ℹ️ These docs are for current Galileo customers running v1.0. Docs for the v2.0 version of Galileo can be found here.
API Reference
health
evaluate-alerts
protect
API Reference
curl --request POST \
--url https://api.acme.rungalileo.io/v1/evaluate/run-workflows \
--header 'Content-Type: application/json' \
--header 'Galileo-API-Key: <api-key>' \
--data '
{
"starting_token": 0,
"limit": 100,
"project_id": "<string>",
"project_name": "<string>",
"run_id": "<string>",
"run_name": "<string>"
}
'{
"workflows": [
{
"input": "<string>",
"type": "workflow",
"redacted_input": "<string>",
"output": "<string>",
"redacted_output": "<string>",
"name": "",
"created_at_ns": 123,
"duration_ns": 0,
"metadata": {},
"status_code": 123,
"ground_truth": "<string>",
"root_workflow_id": "<string>",
"workflow_id": "<string>",
"step_id": "<string>",
"steps": [
"<unknown>"
],
"metrics": [
{
"name": "<string>",
"value": "<unknown>",
"status": "<string>",
"explanation": "<string>",
"rationale": "<string>",
"cost": 123,
"model_alias": "<string>",
"num_judges": 123,
"display_value": "<unknown>",
"data_type": "unknown"
}
]
}
],
"starting_token": 0,
"limit": 100,
"paginated": false,
"next_starting_token": 123
}Get Evaluate Run Results
Fetch evaluation results for a specific run including rows and aggregate information.
curl --request POST \
--url https://api.acme.rungalileo.io/v1/evaluate/run-workflows \
--header 'Content-Type: application/json' \
--header 'Galileo-API-Key: <api-key>' \
--data '
{
"starting_token": 0,
"limit": 100,
"project_id": "<string>",
"project_name": "<string>",
"run_id": "<string>",
"run_name": "<string>"
}
'{
"workflows": [
{
"input": "<string>",
"type": "workflow",
"redacted_input": "<string>",
"output": "<string>",
"redacted_output": "<string>",
"name": "",
"created_at_ns": 123,
"duration_ns": 0,
"metadata": {},
"status_code": 123,
"ground_truth": "<string>",
"root_workflow_id": "<string>",
"workflow_id": "<string>",
"step_id": "<string>",
"steps": [
"<unknown>"
],
"metrics": [
{
"name": "<string>",
"value": "<unknown>",
"status": "<string>",
"explanation": "<string>",
"rationale": "<string>",
"cost": 123,
"model_alias": "<string>",
"num_judges": 123,
"display_value": "<unknown>",
"data_type": "unknown"
}
]
}
],
"starting_token": 0,
"limit": 100,
"paginated": false,
"next_starting_token": 123
}Authorizations
Body
Response
Successful Response
Response model for workflow evaluation results
Show child attributes
Show child attributes
Input to the step.
Type of the step. By default, it is set to workflow.
chain, chat, llm, retriever, tool, agent, workflow, trace, session Redacted input of the step. This is used to redact sensitive information.
Output of the step.
Redacted output of the step. This is used to redact sensitive information.
Name of the step.
Timestamp of the step's creation, as nanoseconds since epoch.
Duration of the step in nanoseconds.
Status code of the step. Used for logging failed/errored steps.
Ground truth expected output for the step.
Show child attributes
Show child attributes
unknown, text, label, floating_point, integer, timestamp, milli_seconds, boolean, uuid, percentage, dollars, array, template_label, thumb_rating_percentage, user_id, text_offsets, segments, hallucination_segments, thumb_rating, score_rating, star_rating, tags_rating, thumb_rating_aggregate, score_rating_aggregate, star_rating_aggregate, tags_rating_aggregate Was this page helpful?