Add dataset entries programmatically using the LangWatch API to build evaluation sets for LLM testing and agent validation.

Add entries to a dataset

POST /api/v1/dataset/{datasetSlug}/entries

Python

Python

import requests

url = "https://app.langwatch.ai/api/v1/dataset/{datasetSlug}/entries"

payload = { "entries": [
        {
            "input": "hi",
            "output": "Hello, how can I help you today?"
        }
    ] }
headers = {
    "X-Auth-Token": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

200

{
  "success": true
}

This endpoint only adds entries. To read them back, call GET /api/dataset/{slugOrId}/records.

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

datasetSlug · string · required

Body

application/json

entries · object[] · required

Required array length: 1 - 4000 elements

Show child attributes

Example:

[
  {
    "input": "hi",
    "output": "Hello, how can I help you today?"
  }
]

Response

200 - application/json

Success

success · boolean · required