Skip to main content
GET
/
tasks
List Tasks
curl --request GET \
  --url https://api.chunkr.ai/tasks \
  --header 'Authorization: <api-key>'
{
  "has_more": true,
  "tasks": [
    {
      "completed": true,
      "configuration": {
        "chunk_processing": {
          "ignore_headers_and_footers": null,
          "target_length": 4096,
          "tokenizer": {
            "Enum": "Word"
          }
        },
        "error_handling": "Fail",
        "ocr_strategy": "All",
        "pipeline": "Chunkr",
        "segment_processing": {
          "Caption": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "Footnote": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "FormRegion": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "Formula": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "GraphicalItem": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "Legend": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "LineNumber": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "ListItem": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "Page": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "PageFooter": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "PageHeader": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "PageNumber": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "Picture": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "Table": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "Text": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "Title": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          },
          "Unknown": {
            "crop_image": "All",
            "description": null,
            "extended_context": null,
            "format": "Html",
            "llm": "<string>",
            "strategy": "LLM"
          }
        },
        "segmentation_strategy": "LayoutAnalysis"
      },
      "created_at": "2023-11-07T05:31:56Z",
      "file_info": {
        "url": "<string>",
        "mime_type": "<string>",
        "name": "<string>",
        "page_count": 1,
        "ss_cell_count": 1
      },
      "message": "<string>",
      "status": "Starting",
      "task_id": "<string>",
      "task_type": "Parse",
      "version_info": {
        "client_version": "Legacy",
        "server_version": "<string>"
      },
      "expires_at": "2023-11-07T05:31:56Z",
      "finished_at": "2023-11-07T05:31:56Z",
      "input_file_url": "<string>",
      "output": {
        "chunks": [
          {
            "chunk_length": 1,
            "segments": [
              {
                "bbox": {
                  "height": 123,
                  "left": 123,
                  "top": 123,
                  "width": 123
                },
                "page_height": 123,
                "page_number": 1,
                "page_width": 123,
                "segment_id": "<string>",
                "segment_type": "Caption",
                "confidence": 123,
                "content": "<string>",
                "description": "<string>",
                "embed": "<string>",
                "image": "<string>",
                "llm": "<string>",
                "ocr": [
                  {
                    "bbox": {
                      "height": 123,
                      "left": 123,
                      "top": 123,
                      "width": 123
                    },
                    "text": "<string>",
                    "confidence": 123,
                    "ocr_id": "<string>",
                    "ss_cell_ref": "<string>"
                  }
                ],
                "segment_length": 1,
                "ss_cells": [
                  {
                    "cell_id": "<string>",
                    "range": "<string>",
                    "text": "<string>",
                    "formula": "<string>",
                    "hyperlink": "<string>",
                    "style": {
                      "align": "Left",
                      "bg_color": "<string>",
                      "font_face": "<string>",
                      "is_bold": true,
                      "text_color": "<string>",
                      "valign": "Top"
                    },
                    "value": "<string>"
                  }
                ],
                "ss_header_bbox": {
                  "height": 123,
                  "left": 123,
                  "top": 123,
                  "width": 123
                },
                "ss_header_ocr": [
                  {
                    "bbox": {
                      "height": 123,
                      "left": 123,
                      "top": 123,
                      "width": 123
                    },
                    "text": "<string>",
                    "confidence": 123,
                    "ocr_id": "<string>",
                    "ss_cell_ref": "<string>"
                  }
                ],
                "ss_header_range": "<string>",
                "ss_header_text": "<string>",
                "ss_range": "<string>",
                "ss_sheet_name": "<string>",
                "text": "<string>"
              }
            ],
            "chunk_id": "<string>",
            "content": "<string>",
            "embed": "<string>"
          }
        ],
        "file_name": "<string>",
        "mime_type": "<string>",
        "page_count": 1,
        "pages": [
          {
            "image": "<string>",
            "page_height": 123,
            "page_number": 1,
            "page_width": 123,
            "dpi": 123,
            "ss_sheet_name": "<string>"
          }
        ],
        "pdf_url": "<string>"
      },
      "parse_task_id": "<string>",
      "started_at": "2023-11-07T05:31:56Z",
      "task_url": "<string>"
    }
  ],
  "next_cursor": "2023-11-07T05:31:56Z"
}

Authorizations

Authorization
string
header
required

Query Parameters

base64_urls
boolean

Whether to return base64 encoded URLs. If false, the URLs will be returned as presigned URLs.

end
string<date-time>

End date

include_chunks
boolean

Whether to include chunks in the output response

limit
integer<int64>

Number of tasks per page

cursor
string<date-time>

Cursor for pagination (timestamp)

start
string<date-time>

Start date

sort
enum<string>

Sort order: 'asc' for ascending, 'desc' for descending (default)

Available options:
asc,
desc
task_types
enum<string>[]

Filter by one or more task types

Available options:
Parse,
Extract
statuses
enum<string>[]

Filter by one or more statuses

The status of the task.

Available options:
Starting,
Processing,
Succeeded,
Failed,
Cancelled

Response

Paginated list of tasks

has_more
boolean
required
tasks
object[]
required
next_cursor
string<date-time> | null