Athina AI Evaluations API

openapi: 3.2.0
info:
  title: Athina AI Datasets Evaluations API
  description: REST API for the Athina AI LLM monitoring, evaluation, and experimentation platform. Log inferences and prompt runs, build traces and spans, manage datasets, run evaluations, and create, version, and run prompt templates. All requests authenticate with an `athina-api-key` header. Inference and prompt-run logging is served from the `https://log.athina.ai` host; all other resources are served from `https://api.athina.ai/api/v1`.
  termsOfService: https://www.athina.ai/terms
  contact:
    name: Athina AI Support
    url: https://www.athina.ai
    email: hello@athina.ai
  version: '1.0'
servers:
- url: https://api.athina.ai/api/v1
  description: Core API (datasets, traces, prompts, evals)
- url: https://log.athina.ai/api/v1
  description: Inference logging host
security:
- athinaApiKey: []
tags:
- name: Evaluations
  description: Run evaluations against datasets and logged inferences.
paths:
  /eval/run:
    post:
      operationId: runEval
      tags:
      - Evaluations
      summary: Run an evaluation
      description: Run one or more preset or custom evaluations against a dataset or set of inference rows. Evaluations grade attributes such as faithfulness, context relevance, answer relevance, and summarization quality.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RunEvalRequest'
      responses:
        '200':
          description: Evaluation run accepted.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RunEvalResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
components:
  schemas:
    DatasetRow:
      type: object
      properties:
        query:
          type: string
        context:
          oneOf:
          - type: string
          - type: array
            items:
              type: string
        response:
          type: string
        expected_response:
          type: string
      additionalProperties: true
    Error:
      type: object
      properties:
        status:
          type: string
        message:
          type: string
    RunEvalRequest:
      type: object
      required:
      - evals
      properties:
        dataset_id:
          type: string
          description: Dataset to evaluate; alternatively provide rows inline.
        rows:
          type: array
          items:
            $ref: '#/components/schemas/DatasetRow'
        evals:
          type: array
          description: List of eval definitions to run.
          items:
            $ref: '#/components/schemas/EvalDefinition'
        model:
          type: string
          description: Grader / evaluator model.
    EvalDefinition:
      type: object
      required:
      - name
      properties:
        name:
          type: string
          example: DoesResponseAnswerQuery
        type:
          type: string
          example: llm_grader
        config:
          type: object
          additionalProperties: true
    RunEvalResponse:
      type: object
      properties:
        eval_request_id:
          type: string
        status:
          type: string
        results:
          type: array
          items:
            type: object
            properties:
              eval_name:
                type: string
              passed:
                type: boolean
              score:
                type: number
              reason:
                type: string
  responses:
    Unauthorized:
      description: Missing or invalid athina-api-key.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
  securitySchemes:
    athinaApiKey:
      type: apiKey
      in: header
      name: athina-api-key
      description: Athina API key created in the Athina platform settings.