Logging your application execution to HoneyHive without using the tracers
API flow to log an evaluation with a self-managed dataset
POST /runs
: Initiate the evaluation run using external datasets. Full API reference link here.POST /session/start
: Start a new session for the evaluation run. Full API reference link here.metadata.run_id = run_id
(use the ID from the evaluation run)session_id = session_id
(use the ID from the session start)PUT /runs
: Mark the evaluation as completed. Full API reference link here.event_ids
: Provide a list of session IDs.status = completed
API flow to log an evaluation with a HoneyHive-managed dataset
GET /datasets
: Fetch the dataset you want to evaluate. This will provide the dataset_id
. Full API reference link here.POST /runs
: Initiate the evaluation run. Full API reference link here.dataset_id = dataset_id
GET /datapoint/{id}
: Retrieve the specific data points to be used for evaluation. Full API reference link here.POST /session/start
: Start a new session for the evaluation run. Full API reference link here.metadata.run_id = run_id
metadata.datapoint_id = datapoint_id
session_id = session_id
PUT /runs
: Mark the evaluation as completed. Full API reference link here.event_ids
: Provide a list of session IDs.status = completed