Skip to main content

Single Comparison

Get a specific field comparison filtered by document and field name. Returns a single N-Shot comparison for detailed evaluation.

Retrieve a single N-Shot comparison for a specific document and field. Use this endpoint when you need detailed information about one particular comparison, including per-shot values, any existing override, and the LLM judge recommendation.

GET/v1/jobs/runs/{runId}/nshot/comparison

Response

Response fields

idstringComparison UUID.
run_idstringJob run UUID.
document_idstringDocument UUID.
field_namestringField name being compared.
statusstringAgreement status: green, yellow, or red.
agreement_scorenumberNumeric agreement score between 0 and 1.
majority_valueanyThe value agreed upon by the majority of shots.
comparison_methodstringMethod used to compare values.
valuesarrayPer-shot values with shot_number and value.
overrideobject | nullOverride record if a value was manually selected.
judgementobject | nullLLM judge recommendation with accepted flag.
created_atstringISO 8601 creation timestamp.
links.selfstringURL to this comparison.

Response

{
  "id": "cmp-uuid-1",
  "run_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
  "document_id": "doc-uuid-1",
  "field_name": "total_amount",
  "status": "yellow",
  "agreement_score": 0.6667,
  "majority_value": "12450.00",
  "comparison_method": "exact",
  "values": [
    { "shot_number": 1, "value": "12450.00" },
    { "shot_number": 2, "value": "12450.00" },
    { "shot_number": 3, "value": "12,450.00" }
  ],
  "override": null,
  "judgement": {
    "recommended_shot": 1,
    "recommended_value": "12450.00",
    "accepted": null,
    "decided_by": null,
    "decided_at": null
  },
  "created_at": "2024-09-14T10:32:00.000Z",
  "links": {
    "self": "/v1/jobs/runs/a1b2c3d4-e5f6-7890-abcd-ef1234567890/nshot/comparison?document_id=doc-uuid-1&field_name=total_amount"
  }
}

This endpoint is typically called after identifying a problematic comparison in the GET /v1/jobs/runs/{runId}/nshot/comparisons list. Inspect the values array to see what each shot extracted, then check the judgement object for the LLM's recommendation. If judgement.accepted is null, you can submit a decision via POST /v1/jobs/runs/{runId}/nshot/judge-decision.

Errors

Error responses

401unauthorizedMissing or invalid API key.
404not_foundNo job run with this ID exists for your organization, or no comparison found for the given document_id and field_name.
429rate_limitedToo many requests. Retry after the period indicated in the Retry-After header.

Related

Comparisons
Override