Get knowledge document

One knowledge document’s full content — raw_text and body_html — plus every field List knowledge documents omits: error_message, chunk_count, token_count, needs_reembed, file metadata, material_type, and writing-style attachment. Round-trip target for Update knowledge document.

Requires the read:knowledge_base scope.


GET /brands/{brand_id}/knowledge-documents/{document_id}

Authorization

Header	Type	Required
`Authorization`	`Bearer asky_sk_…`	required

Path parameters

Parameter	Type	Required	Description
`brand_id`	`uuid`	required	From List brands
`document_id`	`uuid`	required	From List knowledge documents

Request

cURL


curl --request GET \
  --url 'https://api.askylabs.com/v1/brands/242546de-4cee-4a7d-952e-f6aa60c63ef8/knowledge-documents/b4f7e2a1-9c3d-4e6f-8a1b-2c5d7e9f0a3b' \
  --header 'Authorization: Bearer <api-key>'

Python


import requests
 
url = "https://api.askylabs.com/v1/brands/242546de-4cee-4a7d-952e-f6aa60c63ef8/knowledge-documents/b4f7e2a1-9c3d-4e6f-8a1b-2c5d7e9f0a3b"
 
headers = {"Authorization": "Bearer <api-key>"}
 
response = requests.get(url, headers=headers)
 
print(response.text)

JavaScript


const options = {method: 'GET', headers: {Authorization: 'Bearer <api-key>'}};
 
fetch('https://api.askylabs.com/v1/brands/242546de-4cee-4a7d-952e-f6aa60c63ef8/knowledge-documents/b4f7e2a1-9c3d-4e6f-8a1b-2c5d7e9f0a3b', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

PHP


<?php
 
$curl = curl_init();
 
curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.askylabs.com/v1/brands/242546de-4cee-4a7d-952e-f6aa60c63ef8/knowledge-documents/b4f7e2a1-9c3d-4e6f-8a1b-2c5d7e9f0a3b",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <api-key>"
  ],
]);
 
$response = curl_exec($curl);
$err = curl_error($curl);
 
curl_close($curl);
 
if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

Go


package main
 
import (
    "fmt"
    "net/http"
    "io"
)
 
func main() {
 
    url := "https://api.askylabs.com/v1/brands/242546de-4cee-4a7d-952e-f6aa60c63ef8/knowledge-documents/b4f7e2a1-9c3d-4e6f-8a1b-2c5d7e9f0a3b"
 
    req, _ := http.NewRequest("GET", url, nil)
 
    req.Header.Add("Authorization", "Bearer <api-key>")
 
    res, _ := http.DefaultClient.Do(req)
 
    defer res.Body.Close()
    body, _ := io.ReadAll(res.Body)
 
    fmt.Println(string(body))
 
}

Ruby


require 'uri'
require 'net/http'
 
url = URI("https://api.askylabs.com/v1/brands/242546de-4cee-4a7d-952e-f6aa60c63ef8/knowledge-documents/b4f7e2a1-9c3d-4e6f-8a1b-2c5d7e9f0a3b")
 
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
 
request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <api-key>'
 
response = http.request(request)
puts response.read_body

Response

200


{
  "data": {
    "document": {
      "id": "b4f7e2a1-9c3d-4e6f-8a1b-2c5d7e9f0a3b",
      "brand_id": "242546de-4cee-4a7d-952e-f6aa60c63ef8",
      "title": "Product Positioning FAQ",
      "user_description": "Internal FAQ used to ground content about our differentiation.",
      "source_type": "paste",
      "raw_text": "## What makes us different?\n\nAsky tracks...",
      "body_html": "<h2>What makes us different?</h2><p>Asky tracks...</p>",
      "status": "ready",
      "error_message": null,
      "char_count": 4820,
      "chunk_count": 6,
      "token_count": 1180,
      "needs_reembed": false,
      "file_name": null,
      "page_count": null,
      "file_size_bytes": null,
      "mime_type": null,
      "material_type": null,
      "writing_style_id": null,
      "style_prompt_dismissed": false,
      "created_by": "a1b2c3d4-5e6f-4a7b-8c9d-0e1f2a3b4c5d",
      "created_at": "2026-08-18T11:02:04.000Z",
      "updated_at": "2026-08-20T09:14:22.000Z"
    }
  },
  "request_id": "req_c7e1a0b8d3f24e6a9c5b"
}

401


{
  "error": {
    "code": "token_expired",
    "message": "This API key has expired. Roll it from the API tab on the Connections page to get a replacement.",
    "request_id": "req_8f21c0aa47b1490d2e63"
  }
}

404


{
  "error": {
    "code": "not_found",
    "message": "Not found.",
    "request_id": "req_5b0e77d213a94f6a8ce1"
  }
}

429


{
  "error": {
    "code": "rate_limited",
    "message": "Too many requests. Retry after 24 seconds.",
    "request_id": "req_31c9ba7f0e5d4a118cc2"
  }
}

Response fields

Field	Type	Description
`data.document.id`	`uuid`	required
`data.document.brand_id`	`uuid`	required
`data.document.title`	`string`	required
`data.document.user_description`	`string \| null`	required
`data.document.source_type`	`string`	required. One of `paste`, `pdf`, `mcp` — `mcp` is a legacy value, see List knowledge documents
`data.document.raw_text`	`string \| null`	required. `null` while a PDF is still `processing`
`data.document.body_html`	`string \| null`	required. See Notes — effectively never `null` once `status` is `ready`
`data.document.status`	`string`	required. One of `processing`, `ready`, `failed`
`data.document.error_message`	`string \| null`	required. Populated only when `status` is `failed`
`data.document.char_count`	`integer`	required
`data.document.chunk_count`	`integer`	required. Chunks the document was split into for retrieval
`data.document.token_count`	`integer`	required
`data.document.needs_reembed`	`boolean`	required. `true` when the stored embeddings are stale relative to the current content
`data.document.file_name`	`string \| null`	PDF-sourced documents only
`data.document.page_count`	`integer \| null`	PDF-sourced documents only
`data.document.file_size_bytes`	`integer \| null`	PDF-sourced documents only
`data.document.mime_type`	`string \| null`	PDF-sourced documents only. `application/pdf` when set
`data.document.material_type`	`string \| null`	Optional user-assigned classification of the source material
`data.document.writing_style_id`	`uuid \| null`	Set when this document belongs to a writing style rather than general brand knowledge
`data.document.style_prompt_dismissed`	`boolean`	required
`data.document.created_by`	`uuid`	required
`data.document.created_at` / `data.document.updated_at`	`timestamptz`	required
`request_id`	`string`	required. Also returned as the `x-request-id` header. Quote it when contacting support

Errors

Status	Code	When
401	`invalid_token`	The key is missing, malformed, or does not exist
401	`token_expired`	The key passed its expiry date
401	`token_revoked`	The key was revoked
403	`insufficient_scope`	The key does not carry `read:knowledge_base`
404	`not_found`	The brand does not exist, `document_id` does not belong to this brand, or this key is not allowed to reach it
429	`rate_limited`	Over 300 requests per minute

Notes

raw_text and body_html are null while a PDF is still processing. They populate once status flips to ready, after the vision extraction pass finishes.

body_html is synthesized, not always stored. Legacy and pasted rows with no persisted HTML get one generated from raw_text on read, matching what the app does — so the field reads as populated for a ready document even before anyone has edited it. The first edit through Update knowledge document persists a real, independently-stored value.

error_message only appears once a document has failed. It is null for every other status.

File metadata is PDF-only. file_name, page_count, file_size_bytes and mime_type are null for paste and mcp documents. Use Get knowledge document file to download the original PDF for a pdf-sourced one.