Skip to main content
GET
/
datastores
/
{datastore_id}
/
documents
/
{document_id}
/
parse
Get Parse Results
curl --request GET \
  --url https://api.contextual.ai/v1/datastores/{datastore_id}/documents/{document_id}/parse \
  --header 'Authorization: Bearer <token>'
{
  "file_name": "<string>",
  "status": "pending",
  "pages": [
    {
      "index": 123,
      "markdown": "<string>",
      "blocks": [
        {
          "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
          "type": "heading",
          "bounding_box": {
            "x0": 0.5,
            "y0": 0.5,
            "x1": 0.5,
            "y1": 0.5
          },
          "markdown": "<string>",
          "confidence_level": "low",
          "page_index": 123,
          "parent_ids": [
            "3c90c3cc-0d44-4b50-8888-8dd25736052a"
          ],
          "hierarchy_level": 123
        }
      ]
    }
  ],
  "markdown_document": "<string>",
  "document_metadata": {
    "hierarchy": {
      "blocks": [
        {
          "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
          "type": "heading",
          "bounding_box": {
            "x0": 0.5,
            "y0": 0.5,
            "x1": 0.5,
            "y1": 0.5
          },
          "markdown": "<string>",
          "confidence_level": "low",
          "page_index": 123,
          "parent_ids": [
            "3c90c3cc-0d44-4b50-8888-8dd25736052a"
          ],
          "hierarchy_level": 123
        }
      ],
      "table_of_contents": "<string>"
    }
  }
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

​
datastore_id
string<uuid>
required

Datastore ID of the datastore from which to retrieve the document

​
document_id
string<uuid>
required

Document ID of the document to retrieve details for

Query Parameters

​
output_types
enum<string>[]

The desired output format(s) of the parsed file. Must be markdown-document, markdown-per-page, and/or blocks-per-page. Specify multiple values to get multiple formats in the response. markdown-document parses the whole document into a single concatenated markdown output. markdown-per-page provides markdown output per page. blocks-per-page provides a structured JSON representation of the content blocks on each page, sorted by reading order.

The format of the output to be returned by the /parse endpoint.

Available options:
markdown-document,
markdown-per-page,
blocks-per-page

Response

Successful Response

/parse results reponse object.

​
file_name
string
required

The name of the file that was uploaded for parsing

​
status
enum<string>
required

The current status of the parse job

Available options:
pending,
processing,
retrying,
completed,
failed,
cancelled
Example:

"completed"

​
pages
ParsedPage · object[]

Per-page parse results, containing per-page Markdown (if markdown-per-page was requested) and/or per-page ParsedBlocks (if blocks-per-page was requested).

​
markdown_document
string

The parsed, structured Markdown of the input file. Only present if markdown-document was among the requested output types.

​
document_metadata
Document Metadata · object

Document-level metadata parsed from the document