Read an experiment's setup

The experiment’s datasets, targets and evaluators, with the version to send back when you save. Ask for fields=version to check for changes without transferring the setup.

GET /api/v1/experiments/{slug}/workbench-state

Read an experiment's setup

Python

import requests

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

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

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

print(response.text)

200

{
  "id": "<string>",
  "slug": "<string>",
  "version": 0,
  "updatedAt": "<string>",
  "name": "<string>",
  "state": {}
}

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

Query Parameters

fields · string

Set to version to answer with the version and timestamp only

Response

200

application/json

Success

id · string · required

slug · string · required

version · integer · required

Send this back as expectedVersion to save safely

Required range: -9007199254740991 <= x <= 9007199254740991

updatedAt · string · required

ISO 8601 timestamp of the last save

name · string | null

state · object | null

The experiment setup: datasets, targets and evaluators. Read it, change it, send it back whole.

Show child attributes