Skip to main content
POST
/
v1
/
ade
/
parse
cURL
curl -X POST 'https://api.va.landing.ai/v1/ade/parse' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'document=@document.pdf' \
  -F 'model=dpt-2-latest' \ # Set the model (optional)
{
  "markdown": "<string>",
  "chunks": [
    {
      "markdown": "<string>",
      "type": "<string>",
      "id": "<string>",
      "grounding": {
        "box": {
          "left": 123,
          "top": 123,
          "right": 123,
          "bottom": 123
        },
        "page": 123
      }
    }
  ],
  "splits": [
    {
      "class": "<string>",
      "identifier": "<string>",
      "pages": [
        123
      ],
      "markdown": "<string>",
      "chunks": [
        "<string>"
      ]
    }
  ],
  "grounding": {},
  "metadata": {
    "filename": "<string>",
    "org_id": "<string>",
    "page_count": 123,
    "duration_ms": 123,
    "credit_usage": 123,
    "job_id": "<string>",
    "version": "<string>"
  }
}

Authorizations

Authorization
string
header
required

Your unique API key for authentication.

Get your API key here: https://va.landing.ai/settings/api-key.

If using the EU endpoint, get your API key here: https://va.eu-west-1.landing.ai/settings/api-key.

Body

multipart/form-data
model
string | null

The version of the model to use for parsing.

document
file | null

A file to be parsed. The file can be a PDF or an image. See the list of supported file types here: https://docs.landing.ai/ade/ade-file-types. Either this parameter or the document_url parameter must be provided.

document_url
string | null

The URL to the file to be parsed. The file can be a PDF or an image. See the list of supported file types here: https://docs.landing.ai/ade/ade-file-types. Either this parameter or the document parameter must be provided.

split
enum<string> | null

If you want to split documents into smaller sections, include the split parameter. Set the parameter to page to split documents at the page level. The splits object in the API output will contain a set of data for each page.

Available options:
TitleConst
SplitTypepage

Response

Successful Response

markdown
string
required
chunks
ParseChunk · object[]
required
splits
ParseSplit · object[]
required
metadata
object
required
grounding
object