Trigger document processing

curl --request POST \
  --url https://api.example.com/api/v1/knowledge-base/process-document \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "document_uuid": "<string>",
  "s3_key": "<string>",
  "embedding_service": "openai"
}
'

import requests

url = "https://api.example.com/api/v1/knowledge-base/process-document"

payload = {
    "document_uuid": "<string>",
    "s3_key": "<string>",
    "embedding_service": "openai"
}
headers = {
    "X-API-Key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'X-API-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({document_uuid: '<string>', s3_key: '<string>', embedding_service: 'openai'})
};

fetch('https://api.example.com/api/v1/knowledge-base/process-document', 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/knowledge-base/process-document",
  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([
    'document_uuid' => '<string>',
    's3_key' => '<string>',
    'embedding_service' => 'openai'
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "X-API-Key: <api-key>"
  ],
]);

$response = curl_exec($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/knowledge-base/process-document"

	payload := strings.NewReader("{\n  \"document_uuid\": \"<string>\",\n  \"s3_key\": \"<string>\",\n  \"embedding_service\": \"openai\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("X-API-Key", "<api-key>")
	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/knowledge-base/process-document")
  .header("X-API-Key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"document_uuid\": \"<string>\",\n  \"s3_key\": \"<string>\",\n  \"embedding_service\": \"openai\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/api/v1/knowledge-base/process-document")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"document_uuid\": \"<string>\",\n  \"s3_key\": \"<string>\",\n  \"embedding_service\": \"openai\"\n}"

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

{
  "id": 123,
  "document_uuid": "<string>",
  "filename": "<string>",
  "file_size_bytes": 123,
  "file_hash": "<string>",
  "mime_type": "<string>",
  "processing_status": "<string>",
  "total_chunks": 123,
  "custom_metadata": {},
  "docling_metadata": {},
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "organization_id": 123,
  "created_by": 123,
  "is_active": true,
  "processing_error": "<string>",
  "source_url": "<string>"
}

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

Knowledge Base

Trigger document processing

Trigger asynchronous processing of an uploaded document.

This endpoint should be called after successfully uploading a file to the presigned URL. It will:

Create a document record in the database with the specified UUID
Enqueue a background task to process the document (chunking and embedding)

The document status will be updated from ‘pending’ -> ‘processing’ -> ‘completed’ or ‘failed’.

Embedding Services:

openai (default): High-quality 1536-dimensional embeddings (requires OPENAI_API_KEY)
sentence_transformer: Free, offline-capable, 384-dimensional embeddings

Access Control:

Users can only process documents in their organization.

POST

api

knowledge-base

process-document

Trigger document processing

curl --request POST \
  --url https://api.example.com/api/v1/knowledge-base/process-document \
  --header 'Content-Type: application/json' \
  --header 'X-API-Key: <api-key>' \
  --data '
{
  "document_uuid": "<string>",
  "s3_key": "<string>",
  "embedding_service": "openai"
}
'

import requests

url = "https://api.example.com/api/v1/knowledge-base/process-document"

payload = {
    "document_uuid": "<string>",
    "s3_key": "<string>",
    "embedding_service": "openai"
}
headers = {
    "X-API-Key": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'X-API-Key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({document_uuid: '<string>', s3_key: '<string>', embedding_service: 'openai'})
};

fetch('https://api.example.com/api/v1/knowledge-base/process-document', 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/knowledge-base/process-document",
  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([
    'document_uuid' => '<string>',
    's3_key' => '<string>',
    'embedding_service' => 'openai'
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "X-API-Key: <api-key>"
  ],
]);

$response = curl_exec($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/knowledge-base/process-document"

	payload := strings.NewReader("{\n  \"document_uuid\": \"<string>\",\n  \"s3_key\": \"<string>\",\n  \"embedding_service\": \"openai\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("X-API-Key", "<api-key>")
	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/knowledge-base/process-document")
  .header("X-API-Key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"document_uuid\": \"<string>\",\n  \"s3_key\": \"<string>\",\n  \"embedding_service\": \"openai\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/api/v1/knowledge-base/process-document")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["X-API-Key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"document_uuid\": \"<string>\",\n  \"s3_key\": \"<string>\",\n  \"embedding_service\": \"openai\"\n}"

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

{
  "id": 123,
  "document_uuid": "<string>",
  "filename": "<string>",
  "file_size_bytes": 123,
  "file_hash": "<string>",
  "mime_type": "<string>",
  "processing_status": "<string>",
  "total_chunks": 123,
  "custom_metadata": {},
  "docling_metadata": {},
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "organization_id": 123,
  "created_by": 123,
  "is_active": true,
  "processing_error": "<string>",
  "source_url": "<string>"
}

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

Authorizations

X-API-Key

string

header

required

Your organization's API key (account in the bottom-left of the dashboard → Brosbots API).

Headers

authorization

string | null

X-API-Key

string | null

Body

application/json

Request schema for triggering document processing.

document_uuid

string

required

Document UUID to process

s3_key

string

required

Storage key of the uploaded file.

embedding_service

enum<string>

default:openai

Embedding service to use for processing. Options: 'openai' (default, 1536-dim, requires API key) or 'sentence_transformer' (free, 384-dim)

Available options:

sentence_transformer,

openai

Response

Successful Response

Response schema for document metadata.

integer

required

document_uuid

string

required

filename

string

required

file_size_bytes

integer

required

file_hash

string

required

mime_type

string

required

processing_status

string

required

total_chunks

integer

required

custom_metadata

object

required

docling_metadata

object

required

created_at

string<date-time>

required

updated_at

string<date-time>

required

organization_id

integer

required

created_by

integer

required

is_active

boolean

required

processing_error

string | null

source_url

string | null

Start

Endpoints

Trigger document processing

Authorizations

Headers

Body

Response