job with it.

knowledge_space_idstring#

Internal ID of the knowledge base. Not the knowledge base ID in the path.

operationstring#

What the task does:

document_processing: an indexing task.
document_reindex, document_upload, document_delete: a bulk task. Bulk uploads and deletions come from Dify. A deletion with Delete Document also appears as a document_delete task. Other deletions over this API create only a deletion job.
source_sync, source_crawl_preview, source_crawl_import, source_online_document_import, source_online_drive_import: a source run.

progress_completedinteger#

Items completed: the document of an indexing task, the documents of a bulk task, or the items of a source run.

progress_failedinteger#

Items that failed, counted like progress_completed.

progress_percentinteger#

Progress from 0 to 100. For an indexing task it follows the task's stage.

progress_totalinteger#

Items in the task, counted like progress_completed. 1 for an indexing task.

semantic_enrichmentobject#

Knowledge graph building after an indexing task publishes; null for other kinds. Indexing finishes the knowledge graph before publishing, so it doesn't schedule this step. state is not_scheduled while the task runs and disabled once it has ended. nodes_completed stays 0.

Show child attributes

error_codestring#

Error code when state is failed.

error_messagestring#

The message for error_code. Can differ from failure.message.

failureobject#

Error details when state is failed. null otherwise.

Show child attributes

actionstring#

Suggested next step, when there is one: configure_model, configure_parser, configure_source, contact_admin, reupload, or retry. null when not applicable; omitted from HTTP error bodies.

categorystring#

Kind of failure: authorization, canceled, configuration, conflict, dependency, internal, not_found, rate_limit, timeout, or validation.

codestring#

Stable error code in upper snake case, for example KNOWLEDGE_FS_CONFLICT or SOURCE_CREDENTIAL_TEST_FAILED.

messagestring#

Public message for the error code or failure category. Provider error details are not exposed.

parametersobject#

retryPolicystring#

stagestring#

Stage the failure belongs to, for example query_generation or credential-test. null when not applicable; omitted from HTTP error bodies.

traceIdstring#

Reference to quote when contacting an administrator. May be null in a successful response containing failure details, or omitted from an HTTP error body.

nodes_completedinteger#

Knowledge graph nodes built: 0 until state is ready, then the same as nodes_total.

nodes_totalinteger#

Knowledge graph nodes to build. null until known.

provider_callsinteger#

Model calls made so far.

provider_calls_maximuminteger#

Most model calls knowledge graph building may make.

statestring#

not_scheduled, pending, running, ready, failed, or disabled.

updated_atstring#

When the enrichment last changed, ISO 8601.

source_idstring#

Source of a source run.

source_titlestring#

Name of the source of a source run. Set only when listing without task_ids.

statestring#

queued, running, completed, failed, or canceled, mapped from the task's own state. A crawl preview waiting for its pages to be selected is completed.

For the exact state, read an indexing task with Get Indexing Task and a source run with Get Source Run.

task_kindstring#

document (an indexing task), document_bulk (a bulk task), or source (a source run).

updated_atstring#

When the task last changed, ISO 8601.

provider_item_idstring#

For a document imported from a source, the item's identifier there: the providerItemId sent to Import Source Items, or the page_id of a website page.

row_versioninteger#

Change counter. Send it as expectedRowVersion on Update Document Metadata, and as expectedRevision on Delete Document. It increases on metadata updates, when a new revision becomes active or the active revision's file is deleted, when the document's source is deleted with documents=keep, and when the document is enabled or disabled in Dify.

source_idstring#

Source the document came from. null for uploaded files.

statusstring#

pending (no revision active yet), ready (a revision is active), failed (the first revision failed to index and none is active), or deleting. A ready document stays ready when a later revision fails.

titlestring#

Document title.

updated_atstring#

When the document last changed, ISO 8601.

user_metadataobject#

Custom metadata, keyed by metadata field name. Change it with Update Document Metadata or in Dify.

next_cursorstring#

Cursor for the next page, or null on the last page. Send it back as cursor.

List Research Task Results Get Document