Skip to main content
POST
/
extract
/
doc
Extract Word documents
curl --request POST \
  --url https://api.horizon.new/v1/extract/doc \
  --header 'Content-Type: application/json' \
  --data '{
  "sourceUrl": "<string>",
  "sourceName": "<string>",
  "options": {},
  "webhookUrl": "<string>"
}'
{
  "jobId": "job_01hx9q9",
  "status": "queued",
  "statusUrl": "<string>",
  "result": {},
  "etaSeconds": 123,
  "jobType": "extract/pdf"
}
Flatten Microsoft Word (.doc, .docx) or similar word-processing files into clean text blocks. Styles, tables, and lists are normalized while preserving heading hierarchy for downstream indexing.

​
Request body

  • sourceUrl — HTTPS or signed URL pointing to the document. Required if file is not provided.
  • file — Optional uploaded document (.doc, .docx, etc.) using multipart/form-data.
  • sourceName — Optional label for the extracted dataset (e.g., Pricing Policy).
  • options — Optional object. Supported keys:
    • segmentLength — Target characters per chunk (default 1000).
    • language — ISO language hint to improve sentence segmentation.
    • includeComments — Boolean; include tracked changes and comments in output (default false).
  • webhookUrl — Optional HTTPS URL Horizon should call when the extraction finishes.

​
Sample request

curl https://api.horizon.new/v1/extract/doc \
  -H "Content-Type: application/json" \
  -d '{
    "sourceUrl": "https://cdn.example.com/policies/pricing.docx",
    "sourceName": "Pricing Policy v3",
    "options": {
      "segmentLength": 1200,
      "language": "en",
      "includeComments": false
    }
  }'

# or upload the raw document

curl https://api.horizon.new/v1/extract/doc \
  -H "Content-Type: application/json" \
  -d '{
    "file": "data:application/vnd.openxmlformats-officedocument.wordprocessingml.document;base64,UEsDBBQABgAIA...",
    "sourceName": "Pricing Policy v3",
    "options": {
      "segmentLength": 1200,
      "language": "en",
      "includeComments": false
    }
  }'

​
Response

Returns 202 Accepted with jobId, status, and statusUrl. When the doc is small, extracted chunks appear immediately in result.

​
Notes

  • Track changes are removed by default; set includeComments: true to retain reviewer notes.
  • Embedded images are ignored; captions are extracted where available.
  • Use segmentLength to tune chunk size for language models or vector storage.
  • Poll GET /jobs/{jobId} (matches the statusUrl) to check progress or fetch the final output later on demand.
  • To upload the document directly, send multipart/form-data with a file field instead of sourceUrl.

​
x402 flow

Word document extraction is priced via Coinbase’s x402 protocol. A missing proof yields a challenge like: 
HTTP/1.1 402 Payment Required
Content-Type: application/json

{
  "x402Version": 1,
  "accepts": [
    {
      "scheme": "exact",
      "network": "base-sepolia",
      "maxAmountRequired": "140000",
      "resource": "POST /extract/doc",
      "description": "Horizon Word document extraction",
      "mimeType": "application/json",
      "payTo": "0xYourReceivingWallet",
      "maxTimeoutSeconds": 300,
      "asset": "0xYourUSDCContract",
      "extra": {
        "name": "USDC",
        "version": "1"
      }
    }
  ],
  "error": null
}
Send the accepts payload to your facilitator, complete /verify and /settle, then replay the request with the Base64 token in X-PAYMENT. Horizon validates the proof, resumes extraction, and includes X-PAYMENT-RESPONSE on success. Refer to the Coinbase quickstart if you need a reference implementation.

Body

application/json

Provide either sourceUrl or file.

​
sourceUrl
string<uri>
​
sourceName
string
​
options
object

Extraction hints such as language, segmentLength, transcriptionModel, or sheet preferences depending on the endpoint.

​
webhookUrl
string<uri>

Webhook to call when the extraction completes.

​
file
file

Upload the raw file instead of providing sourceUrl.

Response

Extraction job accepted

​
jobId
string
required
Example:

"job_01hx9q9"

​
status
enum<string>
required
Available options:
queued,
processing,
completed,
failed
​
statusUrl
string<uri>
required

Canonical link to GET /jobs/{jobId} for this job.

​
jobType
string
required
Example:

"extract/pdf"

​
result
object | null

Present when the job completes synchronously.

​
etaSeconds
integer | null

Estimated seconds until completion.