Create Document by Text

Creates a document in a knowledge base from raw text. Indexing runs asynchronously; track it with the returned batch ID via Get Document Indexing Status.

POST /datasets/{dataset_id}/document/create-by-text

Create Document by Text

cURL

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

200

success

{
  "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

Authorization · string · header · required

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

dataset_id · string<uuid> · required

Knowledge base ID. From List Knowledge Bases.

Body

application/json

name · string · required

Document name.

text · string · required

Document text content.

indexing_technique · enum<string>

Required when adding the first document to a knowledge base. Subsequent documents inherit the knowledge base's indexing technique if omitted. high_quality uses embedding models for precise search; economy uses keyword-based indexing.

Available options: high_quality, economy

doc_form · enum<string> · default: text_model

text_model for standard text chunking, hierarchical_model for parent-child chunk structure, qa_model for question-answer pair extraction.

Available options: text_model, hierarchical_model, qa_model

doc_language · string · default: English

Language of the document for processing optimization.

process_rule · object

Processing rules for chunking.

Show child attributes

retrieval_model · object

Controls how chunks are searched and ranked when querying this knowledge base.

Show child attributes

embedding_model · string

Embedding model name. Use the model field from Get Available Models with model_type=text-embedding.

embedding_model_provider · string

Embedding model provider. Use the provider field from Get Available Models with model_type=text-embedding.

original_document_id · string

Original document ID for versioning. Get it from List Documents.

Response

200

application/json

Document created successfully.

document · object

Show child attributes

batch · string

Batch ID for tracking indexing progress.