Extract schedules

Schedule extraction · model schedule-extractor

POST/v1/drawings/schedules

Extract structured schedule tables from an architectural drawing PDF. Accepts a previously uploaded document_id, enqueues extraction, and returns a job you poll for results. Each schedule is returned with headers, rows, and schedule-level confidence.

Returns: A job to check202 Accepted
Usage: Document indexingper page scanned
Results in: A list of schedulesresult.schedules
Auth: API keyX-API-Key header

Example

Drawing schedule input — A sample drawing set before and after schedule extraction: 4 schedules extracted.

Extracted schedule result — A sample drawing set before and after schedule extraction: 4 schedules extracted.

How it runs

Send a document_id
Get a job_id
Check your results or receive a webhook

Request

This endpoint requires a document_id. Upload your PDF first.

Body is JSON — this endpoint does not accept file uploads directly.

Field	Description
`document_id`string · UUIDRequired	ID of the uploaded PDF. Must belong to this account and not be expired.
`page_numbers`array of integersOptional	1-based page indices to scan. Omit for a full-document scan.
`webhook_url`string · URLOptional	URL to POST the completed job payload to. Delivered on developer, pro, and enterprise tiers only.

Header	Description
`X-API-Key`Required	Your API key. A missing or invalid key returns 401.
`Content-Type`Required	`application/json`

Usage and pages_analyzedA schedule job counts as one document-indexing page (See pricing). When page_numbers is omitted, pages_analyzed in the completed result is null; when provided, it reflects len(page_numbers) (not a substituted total page count).

Responses

The job is enqueued immediately. Poll GET /v1/jobs/{job_id} until status is complete or failed.

Field	Description
`job_id`string · UUID	Use this to poll for results.
`status`string	Always queued on this response.
`poll_url`string	Path only — prepend `https://api.anchorgrid.ai` to build the full URL.

When status is complete and model is schedule-extractor, the result field on the job contains:

Field	Description
`document_id`string	UUID of the source document.
`schedules_found`integer	Count of schedules in the schedules array.
`pages_analyzed`integer \| null	len(page_numbers) if provided; null for a full-document scan.
`model_version`string	e.g. `schedule-extractor-v1.0.0`
`processing_time_ms`integer	Wall time for the extraction task.
`ocr_fallback_used`boolean	True if any page fell back to OCR due to low PDF text quality.
`rasterized_pages`integer[]	Pages that were rasterized before extraction. Empty when PDF text layer was sufficient.
`schedules`array	One object per detected schedule table.
`schedules[].schedule_type`string	Classifier label — e.g. "door_schedule", "window_schedule", "finish_schedule".
`schedules[].title`string	Title as printed on the sheet.
`schedules[].confidence`number	Schedule-level confidence score (0–1).
`schedules[].bounding_box`number[4]	Page coordinates of the table: [x1, y1, x2, y2] in PDF units.
`schedules[].headers`string[]	Column labels in left-to-right order.
`schedules[].rows`object[]	Each row is an object keyed by header label. Empty string for blank cells.
`schedules[].metadata.row_count`integer	Number of data rows detected.
`schedules[].metadata.col_count`integer	Number of columns detected.
`schedules[].metadata.method`string	Extraction strategy used internally (e.g. wide_net_proximity).
`schedules[].metadata.pdf_quality_issues`string[]	Any quality flags raised for this schedule. Empty when extraction was clean.
`schedules[].metadata.ocr_fallback`boolean	True if this specific schedule used OCR.
`schedules[].metadata.item_bboxes`object	Each piece of text in the schedule region (e.g. a door number) mapped to the boxes where it appears, as [x1, y1, x2, y2] in PDF points. Empty for scanned schedules.

Rows are returned as objects keyed by header label — no column index arithmetic needed. Use schedules[].headers if you need the original column order.

Usage & rate limits

Each job counts as one document-indexing page (See pricing). Rate limit: tier RPM (5 / 60 / 120 / 300).

Plan	When the allowance is used up
`trial`	Trial allowance — `402 FREE_TIER_LIMIT_REACHED` when used up, `402 TRIAL_ENDED` once the trial is over.
`developer`	Monthly allowance, then overage up to your overage limit — `402 OVERAGE_LIMIT_REACHED` at the limit (`429 QUOTA_EXCEEDED` when the allowance is used up without overage billing).
`enterprise`	No allowance check.

Rate-limit 429s include retry_after_seconds in the body. Quota 429s and rate-limit 429s return the same status code — check the error body to distinguish them.

Errors

Status	What it means
401	Missing or invalid X-API-Key.
402	Trial allowance used up.
404	document_id not found or expired (DOCUMENT_NOT_FOUND in API code).
422	Validation error — malformed UUID or invalid body.
429	Rate limit or monthly quota exceeded.

Examples

curl -X POST https://api.anchorgrid.ai/v1/drawings/schedules \
  -H "X-API-Key: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "document_id": "550e8400-e29b-41d4-a716-446655440000",
    "page_numbers": [1, 2, 3]
  }'

Response · 202

{
  "job_id": "7c9e6679-7425-40de-944b-e07fc1f90ae7",
  "status": "queued",
  "poll_url": "/v1/jobs/7c9e6679-7425-40de-944b-e07fc1f90ae7"
}

Completed job · result

{
  "document_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
  "schedules_found": 3,
  "pages_analyzed": 5,
  "model_version": "schedule-extractor-v1.0.0",
  "processing_time_ms": 18450,
  "ocr_fallback_used": false,
  "rasterized_pages": [],
  "schedules": [
    {
      "schedule_type": "door_schedule",
      "title": "DOOR SCHEDULE",
      "confidence": 0.94,
      "bounding_box": [
        36,
        112.5,
        780,
        540
      ],
      "metadata": {
        "row_count": 24,
        "col_count": 8,
        "method": "wide_net_proximity",
        "pdf_quality_issues": [],
        "ocr_fallback": false,
        "item_bboxes": {
          "101": [
            [
              52.1,
              160.4,
              64.8,
              168.9
            ]
          ]
        }
      },
      "headers": [
        "DOOR NO.",
        "WIDTH",
        "HEIGHT",
        "THICKNESS",
        "MATERIAL",
        "FIRE RATING",
        "HARDWARE SET",
        "REMARKS"
      ],
      "rows": [
        {
          "DOOR NO.": "101",
          "WIDTH": "3'-0\"",
          "HEIGHT": "7'-0\"",
          "THICKNESS": "1-3/4\"",
          "MATERIAL": "HM",
          "FIRE RATING": "90 MIN",
          "HARDWARE SET": "HS-1",
          "REMARKS": "PAIR"
        },
        {
          "DOOR NO.": "102",
          "WIDTH": "2'-8\"",
          "HEIGHT": "7'-0\"",
          "THICKNESS": "1-3/4\"",
          "MATERIAL": "WD",
          "FIRE RATING": "",
          "HARDWARE SET": "HS-2",
          "REMARKS": ""
        }
      ]
    }
  ]
}

Cookies & analytics