文档
从文本创建文档
通过纯文本内容创建文档。文档将异步处理——使用返回的 batch ID 配合 获取文档嵌入状态（进度） 跟踪进度。
POST
/
datasets
/
{dataset_id}
/
document
/
create-by-text
从文本创建文档
curl --request POST \
--url https://{api_base_url}/datasets/{dataset_id}/document/create-by-text \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"name": "<string>",
"text": "<string>",
"doc_form": "text_model",
"doc_language": "English",
"embedding_model": "<string>",
"embedding_model_provider": "<string>",
"original_document_id": "<string>"
}
'import requests
url = "https://{api_base_url}/datasets/{dataset_id}/document/create-by-text"
payload = {
"name": "<string>",
"text": "<string>",
"doc_form": "text_model",
"doc_language": "English",
"embedding_model": "<string>",
"embedding_model_provider": "<string>",
"original_document_id": "<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({
name: '<string>',
text: '<string>',
doc_form: 'text_model',
doc_language: 'English',
embedding_model: '<string>',
embedding_model_provider: '<string>',
original_document_id: '<string>'
})
};
fetch('https://{api_base_url}/datasets/{dataset_id}/document/create-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}/document/create-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([
'name' => '<string>',
'text' => '<string>',
'doc_form' => 'text_model',
'doc_language' => 'English',
'embedding_model' => '<string>',
'embedding_model_provider' => '<string>',
'original_document_id' => '<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}/document/create-by-text"
payload := strings.NewReader("{\n \"name\": \"<string>\",\n \"text\": \"<string>\",\n \"doc_form\": \"text_model\",\n \"doc_language\": \"English\",\n \"embedding_model\": \"<string>\",\n \"embedding_model_provider\": \"<string>\",\n \"original_document_id\": \"<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}/document/create-by-text")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"name\": \"<string>\",\n \"text\": \"<string>\",\n \"doc_form\": \"text_model\",\n \"doc_language\": \"English\",\n \"embedding_model\": \"<string>\",\n \"embedding_model_provider\": \"<string>\",\n \"original_document_id\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://{api_base_url}/datasets/{dataset_id}/document/create-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 \"name\": \"<string>\",\n \"text\": \"<string>\",\n \"doc_form\": \"text_model\",\n \"doc_language\": \"English\",\n \"embedding_model\": \"<string>\",\n \"embedding_model_provider\": \"<string>\",\n \"original_document_id\": \"<string>\"\n}"
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
API Key 认证。对于所有 API 请求，请在 Authorization HTTP 头中包含您的 API Key，并加上 Bearer 前缀。示例：Authorization: Bearer {API_KEY}。强烈建议将 API Key 存储在服务端，不要在客户端共享或存储，以避免 API Key 泄漏导致严重后果。
Path Parameters
知识库 ID。
Body
application/json
文档名称。
文档文本内容。
向知识库添加首个文档时必填。后续文档如果省略此字段，将继承知识库的索引方式。high_quality 使用嵌入模型进行精确搜索；economy 使用基于关键词的索引。
Available options:
high_quality, economy text_model 为标准文本分段，hierarchical_model 为父子分段结构，qa_model 为问答对提取。
Available options:
text_model, hierarchical_model, qa_model 用于处理优化的文档语言。
分块处理规则。
Show child attributes
Show child attributes
检索模型配置。控制查询此知识库时如何搜索和排序分段。
Show child attributes
Show child attributes
用于版本控制的原始文档 ID。
Last modified on June 29, 2026
Was this page helpful?
⌘I
从文本创建文档
curl --request POST \
--url https://{api_base_url}/datasets/{dataset_id}/document/create-by-text \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"name": "<string>",
"text": "<string>",
"doc_form": "text_model",
"doc_language": "English",
"embedding_model": "<string>",
"embedding_model_provider": "<string>",
"original_document_id": "<string>"
}
'import requests
url = "https://{api_base_url}/datasets/{dataset_id}/document/create-by-text"
payload = {
"name": "<string>",
"text": "<string>",
"doc_form": "text_model",
"doc_language": "English",
"embedding_model": "<string>",
"embedding_model_provider": "<string>",
"original_document_id": "<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({
name: '<string>',
text: '<string>',
doc_form: 'text_model',
doc_language: 'English',
embedding_model: '<string>',
embedding_model_provider: '<string>',
original_document_id: '<string>'
})
};
fetch('https://{api_base_url}/datasets/{dataset_id}/document/create-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}/document/create-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([
'name' => '<string>',
'text' => '<string>',
'doc_form' => 'text_model',
'doc_language' => 'English',
'embedding_model' => '<string>',
'embedding_model_provider' => '<string>',
'original_document_id' => '<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}/document/create-by-text"
payload := strings.NewReader("{\n \"name\": \"<string>\",\n \"text\": \"<string>\",\n \"doc_form\": \"text_model\",\n \"doc_language\": \"English\",\n \"embedding_model\": \"<string>\",\n \"embedding_model_provider\": \"<string>\",\n \"original_document_id\": \"<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}/document/create-by-text")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"name\": \"<string>\",\n \"text\": \"<string>\",\n \"doc_form\": \"text_model\",\n \"doc_language\": \"English\",\n \"embedding_model\": \"<string>\",\n \"embedding_model_provider\": \"<string>\",\n \"original_document_id\": \"<string>\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://{api_base_url}/datasets/{dataset_id}/document/create-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 \"name\": \"<string>\",\n \"text\": \"<string>\",\n \"doc_form\": \"text_model\",\n \"doc_language\": \"English\",\n \"embedding_model\": \"<string>\",\n \"embedding_model_provider\": \"<string>\",\n \"original_document_id\": \"<string>\"\n}"
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"
}