Generate a document

Produce a finished document from structured input.

Goal. Turn structured data — borrower details, terms, schedules — into a finished, styled document your business can send.

This runs the pipeline in the opposite direction to extraction. You supply sections of data; the platform returns a rendered file and a download URL.

Generated endpoint reference

Use Generate a document asynchronously or generate a document synchronously for request schemas. Get generation details documents the retrieval endpoint.

Before you start

• An API key, exported as $DOCAI_API_KEY.

• Your content, organised into sections.

Step 1 — Structure the content

data is the one required property: an array of at least one section. Each section pairs a sectionKey with its sectionData.

{
  "data": [
    {
      "sectionKey": "borrower",
      "sectionData": {
        "name": "Northwind Trading Co.",
        "entityType": "Corporation",
        "address": "44 Harbour Road, Portland, OR"
      }
    },
    {
      "sectionKey": "terms",
      "sectionData": {
        "principal": 250000,
        "ratePct": 7.25,
        "termMonths": 60
      }
    }
  ],
  "format": "docx"
}

sectionKey must be unique within the array. Order the array the way you want the document to read.

format currently supports docx only, and that is what it defaults to. Asking for "PDF" is not a supported request — if you need PDF, convert after generation.

Step 2 — Style it

style is optional and controls presentation:

{
  "style": {
    "lenderName": "Example Bank",
    "fontFamily": "Calibri",
    "fontSize": 11,
    "primaryColor": "#1a4d80",
    "secondaryColor": "6c757d",
    "headerFooter": true,
    "pageNumbers": true,
    "tableOfContents": true
  }
}

fontSize accepts 8–72. Colours take hex with or without the leading #.

Keep a single style object in your configuration rather than repeating it per call — it is the part most likely to change when branding does.

Step 3 — Generate

Asynchronous, returning 201:

curl -X POST "https://api-docai-uat.uptiq.ai/generate" \
  -H "X-Api-Key: $DOCAI_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @generate.json

{
  "success": true,
  "generationId": "fb728716-0300-49bb-ae17-f7b480d37544",
  "requestId": "36a8be90-5d19-4133-b102-9a755f60ec21",
  "status": "Pending",
  "message": "Document generation job created successfully"
}

Note the field is generationId, not _id — generation names its identifier differently from extraction and classification.

Generation is the only capability whose request takes its own webhookUrl (HTTPS required). You can direct an individual job to an endpoint without touching account settings — extraction and classification cannot do this.

Step 4 — Collect the document

GET /generate/{_id} does not currently work. Every call returns 500 with "Invalid generation ID format" — including when passed the exact generationId the API itself just issued. Tested against the returned UUID, a stripped form, a prefixed form and a nil UUID: all 500. There is no ID format that succeeds.

Until it is fixed, do not build on the async retrieval path. Use one of the two routes below instead.

Route A — POST /generate/sync. The simplest working option: it returns the finished file directly on the same connection.

curl -X POST "https://api-docai-uat.uptiq.ai/generate/sync" \
  -H "X-Api-Key: $DOCAI_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @generate.json \
  -o loan-agreement.docx

HTTP/1.1 200 OK
Content-Type: application/vnd.openxmlformats-officedocument.wordprocessingml.document
Content-Disposition: attachment; filename="document.docx"
Content-Length: 10193

This response is the binary document itself, not JSON. There is no envelope, no status field, and nothing to parse — write the body straight to a file. A client that calls .json() on it will throw.

Route B — the webhook. Set webhookUrl on the async request and take the download URL from the completion payload, which is covered in step 5.

Generation is fast enough that the synchronous route is reasonable for most cases — unlike extraction, where a ~90-second hold makes it impractical.

Step 5 — Or let the webhook bring it

If you set webhookUrl, the completion payload arrives with the download URL already in it:

{
  "_id": "60d5ec18…",
  "status": "Processed",
  "format": "PDF",
  "downloadUrl": "https://signed-url…",
  "storageInfo": { },
  "error": null,
  "eventId": "evt_jkl012"
}

Verify the signature before acting on it — see Webhook payloads.

When it goes wrong

Symptom	Cause	Fix
400 on submit	data missing or empty	At least one section is required
400 mentioning sections	Duplicate sectionKey	Keys must be unique within data
500 "Invalid generation ID format" on retrieve	The endpoint is broken for all IDs — not your ID	Use /generate/sync or a webhook
JSON parse error on /generate/sync	The response is a binary DOCX	Write the body to a file; do not parse it
Download 403s	The signed webhook URL expired	Signed URLs are time-limited; fetch promptly
Unexpected file type	format only supports docx	Convert downstream
Webhook never arrives	webhookUrl was not HTTPS	HTTPS is required

Related pages

• Generation API — all three endpoints and the full schema.

• Document Generation — the same capability in the UI.

• Webhook payloads — the generation completion payload.