---
title: "Get metric evaluation results"
method: GET
path: "/v1/{organization}/metric/metric_evaluation_result"
tags: ["Metric"]
---

# Get metric evaluation results

`GET /v1/{organization}/metric/metric_evaluation_result`

Retrieve metric evaluation results that match the given filters.

#### Permissions
This endpoint may be impacted by the following permissions:
* Only metric evaluation results that the authenticated user has `Metric:GetMetricEvaluationResult` permission for will be retrieved.

## Path parameters

- `organization` string, required

## Query parameters

- `limit` integer — The maximum number of metrics to return.
- `continuation_token` integer — The continuation token from the previous request used to retrieve the next page of metrics.
- `timestamp_after` string, date-time, nullable — An ISO8601 timestamp. Only results evaluated on or after this moment is returned.
- `timestamp_before` string, date-time, nullable — An ISO8601 timestamp. Only results evaluated on or before this moment is returned.
- `metric_id` string[] — The ID of the metric to retrieve.
- `metric_id_and_version` string[] — The metric IDs and their versions to retrieve. Each value must be in the format of `<metric_id>-<version>`. If `version` is left empty, any versions of the metric would be retrieved.
- `source_type` EvaluationSourceType[] — The type of the source of the metric evaluation results.
- `conversation_id` string[] — For metric evaluation sources with type `post-session` or `manual`, this field filters the metric evaluation results to only include those that were computed from the given conversation IDs.
- `simulation_unit_test_set_run_id` string[] — For metric evaluation sources with type `simulation`, this field filters the metric evaluation results to only include those that were computed from the given simulation unit test set run IDs.
- `sort_by` string[] — The fields to sort the metrics by. Supported fields are `created_at`. Specify a `+` before the field name to indicate ascending sorting and `-` for descending sorting. Multiple fields can be specified to break ties.

## Headers

- `x-mongo-cluster-name` string, nullable — The Mongo cluster name to perform this request in. This is usually not needed unless the organization does not exist yet in the Amigo organization infra config database.
- `Sec-WebSocket-Protocol` string[]

## Response `200`

Succeeded

- SrcAppEndpointsMetricGetMetricEvaluationResultsResponse
  - `metric_evaluation_results` MetricEvaluationResultInstance[], required — The list of retrieved metric evaluation results.
    - `id` string, required — The ID of the metric evaluation result.
    - `org_id` string, required — The ID of the organization.
    - `created_at` string, date-time
    - `updated_at` string, date-time
    - `metric_id` string, required — The ID of the metric that was evaluated.
    - `metric_version` integer, required — The version of the metric that was evaluated.
    - `result` union, required — The result of the metric evaluation. If `None`, the metric was deemed not applicable.
      - number
      - boolean
      - string
    - `justification` string, required — The justification for the result of the metric evaluation.
    - `source` union, required
      - PostSessionEvaluationSource
        - `type` 'post-session'
        - `conversation_id` string, required
        - `references` string[], required — A list of references to the messages that were used to compute this metric.
      - ManualEvaluationSource
        - `type` 'manual'
        - `conversation_id` string, required
        - `evaluate_to_interaction_id` string, nullable, required
        - `invoked_by` AmigoLibMongoCollectionsMetricEvaluationResultMetricEvaluationResultManualEvaluationSourceUserInfo, required
          - `org_id` string, required
          - `user_id` string, required
        - `references` string[], required — A list of references to the messages that were used to compute this metric.
      - SimulationEvaluationSource
        - `type` 'simulation'
        - `simulation_unit_test_set_run_id` string, required
        - `unit_test_id` string, required
        - `run_index` integer, required
        - `references` string[], required — A list of messages that were used to compute this metric.
  - `has_more` boolean, required — Whether there are more metric evaluation results to retrieve.
  - `continuation_token` unknown, required
  - `filter_values` SrcAppEndpointsMetricGetMetricEvaluationResultsResponseFilterValues, required
    - `metric_ids` string[], required — The IDs of the metrics that the metric evaluation results are for.

## Other responses

- `401` — Invalid authorization credentials.
- `403` — Missing required permissions.
- `404` — Specified organization is not found.
- `422` — Invalid request path parameter or request query parameter failed validation.
- `429` — The user has exceeded the rate limit of 10 requests per minute for this endpoint.
- `503` — The service is going through temporary maintenance.

---

[API](https://skmtc.net/amigo/apis/amigo-api.md) · [All operations](https://skmtc.net/amigo/apis/amigo-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/amigo/amigo-api/revisions/f0f28319e448/schema)