bol-ai

Extract structured data from a freight document (PDF, PNG or JPG, max 10 MB): Bill of Lading, commercial invoice, packing list, or CMR road waybill. The document type is detected automatically and returned as `doc_type`. Provide either a fetchable `url` or `base64` file content. Fields not present in the document are null — never guessed. Each successful extraction bills one document.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "URL of the document to fetch and extract"
    },
    "base64": {
      "type": "string",
      "description": "Base64-encoded file content (alternative to url)"
    },
    "filename": {
      "type": "string",
      "description": "Filename including extension, e.g. shipment-4711.pdf"
    }
  }
}

Extract up to 10 freight documents in one call. Provide an array of fetchable URLs; each document is processed and billed independently, and the response reports a per-document outcome so partial success (e.g. running out of credits mid-batch) is explicit.

{
  "type": "object",
  "properties": {
    "urls": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 10,
      "description": "URLs of documents to fetch and extract (max 10)"
    }
  },
  "required": [
    "urls"
  ]
}

List the 100 most recent documents for this account with id, filename, status (pending/done/failed), doc_type and primary reference number.

{
  "type": "object",
  "properties": {}
}

Get the extraction result for a document by id: doc_type, extracted fields, user corrections (when present), and deterministic verification warnings (ISO 6346 container check digits, plausibility flags). `fields` is the best available data (corrections win); `original_fields` and `corrected_fields` show both sides.

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Document id"
    }
  },
  "required": [
    "id"
  ]
}

Save corrected field values for an extracted document. The original extraction is kept alongside the corrections; corrected data takes precedence in get_document, exports and reconciliation. Pass the complete corrected fields object (same shape as returned by get_document).

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Document id"
    },
    "fields": {
      "type": "object",
      "description": "Complete corrected fields object, including doc_type"
    }
  },
  "required": [
    "id",
    "fields"
  ]
}

Cross-document reconciliation: find the other documents in this shipment (linked by shared reference numbers such as B/L number and invoice number) and compare them field by field — shipper/seller and consignee/buyer names, total gross weight (5% tolerance) and package counts. Returns matches and mismatches per linked document. Catches the discrepancies that cause customs holds, amended entries and demurrage. Deterministic — no extra document billed.

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Document id to reconcile against the rest of the account"
    }
  },
  "required": [
    "id"
  ]
}

Export completed extractions as TMS/ERP-ready normalized line rows (one row per container / invoice line / package / goods line), newest first. Optional doc_type filter and max_rows cap. Corrected data wins over the original extraction. For CSV/XLSX files use GET /api/bol/export on the REST API.

{
  "type": "object",
  "properties": {
    "type": {
      "type": "string",
      "enum": [
        "bill_of_lading",
        "commercial_invoice",
        "packing_list",
        "cmr"
      ],
      "description": "Only include documents of this type"
    },
    "max_rows": {
      "type": "number",
      "description": "Maximum rows to return (default 500)"
    }
  }
}

Check this account's remaining prepaid credits and subscription status. Call this before large batches to avoid running out of credits mid-workflow. When the account cannot bill more documents, a human can top up at the returned buy_credits_url.

{
  "type": "object",
  "properties": {}
}