Skip to main content
POST
/
langevals
/
competitor_llm
/
evaluate
import langwatch

df = langwatch.datasets.get_dataset("dataset-id").to_pandas()

experiment = langwatch.experiment.init("my-experiment")

for index, row in experiment.loop(df.iterrows()):
    # your execution code here
    experiment.evaluate(
        "langevals/competitor_llm",
        index=index,
        data={
            "output": output,
            "input": row["input"],
        },
        settings={}
    )
[
  {
    "status": "processed",
    "score": 123,
    "passed": true,
    "label": "<string>",
    "details": "<string>",
    "cost": {
      "currency": "<string>",
      "amount": 123
    }
  }
]

Authorizations

​
X-Auth-Token
string
header
required

API key for authentication

Body

application/json
​
data
object
required
​
trace_id
string

Optional trace ID to associate this evaluation with a trace

​
settings
object

Response

Successful evaluation

​
status
enum<string>
Available options:
processed,
skipped,
error
​
score
number

Numeric score from the evaluation

​
passed
boolean

Whether the evaluation passed

​
label
string

Label assigned by the evaluation

​
details
string

Additional details about the evaluation

​
cost
object