从文件创建文档

POST

datasets

{dataset_id}

document

create-by-file

从文件创建文档

curl --request POST \
  --url https://{api_base_url}/datasets/{dataset_id}/document/create-by-file \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form 'data={"indexing_technique":"high_quality","doc_form":"text_model","doc_language":"English","process_rule":{"mode":"automatic"}}'

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"
  ],
]);

$response = curl_exec($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>")

	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>")
  .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.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

{
  "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": "indexing",
    "doc_form": "text_model",
    "doc_metadata": [],
    "enabled": true,
    "error": null,
    "hit_count": 0,
    "id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
    "indexing_status": "indexing",
    "name": "guide.txt",
    "need_summary": false,
    "position": 1,
    "summary_index_status": null,
    "tokens": 0,
    "word_count": 0
  }
}

Authorizations

Authorization

string

header

required

每个请求都通过 API Key 认证：Authorization: Bearer {API_KEY}。应用接口使用应用 API Key，知识库接口使用知识库 API Key（快速开始）。

API Key 应保存在服务端，切勿嵌入客户端代码。缺失或无效的 Key 会返回 HTTP 401（unauthorized）。

Path Parameters

dataset_id

string<uuid>

required

知识库 ID，通过获取知识库列表获取。使用限定范围的密钥时，从 Dify 页面 URL 复制 ID。

Body

multipart/form-data

file

required

要上传的文件，默认上限 15 MB。

自部署可通过 UPLOAD_FILE_SIZE_LIMIT 环境变量调整。Dify Cloud 的 Professional 和 Team 套餐上限为 50 MB。

data

string

包含配置信息的 JSON 字符串。接受与从文本创建文档相同的字段（indexing_technique、doc_form、doc_language、process_rule、retrieval_model、embedding_model、embedding_model_provider），但不包括 name 和 text。

Example:

"{\"indexing_technique\":\"high_quality\",\"doc_form\":\"text_model\",\"doc_language\":\"English\",\"process_rule\":{\"mode\":\"automatic\"}}"

Response

文档创建成功。

batch

string

用于跟踪索引进度的批次 ID。

document

object

Show child attributes

Last modified on September 22, 2026

从文件创建文档

curl --request POST \
  --url https://{api_base_url}/datasets/{dataset_id}/document/create-by-file \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form 'data={"indexing_technique":"high_quality","doc_form":"text_model","doc_language":"English","process_rule":{"mode":"automatic"}}'

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"
  ],
]);

$response = curl_exec($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>")

	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>")
  .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.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

{
  "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": "indexing",
    "doc_form": "text_model",
    "doc_metadata": [],
    "enabled": true,
    "error": null,
    "hit_count": 0,
    "id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
    "indexing_status": "indexing",
    "name": "guide.txt",
    "need_summary": false,
    "position": 1,
    "summary_index_status": null,
    "tokens": 0,
    "word_count": 0
  }
}