Get evaluation results

Retrieve evaluation results with all calculated metrics

GET /v1/retrievers/{retriever_id}/evaluations/{evaluation_id}

Get evaluation results

cURL

curl --request GET \
  --url https://api.mixpeek.com/v1/retrievers/{retriever_id}/evaluations/{evaluation_id} \
  --header 'Authorization: Bearer <token>' \
  --header 'X-Namespace: <api-key>'

200

{
  "evaluation_id": "<string>",
  "retriever_id": "<string>",
  "dataset_id": "<string>",
  "dataset_name": "<string>",
  "config": {
    "k_values": [
      1,
      5,
      10,
      20
    ],
    "metrics": [
      "precision",
      "recall",
      "f1",
      "map",
      "ndcg",
      "mrr"
    ]
  },
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "namespace_id": "<string>",
  "internal_id": "<string>",
  "query_count": 123,
  "completed_at": "2023-11-07T05:31:56Z",
  "overall_metrics": {},
  "metrics_by_k": {},
  "total_queries": 123,
  "evaluated_queries": 123,
  "skipped_queries": 123,
  "error_message": "<string>"
}

Authorizations

Authorization · string · header · required

Mixpeek API key, sent as Authorization: Bearer mxp_sk_.... Create one in Studio under Settings → API Keys, or with an admin key via POST /v1/organizations/users/{user_email}/api-keys. A missing header returns 403; an invalid or revoked key returns 401.

X-Namespace · string · header · required

Namespace id (ns_...), not the namespace name. This scopes the request rather than authenticating it, and it is required on every operation marked x-mixpeek-namespace-scoped.

Path Parameters

retriever_id · string · required

evaluation_id · string · required

Response

200

application/json

Successful Response

Complete evaluation record with results.

evaluation_id · string · required

Unique evaluation identifier

retriever_id · string · required

ID of retriever being evaluated

dataset_id · string · required

ID of dataset used for evaluation

dataset_name · string · required

Name of dataset

config · EvaluationConfig · object · required

Evaluation configuration

Show child attributes

status · enum<string> · required

Current status

Available options: pending, in_progress, completed, failed

created_at · string<date-time> · required

When evaluation was created

updated_at · string<date-time> · required

Last update timestamp

namespace_id · string · required

Namespace ID

internal_id · string · required

Internal organization ID

query_count · integer · required

Number of queries evaluated

completed_at · string<date-time> | null

When evaluation completed

overall_metrics · Overall Metrics · object | null

Aggregated metrics across all queries

Show child attributes

metrics_by_k · Metrics By K · object | null

Metrics broken down by K value (keys are string K values like '5', '10', '20')

Show child attributes

total_queries · integer | null

Total queries in the dataset for this run (= evaluated_queries + skipped_queries).

evaluated_queries · integer | null

Number of queries that produced metrics. May be < total_queries when some queries were skipped (skip-and-continue on empty/failing input).

skipped_queries · integer | null

Number of queries skipped during evaluation (empty query_input or a per-query execution failure) — these did not fail the whole eval.

error_message · string | null

Error message if failed