Evaluate
Evaluation
Evaluate
Run evaluation on dataset
This creates an evaluation run and processes the dataset with specified metrics. Metrics are created on-demand if they don’t exist.
POST
Evaluate
Authorizations
Valiqor API key. Pass as Bearer token: Authorization: Bearer vq-xxxxxxxxxxxxxxxxxxxx
Body
application/json
Request model for evaluation endpoint
Project name (will be created if doesn't exist)
Dataset to evaluate
Metric keys to compute
Optional run name
Evaluation configuration
Additional metadata
Optional OpenAI key override
Response
Successful Response