Upload Knowledge File With Stream
curl --request POST \
--url https://api-spectra.duplik.cn/v1/knowledge/{knowledge_id}/files/form \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: multipart/form-data' \
--form file='@example-file' \
--form 'folder_id=<string>' \
--form process_document=true \
--form 'document_metadata=<string>' \
--form 'document_setting=<string>'import requests
url = "https://api-spectra.duplik.cn/v1/knowledge/{knowledge_id}/files/form"
files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
"folder_id": "<string>",
"process_document": "true",
"document_metadata": "<string>",
"document_setting": "<string>"
}
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('folder_id', '<string>');
form.append('process_document', 'true');
form.append('document_metadata', '<string>');
form.append('document_setting', '<string>');
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
options.body = form;
fetch('https://api-spectra.duplik.cn/v1/knowledge/{knowledge_id}/files/form', 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-spectra.duplik.cn/v1/knowledge/{knowledge_id}/files/form",
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=\"folder_id\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"process_document\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_setting\"\r\n\r\n<string>\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-spectra.duplik.cn/v1/knowledge/{knowledge_id}/files/form"
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=\"folder_id\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"process_document\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_setting\"\r\n\r\n<string>\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-spectra.duplik.cn/v1/knowledge/{knowledge_id}/files/form")
.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=\"folder_id\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"process_document\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_setting\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://api-spectra.duplik.cn/v1/knowledge/{knowledge_id}/files/form")
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=\"folder_id\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"process_document\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_setting\"\r\n\r\n<string>\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"org_id": "<string>",
"user_id": "<string>",
"dataset_id": "<string>",
"file_id": "<string>",
"document_id": "<string>",
"created_at": 123,
"updated_at": 123,
"overall_summarize_enabled": true,
"smart_indexing_mode": 0,
"smart_indexing_enabled": true,
"split_media_enabled": true,
"pdf_parsing_mode": 2,
"pdf_parsing_element_types": [
1,
2
],
"read_pdf_pages": "<string>",
"audio_parsing_mode": 123,
"audio_chunk_mode": 1,
"name": "<string>",
"document_type": 1,
"next_step": true,
"llm": {},
"metadata_info": {},
"task_priority": 123,
"description": "",
"summary": "",
"step_status": 100,
"status": 1,
"process_status": 100,
"version": 2,
"splitter_type": 1,
"splitter": {},
"sections": [],
"content_text": "<string>",
"trim_text": true
}{
"code": 123,
"message": "<string>"
}{
"code": 123,
"message": "<string>"
}{
"code": 123,
"message": "<string>"
}Knowledge
Upload Knowledge File With Stream
Upload one document as a raw file stream (multipart/form-data)
POST
/
v1
/
knowledge
/
{knowledge_id}
/
files
/
form
Upload Knowledge File With Stream
curl --request POST \
--url https://api-spectra.duplik.cn/v1/knowledge/{knowledge_id}/files/form \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: multipart/form-data' \
--form file='@example-file' \
--form 'folder_id=<string>' \
--form process_document=true \
--form 'document_metadata=<string>' \
--form 'document_setting=<string>'import requests
url = "https://api-spectra.duplik.cn/v1/knowledge/{knowledge_id}/files/form"
files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
"folder_id": "<string>",
"process_document": "true",
"document_metadata": "<string>",
"document_setting": "<string>"
}
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('folder_id', '<string>');
form.append('process_document', 'true');
form.append('document_metadata', '<string>');
form.append('document_setting', '<string>');
const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};
options.body = form;
fetch('https://api-spectra.duplik.cn/v1/knowledge/{knowledge_id}/files/form', 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-spectra.duplik.cn/v1/knowledge/{knowledge_id}/files/form",
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=\"folder_id\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"process_document\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_setting\"\r\n\r\n<string>\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-spectra.duplik.cn/v1/knowledge/{knowledge_id}/files/form"
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=\"folder_id\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"process_document\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_setting\"\r\n\r\n<string>\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-spectra.duplik.cn/v1/knowledge/{knowledge_id}/files/form")
.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=\"folder_id\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"process_document\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_setting\"\r\n\r\n<string>\r\n-----011000010111000001101001--")
.asString();require 'uri'
require 'net/http'
url = URI("https://api-spectra.duplik.cn/v1/knowledge/{knowledge_id}/files/form")
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=\"folder_id\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"process_document\"\r\n\r\ntrue\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_metadata\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"document_setting\"\r\n\r\n<string>\r\n-----011000010111000001101001--"
response = http.request(request)
puts response.read_body{
"org_id": "<string>",
"user_id": "<string>",
"dataset_id": "<string>",
"file_id": "<string>",
"document_id": "<string>",
"created_at": 123,
"updated_at": 123,
"overall_summarize_enabled": true,
"smart_indexing_mode": 0,
"smart_indexing_enabled": true,
"split_media_enabled": true,
"pdf_parsing_mode": 2,
"pdf_parsing_element_types": [
1,
2
],
"read_pdf_pages": "<string>",
"audio_parsing_mode": 123,
"audio_chunk_mode": 1,
"name": "<string>",
"document_type": 1,
"next_step": true,
"llm": {},
"metadata_info": {},
"task_priority": 123,
"description": "",
"summary": "",
"step_status": 100,
"status": 1,
"process_status": 100,
"version": 2,
"splitter_type": 1,
"splitter": {},
"sections": [],
"content_text": "<string>",
"trim_text": true
}{
"code": 123,
"message": "<string>"
}{
"code": 123,
"message": "<string>"
}{
"code": 123,
"message": "<string>"
}Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
Knowledge base ID
Body
multipart/form-data
File content. The type is decided by the file name extension (case-insensitive), not the Content-Type. Supported: pdf / doc / docx / ppt / pptx, xlsx / xls / csv, txt / md / markdown / html / htm / xml, png / jpg, and mp3 / mp4 / m4a / wav / webm / mpga / mpeg / mov / flv. Any other extension returns 400.
Target folder ID. Defaults to the knowledge base root folder
Whether to start the processing pipeline right away
Document metadata as a JSON string, merged into the document's metadata_info. Common fields: title, entity_names (tags written as "key:value" that drive metadata pre-filtering at retrieval time), time_periods, and custom_data (free-form key-values that are stored, indexed and returned but never used for filtering). A non-empty entity_names skips LLM metadata generation entirely, so title and time_periods are no longer produced automatically — pass title alongside it or the title stays empty. folder_id, folder_ids, url, source_url, file_path, file_size, file_name and file_type are filled in by the server from the uploaded file and are ignored if supplied. Invalid JSON is logged server-side and treated as if the field were absent; the request still succeeds. Example: {"title":"SY500 Service Manual","entity_names":["model:SY500"]}
Processing settings for this upload as a JSON string. Omit it and every setting follows the knowledge base (pdf_parsing_mode, smart_indexing_mode, smart_indexing_enabled, overall_summarize_enabled, split_media_enabled, audio_parsing_mode, audio_chunk_mode, pdf_parsing_element_types). Supplying it is all-or-nothing rather than a patch: the settings are built from your JSON alone, so any field you leave out falls back to its model default instead of the knowledge base — pass {"pdf_parsing_mode":2} on its own and smart_indexing_mode becomes 0 and overall_summarize_enabled becomes true. Chunking (chunk size, overlap, separators) is never part of this field and always comes from the knowledge base. Smart indexing runs only when smart_indexing_enabled is true AND smart_indexing_mode is 2 (advanced); leaving it off is recommended. Invalid JSON is logged and treated as absent. Example: {"pdf_parsing_mode":2,"smart_indexing_enabled":false}
Response
Successful Response
Maximum string length:
20Maximum string length:
20Generate an overall summary. Boolean
Smart indexing mode. 0: disabled (recommended), 1: standard, 2: advanced
Enable smart indexing. Boolean. Takes effect only together with smart_indexing_mode 2 (advanced); leaving it false is recommended unless the corpus needs it, as it adds noticeable processing time and token cost
Generate media segments. Boolean
PDF parsing mode. 1: page, 2: section (recommended), 3: section v2
pdf parsing element list, eg: [1, 2]. 1: table, 2: image, 3: formula
read pdf pages, Example: '1,3,4' or '1,4-end' or 'all'
audio parsing mode, 1: transcript, 2: speaker diarization
Maximum string length:
256next step
task priority
Maximum string length:
512