Update Document by Text
Updates a document’s text content, name, or processing configuration. Re-indexes the document when its text changes.
curl --request POST \
--url https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"doc_language": "English",
"name": "<string>",
"text": "<string>"
}
'import requests
url = "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text"
payload = {
"doc_language": "English",
"name": "<string>",
"text": "<string>"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({doc_language: 'English', name: '<string>', text: '<string>'})
};
fetch('https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text', 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}/update-by-text",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'doc_language' => 'English',
'name' => '<string>',
'text' => '<string>'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text"
payload := strings.NewReader("{\n \"doc_language\": \"English\",\n \"name\": \"<string>\",\n \"text\": \"<string>\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"doc_language\": \"English\",\n \"name\": \"<string>\",\n \"text\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"doc_language\": \"English\",\n \"name\": \"<string>\",\n \"text\": \"<string>\"\n}"
response = http.request(request)
puts response.read_body{
"batch": "20250306150245647595",
"document": {
"archived": false,
"created_at": 1741267200,
"created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
"created_from": "api",
"data_source_detail_dict": {
"upload_file": {
"created_at": 1741267200,
"created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
"extension": "txt",
"id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
"mime_type": "text/plain",
"name": "guide.txt",
"size": 2048
}
},
"data_source_info": {
"upload_file_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
},
"data_source_type": "upload_file",
"dataset_process_rule_id": "e1f2a3b4-c5d6-7890-ef12-345678901234",
"disabled_at": null,
"disabled_by": null,
"display_status": "available",
"doc_form": "text_model",
"doc_metadata": [],
"enabled": true,
"error": null,
"hit_count": 0,
"id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
"indexing_status": "completed",
"name": "guide.txt",
"need_summary": false,
"position": 1,
"summary_index_status": null,
"tokens": 512,
"word_count": 350
}
}Authorizations
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 ID, from List Knowledge Bases. For a scoped key, copy the ID from the Dify URL.
Document ID. From List Documents.
Body
Chunk structure: text_model for standard text chunking, hierarchical_model for parent-child chunks, qa_model for question-answer pairs.
Must match the knowledge base's existing chunk structure. When omitted, the knowledge base's existing structure is used, or text_model if it doesn't have one yet.
text_model, hierarchical_model, qa_model Document text content.
Was this page helpful?
curl --request POST \
--url https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"doc_language": "English",
"name": "<string>",
"text": "<string>"
}
'import requests
url = "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text"
payload = {
"doc_language": "English",
"name": "<string>",
"text": "<string>"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({doc_language: 'English', name: '<string>', text: '<string>'})
};
fetch('https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text', 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}/update-by-text",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => json_encode([
'doc_language' => 'English',
'name' => '<string>',
'text' => '<string>'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: application/json"
],
]);
$response = curl_exec($curl);
$err = curl_error($curl);
curl_close($curl);
if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text"
payload := strings.NewReader("{\n \"doc_language\": \"English\",\n \"name\": \"<string>\",\n \"text\": \"<string>\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.post("https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"doc_language\": \"English\",\n \"name\": \"<string>\",\n \"text\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"doc_language\": \"English\",\n \"name\": \"<string>\",\n \"text\": \"<string>\"\n}"
response = http.request(request)
puts response.read_body{
"batch": "20250306150245647595",
"document": {
"archived": false,
"created_at": 1741267200,
"created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
"created_from": "api",
"data_source_detail_dict": {
"upload_file": {
"created_at": 1741267200,
"created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
"extension": "txt",
"id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
"mime_type": "text/plain",
"name": "guide.txt",
"size": 2048
}
},
"data_source_info": {
"upload_file_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
},
"data_source_type": "upload_file",
"dataset_process_rule_id": "e1f2a3b4-c5d6-7890-ef12-345678901234",
"disabled_at": null,
"disabled_by": null,
"display_status": "available",
"doc_form": "text_model",
"doc_metadata": [],
"enabled": true,
"error": null,
"hit_count": 0,
"id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
"indexing_status": "completed",
"name": "guide.txt",
"need_summary": false,
"position": 1,
"summary_index_status": null,
"tokens": 512,
"word_count": 350
}
}