List Chunks

List Chunks

curl --request GET \
  --url https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments"

	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))

}

require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

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

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

{
  "data": [
    {
      "id": "f3d1c7be-9f3a-40d8-8eb8-3a1ef9c3f2c1",
      "position": 1,
      "document_id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
      "content": "Dify is an open-source LLM app development platform.",
      "sign_content": "",
      "answer": "",
      "word_count": 9,
      "tokens": 12,
      "keywords": [
        "dify",
        "platform",
        "llm"
      ],
      "index_node_id": "a1b2c3d4-e5f6-7890-abcd-000000000001",
      "index_node_hash": "abc123def456",
      "hit_count": 0,
      "enabled": true,
      "disabled_at": null,
      "disabled_by": null,
      "status": "completed",
      "created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
      "created_at": 1741267200,
      "updated_at": 1741267200,
      "updated_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
      "indexing_at": 1741267200,
      "completed_at": 1741267200,
      "error": null,
      "stopped_at": null,
      "child_chunks": [],
      "attachments": [],
      "summary": null
    }
  ],
  "doc_form": "text_model",
  "total": 1,
  "has_more": false,
  "limit": 20,
  "page": 1
}

GET

datasets

{dataset_id}

documents

{document_id}

segments

List Chunks

curl --request GET \
  --url https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments"

	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))

}

require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

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

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

{
  "data": [
    {
      "id": "f3d1c7be-9f3a-40d8-8eb8-3a1ef9c3f2c1",
      "position": 1,
      "document_id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
      "content": "Dify is an open-source LLM app development platform.",
      "sign_content": "",
      "answer": "",
      "word_count": 9,
      "tokens": 12,
      "keywords": [
        "dify",
        "platform",
        "llm"
      ],
      "index_node_id": "a1b2c3d4-e5f6-7890-abcd-000000000001",
      "index_node_hash": "abc123def456",
      "hit_count": 0,
      "enabled": true,
      "disabled_at": null,
      "disabled_by": null,
      "status": "completed",
      "created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
      "created_at": 1741267200,
      "updated_at": 1741267200,
      "updated_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
      "indexing_at": 1741267200,
      "completed_at": 1741267200,
      "error": null,
      "stopped_at": null,
      "child_chunks": [],
      "attachments": [],
      "summary": null
    }
  ],
  "doc_form": "text_model",
  "total": 1,
  "has_more": false,
  "limit": 20,
  "page": 1
}

Authorizations

Authorization

string

header

required

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

dataset_id

string<uuid>

required

Knowledge base ID, from List Knowledge Bases. For a scoped key, copy the ID from the Dify URL.

document_id

string<uuid>

required

Document ID. Obtain it from List Documents.

Query Parameters

page

integer

default:1

Page number.

Required range: x >= 1

limit

integer

default:20

Number of items per page. Server caps at 100.

Required range: x >= 1

status

string[]

Filter chunks by indexing status, e.g. completed, indexing, error.

keyword

string

Search keyword.

Response

List of chunks.

data

object[]

List of chunks.

Show child attributes

doc_form

string

Document chunking mode used by this document.

total

integer

Total number of matching chunks.

has_more

boolean

Whether more items exist on the next page.

limit

integer

Number of items per page.

page

integer

Current page number.

Guides

App APIs

Knowledge APIs

Authorizations

Path Parameters

Query Parameters

Response