Create Chunks

Create chunks/embeddings from existing content. This endpoint processes uploaded content that was stored without ingestion (ingest=False) and creates vector embeddings for it. Args: request: CreateChunksRequest containing: - content_id: Content ID to process - reader: Reader to use ("native", "langchain", "markitdown", etc.) - force_rechunk: Whether to force re-chunking existing chunks Returns: CreateChunksResponse with processing results Examples: Create chunks for uploaded content: POST /chunks/create { "content_id": "content_123", "reader": "markitdown", "force_rechunk": false } Force re-chunk with different reader: POST /chunks/create { "content_id": "content_123", "reader": "langchain_pdfplumber", "force_rechunk": true }

POST /api/v1/chunks/create

Create Chunks

cURL

curl --request POST \
  --url https://api.example.com/api/v1/chunks/create \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "content_id": "<string>",
  "reader": "native",
  "force_rechunk": false
}
'

import requests

url = "https://api.example.com/api/v1/chunks/create"

payload = {
    "content_id": "<string>",
    "reader": "native",
    "force_rechunk": False
}
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({content_id: '<string>', reader: 'native', force_rechunk: false})
};

fetch('https://api.example.com/api/v1/chunks/create', 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.example.com/api/v1/chunks/create",
  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([
    'content_id' => '<string>',
    'reader' => 'native',
    'force_rechunk' => false
  ]),
  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.example.com/api/v1/chunks/create"

	payload := strings.NewReader("{\n  \"content_id\": \"<string>\",\n  \"reader\": \"native\",\n  \"force_rechunk\": false\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.example.com/api/v1/chunks/create")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"content_id\": \"<string>\",\n  \"reader\": \"native\",\n  \"force_rechunk\": false\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/api/v1/chunks/create")

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  \"content_id\": \"<string>\",\n  \"reader\": \"native\",\n  \"force_rechunk\": false\n}"

response = http.request(request)
puts response.read_body

200

{
  "status": "<string>",
  "message": "<string>",
  "content_ids_processed": [
    "<string>"
  ],
  "content_ids_failed": [
    "<string>"
  ],
  "total_chunks_created": 0
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Headers

X-Workspace-Id · string | null

The workspace ID

Body

application/json

Request to create chunks from existing content.

content_id · string · required

Content ID to create chunks from

reader · string | null · default: native

Reader to use for processing

force_rechunk · boolean · default: false

Force re-chunking even if chunks already exist

Response

200

application/json

Successful Response

Response for chunk creation.

status · string · required

Status of the operation

message · string · required

Summary message

content_ids_processed · string[]

Successfully processed content IDs

content_ids_failed · string[]

Failed content IDs

total_chunks_created · integer · default: 0

Total number of chunks created