Documents
Create Document by File
Creates a document in a knowledge base from an uploaded file. Common formats such as PDF, TXT, and DOCX are supported. Indexing runs asynchronously; track it with the returned batch ID via Get Document Indexing Status.
POST
/
datasets
/
{dataset_id}
/
document
/
create-by-file
cURL
curl --request POST \
--url 'https://{api_base_url}/datasets/{dataset_id}/document/create-by-file' \
--header 'Authorization: Bearer {api_key}' \
--form 'file=@quarterly-report.pdf' \
--form 'data={"indexing_technique":"high_quality","process_rule":{"mode":"automatic"}};type=application/json'import requests
url = "https://{api_base_url}/datasets/{dataset_id}/document/create-by-file"
files = { "file": ("example-file", open("example-file", "rb")) }
payload = { "data": "{\"indexing_technique\":\"high_quality\",\"doc_form\":\"text_model\",\"doc_language\":\"English\",\"process_rule\":{\"mode\":\"automatic\"}}" }
headers = {"Authorization": "Bearer <token>"}
response = requests.post(url, data=payload, files=files, headers=headers)
print(response.text)const form = new FormData();
form.append('file', '<string>');
form.append('data', '{"indexing_technique":"high_quality","doc_form":"text_model","doc_language":"English","process_rule":{"mode":"automatic"}}');
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
options.body = form;
fetch('https://{api_base_url}/datasets/{dataset_id}/document/create-by-file', 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}/document/create-by-file",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"data\"\r\n\r\n{\"indexing_technique\":\"high_quality\",\"doc_form\":\"text_model\",\"doc_language\":\"English\",\"process_rule\":{\"mode\":\"automatic\"}}\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: multipart/form-data; boundary=---011000010111000001101001"
],
]);
$response = curl_exec($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}/document/create-by-file"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"data\"\r\n\r\n{\"indexing_technique\":\"high_quality\",\"doc_form\":\"text_model\",\"doc_language\":\"English\",\"process_rule\":{\"mode\":\"automatic\"}}\r\n-----011000010111000001101001--")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
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}/document/create-by-file")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"data\"\r\n\r\n{\"indexing_technique\":\"high_quality\",\"doc_form\":\"text_model\",\"doc_language\":\"English\",\"process_rule\":{\"mode\":\"automatic\"}}\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://{api_base_url}/datasets/{dataset_id}/document/create-by-file")
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"] = 'multipart/form-data; boundary=---011000010111000001101001'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"data\"\r\n\r\n{\"indexing_technique\":\"high_quality\",\"doc_form\":\"text_model\",\"doc_language\":\"English\",\"process_rule\":{\"mode\":\"automatic\"}}\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"document": {
"id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
"position": 1,
"data_source_type": "upload_file",
"data_source_info": {
"upload_file_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
},
"data_source_detail_dict": {
"upload_file": {
"id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
"name": "guide.txt",
"size": 2048,
"extension": "txt",
"mime_type": "text/plain",
"created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
"created_at": 1741267200
}
},
"dataset_process_rule_id": "e1f2a3b4-c5d6-7890-ef12-345678901234",
"name": "guide.txt",
"created_from": "api",
"created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
"created_at": 1741267200,
"tokens": 0,
"indexing_status": "indexing",
"error": null,
"enabled": true,
"disabled_at": null,
"disabled_by": null,
"archived": false,
"display_status": "indexing",
"word_count": 0,
"hit_count": 0,
"doc_form": "text_model",
"doc_metadata": [],
"summary_index_status": null,
"need_summary": false
},
"batch": "20250306150245647595"
}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.
Body
multipart/form-data
File to upload, capped at 15 MB by default.
Self-hosted deployments adjust the limit with the UPLOAD_FILE_SIZE_LIMIT environment variable. On Dify Cloud, Professional and Team plans raise the cap to 50 MB.
JSON string containing configuration. Accepts the same fields as Create Document by Text (indexing_technique, doc_form, doc_language, process_rule, retrieval_model, embedding_model, embedding_model_provider) except name and text.
Example:
"{\"indexing_technique\":\"high_quality\",\"doc_form\":\"text_model\",\"doc_language\":\"English\",\"process_rule\":{\"mode\":\"automatic\"}}"
Last modified on August 10, 2026
Was this page helpful?
⌘I
cURL
curl --request POST \
--url 'https://{api_base_url}/datasets/{dataset_id}/document/create-by-file' \
--header 'Authorization: Bearer {api_key}' \
--form 'file=@quarterly-report.pdf' \
--form 'data={"indexing_technique":"high_quality","process_rule":{"mode":"automatic"}};type=application/json'import requests
url = "https://{api_base_url}/datasets/{dataset_id}/document/create-by-file"
files = { "file": ("example-file", open("example-file", "rb")) }
payload = { "data": "{\"indexing_technique\":\"high_quality\",\"doc_form\":\"text_model\",\"doc_language\":\"English\",\"process_rule\":{\"mode\":\"automatic\"}}" }
headers = {"Authorization": "Bearer <token>"}
response = requests.post(url, data=payload, files=files, headers=headers)
print(response.text)const form = new FormData();
form.append('file', '<string>');
form.append('data', '{"indexing_technique":"high_quality","doc_form":"text_model","doc_language":"English","process_rule":{"mode":"automatic"}}');
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
options.body = form;
fetch('https://{api_base_url}/datasets/{dataset_id}/document/create-by-file', 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}/document/create-by-file",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"data\"\r\n\r\n{\"indexing_technique\":\"high_quality\",\"doc_form\":\"text_model\",\"doc_language\":\"English\",\"process_rule\":{\"mode\":\"automatic\"}}\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: multipart/form-data; boundary=---011000010111000001101001"
],
]);
$response = curl_exec($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}/document/create-by-file"
payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"data\"\r\n\r\n{\"indexing_technique\":\"high_quality\",\"doc_form\":\"text_model\",\"doc_language\":\"English\",\"process_rule\":{\"mode\":\"automatic\"}}\r\n-----011000010111000001101001--")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Authorization", "Bearer <token>")
req.Header.Add("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
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}/document/create-by-file")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"data\"\r\n\r\n{\"indexing_technique\":\"high_quality\",\"doc_form\":\"text_model\",\"doc_language\":\"English\",\"process_rule\":{\"mode\":\"automatic\"}}\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://{api_base_url}/datasets/{dataset_id}/document/create-by-file")
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"] = 'multipart/form-data; boundary=---011000010111000001101001'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"data\"\r\n\r\n{\"indexing_technique\":\"high_quality\",\"doc_form\":\"text_model\",\"doc_language\":\"English\",\"process_rule\":{\"mode\":\"automatic\"}}\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"document": {
"id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
"position": 1,
"data_source_type": "upload_file",
"data_source_info": {
"upload_file_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
},
"data_source_detail_dict": {
"upload_file": {
"id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
"name": "guide.txt",
"size": 2048,
"extension": "txt",
"mime_type": "text/plain",
"created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
"created_at": 1741267200
}
},
"dataset_process_rule_id": "e1f2a3b4-c5d6-7890-ef12-345678901234",
"name": "guide.txt",
"created_from": "api",
"created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
"created_at": 1741267200,
"tokens": 0,
"indexing_status": "indexing",
"error": null,
"enabled": true,
"disabled_at": null,
"disabled_by": null,
"archived": false,
"display_status": "indexing",
"word_count": 0,
"hit_count": 0,
"doc_form": "text_model",
"doc_metadata": [],
"summary_index_status": null,
"need_summary": false
},
"batch": "20250306150245647595"
}