文档与分段
获取文档文件
返回一个文档文件,即文档背后存储的文件,包括其 version 和 parser_status。
GET
/
knowledge-fs
/
spaces
/
{knowledge_base_id}
/
documents
/
{document_file_id}
获取文档文件
curl --request GET \
--url https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_file_id} \
--header 'Authorization: Bearer <token>'import requests
url = "https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_file_id}"
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}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_file_id}', 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}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_file_id}",
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}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_file_id}"
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))
}HttpResponse<String> response = Unirest.get("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_file_id}")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_file_id}")
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{
"created_at": "2026-09-03T10:02:11Z",
"filename": "handbook.pdf",
"id": "6ec0bd7f-11c0-43da-975e-2a8ad9ebae0b",
"knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
"metadata": {},
"mime_type": "application/pdf",
"object_key": "1a7c9e40-2b3d-4f56-8a90-b1c2d3e4f506/spaces/9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b/documents/6ec0bd7f-11c0-43da-975e-2a8ad9ebae0b/handbook.pdf",
"parser_status": "parsed",
"sha256": "9f86d081884c7d659a2feaa0c55ad015a3bf4f1b2b0b822cd15d6c15b0f00a08",
"size_bytes": 482113,
"source_id": null,
"updated_at": null,
"version": 1
}Authorizations
Path Parameters
知识库 ID:即知识库 API 访问 对话框中所示服务 API 端点的最后一段(…/knowledge-fs/spaces/<knowledge base ID>),也是地址栏中 /datasets/new/ 之后的那一段。
Response
文档文件。
文件存储时间,ISO 8601 格式。
原始文件名。
文档文件 ID。与在 Dify 中打开文档时地址栏里的文档 ID 不同。
知识库的内部 ID,并非路径中的知识库 ID。
上传或导入文件时随文件记录的元数据。
文件的 MIME 类型。
文件在对象存储中的键。此 API 中没有返回文件内容的操作。
该版本文件的解析状态:pending、parsed 或 failed。解析是索引的一个步骤。parsed 的文件也可能没有大纲和分段。
文件内容的 SHA-256 哈希值,十六进制编码。
文件大小,单位为字节。
文件导入来源的数据源 ID。上传的文件为 null。
文件记录最后变更时间,ISO 8601 格式。创建后未变更时为 null。
Was this page helpful?
⌘I
获取文档文件
curl --request GET \
--url https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_file_id} \
--header 'Authorization: Bearer <token>'import requests
url = "https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_file_id}"
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}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_file_id}', 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}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_file_id}",
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}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_file_id}"
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))
}HttpResponse<String> response = Unirest.get("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_file_id}")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_file_id}")
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{
"created_at": "2026-09-03T10:02:11Z",
"filename": "handbook.pdf",
"id": "6ec0bd7f-11c0-43da-975e-2a8ad9ebae0b",
"knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
"metadata": {},
"mime_type": "application/pdf",
"object_key": "1a7c9e40-2b3d-4f56-8a90-b1c2d3e4f506/spaces/9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b/documents/6ec0bd7f-11c0-43da-975e-2a8ad9ebae0b/handbook.pdf",
"parser_status": "parsed",
"sha256": "9f86d081884c7d659a2feaa0c55ad015a3bf4f1b2b0b822cd15d6c15b0f00a08",
"size_bytes": 482113,
"source_id": null,
"updated_at": null,
"version": 1
}