PAparsewise
Results

List extraction results

Paginated extraction results for the project, with optional filtering, sorting, and search. Pass include_sources=true to also receive the document sources cited by the results on the returned page — computed per page, so they stay in sync with the current pagination and filters.

get/projects/{project_id}/results/

Request

  • Base URL
    https://api.parsewise.ai/api/v1
  • Auth
    API key in header X-API-Key

Path parameters

project_idstring uuid required

Query parameters

agent_idsstring

Comma-separated UUIDs. Restricts the response to rows produced by the listed agents (defaults to all of the project's agents).

consistent_sources_onlyboolean

When true, sources leaves out extractions judged inconsistent with the resolved value, matching the sources marked consistent on the result. Only applies with include_sources=true. Defaults to false.

dimension_orderstring

Comma-separated dimension names controlling how rows are grouped and how columns are laid out across multiple agents. Order matters: earlier names group at the outermost level of the result table.

filter_inconsistentboolean

When true, only return rows whose values are not fully consistent across the source documents. Defaults to false.

filter_missingboolean

When true, only return rows whose resolved value is missing or empty. Defaults to false.

filter_review_statusstring

Comma-separated review statuses to include. Accepted values: positive, negative, unreviewed. When omitted, no review-status filtering is applied.

filtersstring

JSON-encoded dimension filter, applied to the rows. The value is a JSON object whose keys are dimension names (matching the name of a dimension on one of the project's agents, e.g. "Document" or "Region") and whose values are arrays of dimension values to keep. Within a single key the values are OR-ed (a row matches the key if it has any of the listed values for that dimension); across keys they are AND-ed (a row must match every key to be returned). Empty value arrays and unknown dimension names are ignored. Example: {"Region": ["EMEA", "APAC"], "Year": ["2024"]}.

include_dimension_valuesboolean

When false, omits the all_dimension_values field from the response to reduce payload size. Defaults to true.

include_sourcesboolean

When true, includes the sources field (document pages cited by the results on the current page). Because sources are computed from the returned page, they honour the same pagination, filters, and search as the rows. Defaults to false. Note: computing sources runs extra joins over the page's extractions and their document pages, so enable it only when you need citations.

pageinteger

1-indexed page number to return. Defaults to 1.

page_sizeinteger

Number of rows per page. Defaults to 100.

searchstring

Case-insensitive substring match against resolved values.

search_columnstring

Agent name to restrict search to a single column. Ignored when search is not supplied.

sort_bystring

Column to sort by. Only applied when a single agent is selected and no dimension_order is supplied; otherwise the default ordering is used.

sort_order'asc' | 'desc'

Sort direction for sort_by. Defaults to asc.

Response

countinteger required

Number of rows returned on this page (i.e. the length of results). For the cross-page total, use total_rows.

pageinteger required

1-indexed page number of the returned page.

page_sizeinteger required

Requested page size (rows per page).

total_pagesinteger required

Total number of pages available for the current filters.

total_rowsinteger required

Total matching rows across all pages for the current filters.

displayed_dimensionsstring[] required

Ordered dimension names used to group/lay out rows in the response, reflecting the effective dimension_order.

agent_idsstring[] required

Agents included in the response.

recommended_dimension_orderstring[] nullable

Suggested dimension ordering for multi-agent views, or null when no specific ordering is recommended.

all_dimension_valuesobject

Map of dimension name to the full set of values seen for that dimension across the matching rows, useful for building filter pickers. Omitted when include_dimension_values=false.

Example response

{
  "results": [
    {
      "resolution_result": {
        "references": {
          "1": [
            "Annual Report 2024.pdf",
            12
          ],
          "2": [
            "Investor Deck.pdf",
            null
          ]
        }
      }
    }
  ]
}

Changes

No recorded changes to this operation across all 1 revision of this API.