Run an experiment

Start a run of a saved experiment, addressed by slug. Returns a runId to poll straight away. Send Accept: text/event-stream instead to stream progress events until the run finishes.

POST /api/v1/experiments/{slug}/run

Run an experiment

Python

import requests

url = "https://app.langwatch.ai/api/v1/experiments/{slug}/run"

payload = {
    "data": [{}],
    "dataset_id": "<string>",
    "parameters": {},
    "row_indices": [4503599627370495]
}
headers = {
    "X-Auth-Token": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

200

{
  "runId": "<string>",
  "status": "running",
  "total": 123,
  "runUrl": "<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

slug · string · required

The experiment's slug, or its id

Minimum string length: 1

Body

application/json

data · object[]

Maximum array length: 4000

Show child attributes

dataset_id · string

parameters · object

Show child attributes

row_indices · integer[]

Required range: 0 <= x <= 9007199254740991

Response

200

application/json

Run started

runId · string · required

Identifier to poll this run with

status · string · required

Allowed value: "running"

total · number · required

Number of cells this run will execute

runUrl · string

Link to the run in the LangWatch app