> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mixpeek.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Get evaluation results

> Retrieve evaluation results with all calculated metrics



## OpenAPI

````yaml get /v1/retrievers/{retriever_id}/evaluations/{evaluation_id}
openapi: 3.1.0
info:
  title: Mixpeek API
  description: >-
    This is the Mixpeek API, providing access to various endpoints for data
    processing and retrieval.
  termsOfService: https://mixpeek.com/terms
  contact:
    name: Mixpeek Support
    url: https://mixpeek.com/contact
    email: info@mixpeek.com
  version: '0.82'
servers:
  - url: https://api.mixpeek.com
    description: Production
security: []
paths:
  /v1/retrievers/{retriever_id}/evaluations/{evaluation_id}:
    get:
      tags:
        - Retriever Evaluations
      summary: Get evaluation results
      description: Retrieve evaluation results with all calculated metrics
      operationId: >-
        get_evaluation_v1_retrievers__retriever_id__evaluations__evaluation_id__get
      parameters:
        - name: retriever_id
          in: path
          required: true
          schema:
            type: string
            title: Retriever Id
        - name: evaluation_id
          in: path
          required: true
          schema:
            type: string
            title: Evaluation Id
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EvaluationRecord'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '403':
          description: Forbidden
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '404':
          description: Not Found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
        '500':
          description: Internal Server Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
components:
  schemas:
    EvaluationRecord:
      properties:
        evaluation_id:
          type: string
          title: Evaluation Id
          description: Unique evaluation identifier
        retriever_id:
          type: string
          title: Retriever Id
          description: ID of retriever being evaluated
        dataset_id:
          type: string
          title: Dataset Id
          description: ID of dataset used for evaluation
        dataset_name:
          type: string
          title: Dataset Name
          description: Name of dataset
        config:
          $ref: '#/components/schemas/EvaluationConfig'
          description: Evaluation configuration
        status:
          $ref: '#/components/schemas/EvaluationStatus'
          description: Current status
        created_at:
          type: string
          format: date-time
          title: Created At
          description: When evaluation was created
        updated_at:
          type: string
          format: date-time
          title: Updated At
          description: Last update timestamp
        completed_at:
          anyOf:
            - type: string
              format: date-time
            - type: 'null'
          title: Completed At
          description: When evaluation completed
        namespace_id:
          type: string
          title: Namespace Id
          description: Namespace ID
        internal_id:
          type: string
          title: Internal Id
          description: Internal organization ID
        query_count:
          type: integer
          title: Query Count
          description: Number of queries evaluated
        overall_metrics:
          anyOf:
            - additionalProperties:
                type: number
              type: object
            - type: 'null'
          title: Overall Metrics
          description: Aggregated metrics across all queries
        metrics_by_k:
          anyOf:
            - additionalProperties:
                additionalProperties:
                  type: number
                type: object
              type: object
            - type: 'null'
          title: Metrics By K
          description: >-
            Metrics broken down by K value (keys are string K values like '5',
            '10', '20')
        total_queries:
          anyOf:
            - type: integer
            - type: 'null'
          title: Total Queries
          description: >-
            Total queries in the dataset for this run (= evaluated_queries +
            skipped_queries).
        evaluated_queries:
          anyOf:
            - type: integer
            - type: 'null'
          title: Evaluated Queries
          description: >-
            Number of queries that produced metrics. May be < total_queries when
            some queries were skipped (skip-and-continue on empty/failing
            input).
        skipped_queries:
          anyOf:
            - type: integer
            - type: 'null'
          title: Skipped Queries
          description: >-
            Number of queries skipped during evaluation (empty query_input or a
            per-query execution failure) — these did not fail the whole eval.
        error_message:
          anyOf:
            - type: string
            - type: 'null'
          title: Error Message
          description: Error message if failed
      type: object
      required:
        - evaluation_id
        - retriever_id
        - dataset_id
        - dataset_name
        - config
        - status
        - created_at
        - updated_at
        - namespace_id
        - internal_id
        - query_count
      title: EvaluationRecord
      description: Complete evaluation record with results.
    ErrorResponse:
      properties:
        success:
          type: boolean
          title: Success
          description: Always false for error responses
          default: false
        status:
          type: integer
          title: Status
          description: HTTP status code for this error
        error:
          $ref: '#/components/schemas/ErrorDetail'
          description: Error details payload
      type: object
      required:
        - status
        - error
      title: ErrorResponse
      description: Error response model.
      examples:
        - error:
            details:
              id: ns_123
              resource: namespace
            message: Namespace not found
            type: NotFoundError
          status: 404
          success: false
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    EvaluationConfig:
      properties:
        k_values:
          anyOf:
            - items:
                type: integer
              type: array
            - type: 'null'
          title: K Values
          description: K values for Precision@K, Recall@K, NDCG@K, etc.
          default:
            - 1
            - 5
            - 10
            - 20
        metrics:
          anyOf:
            - items:
                type: string
              type: array
            - type: 'null'
          title: Metrics
          description: >-
            List of metrics to calculate. Available: precision, recall, f1, f2,
            map, ndcg, mrr. f2 is the recall-weighted F-beta (beta=2) — useful
            when missing a relevant doc costs more than a false positive.
          default:
            - precision
            - recall
            - f1
            - map
            - ndcg
            - mrr
      type: object
      title: EvaluationConfig
      description: Configuration for an evaluation run.
    EvaluationStatus:
      type: string
      enum:
        - pending
        - in_progress
        - completed
        - failed
      title: EvaluationStatus
      description: Status of an evaluation run.
    ErrorDetail:
      properties:
        message:
          type: string
          title: Message
          description: Human-readable error message
        type:
          type: string
          title: Type
          description: Stable error type identifier (machine-readable)
        code:
          anyOf:
            - type: string
            - type: 'null'
          title: Code
          description: >-
            Fine-grained error code for programmatic handling (e.g.,
            namespace_name_taken, feature_extractor_not_found). Present only
            when consumers may need to branch on a specific error condition.
        details:
          anyOf:
            - additionalProperties: true
              type: object
            - type: 'null'
          title: Details
          description: >-
            Optional structured details to help debugging (validation errors,
            IDs, etc.)
      type: object
      required:
        - message
        - type
      title: ErrorDetail
      description: Error detail model.
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
              - type: string
              - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
        - loc
        - msg
        - type
      title: ValidationError

````