Cancel a run

Ask a run to stop. The run stops before its next page, so the pages it already judged keep their judgements and are still readable. A run that has already finished, failed or been cancelled answers 409 instant_eval_already_finished.

POST /api/v1/instant-evals/{id}/cancel

Cancel a run

Python

import requests

url = "https://app.langwatch.ai/api/v1/instant-evals/{id}/cancel"

headers = {"X-Auth-Token": "<api-key>"}

response = requests.post(url, headers=headers)

print(response.text)

200

{
  "id": "<string>",
  "name": "<string>",
  "sql": "<string>",
  "parameters": {},
  "questions": [
    {
      "id": "<string>",
      "function": "<string>",
      "kind": "boolean",
      "reads": "<string>",
      "threshold": 123
    }
  ],
  "limit": 0,
  "status": "queued",
  "total": 0,
  "progress": 0,
  "matched": 0,
  "matchedByQuestion": {},
  "failed": 0,
  "skipped": 0,
  "tokens": 0,
  "priceUsd": 123,
  "error": "<string>",
  "createdAt": "<string>",
  "updatedAt": "<string>",
  "startedAt": "<string>",
  "finishedAt": "<string>"
}

Authorizations

X-Auth-Token · string · header · required

Project API key for sending traces and accessing project-scoped resources. Format: sk-lw-... (no underscore). Obtain one by creating a project via the Admin API or the LangWatch UI.

Path Parameters

id · string · required

The run id.

Minimum string length: 1

Response

200

application/json

Success

id · string · required

The run id.

name · string | null · required

What the run was called, if anything.

sql · string · required

The statement, exactly as submitted.

parameters · object · required

The values the statement's parameters were filled with.

Show child attributes

questions · object[] · required

One entry per eval function the statement projects, derived from it when the run was accepted.

Show child attributes

limit · integer · required

Rows this run may judge.

Required range: -9007199254740991 <= x <= 9007199254740991

status · enum<string> · required

Where the run is in its life.

Available options: queued, planning, running, finished, failed, cancelled

total · integer | null · required

Rows the run found, bounded by its limit. Null until it has looked.

Required range: -9007199254740991 <= x <= 9007199254740991

progress · integer · required

Rows judged so far.

Required range: -9007199254740991 <= x <= 9007199254740991

matched · integer | null · required

Judgements that matched, across this run's boolean questions. Null when the run asked none: a score or a category question has no match to count.

Required range: -9007199254740991 <= x <= 9007199254740991

matchedByQuestion · object · required

Per question: matches for a boolean question, judged rows for a score or a category one.

Show child attributes

failed · integer · required

Rows the judge could not answer.

Required range: -9007199254740991 <= x <= 9007199254740991

skipped · integer · required

Rows the judge declined to answer.

Required range: -9007199254740991 <= x <= 9007199254740991

tokens · integer · required

Input tokens the judge billed for.

Required range: -9007199254740991 <= x <= 9007199254740991

priceUsd · number · required

What the judging costs you, in United States dollars.

error · string | null · required

The code of the failure that ended the run, when one did.

createdAt · string · required

When the run was accepted.

updatedAt · string · required

When the run was last written to.

startedAt · string | null · required

When the run began reading rows.

finishedAt · string | null · required

When the run ended.