Skip to main content
POST
Evaluate a dataset

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.

Body

application/json
evaluation
string
required

Which evaluator to run, addressed the same way the evaluate endpoints address it

datasetSlug
string
required

The saved dataset to evaluate

experimentSlug
string

Groups the results under an experiment. Omit it and a batch id is generated instead.

batchId
string

Older name for experimentSlug, used when that is absent

data
object | null

Extra fields merged into every row before evaluating

settings
object | null

Per-call overrides of the evaluator's settings

Response

The evaluator ran; branch on status

status
string
required
Allowed value: "processed"
score
number
passed
boolean
label
string
details
string
cost
object

What running the evaluator cost

raw_response
any

The evaluator's own output, unprocessed