UpTrain Evaluations API

openapi: 3.0.1
info:
  title: UpTrain Managed Evaluation API
  description: >-
    Managed HTTP API for UpTrain, the open-source (Apache-2.0) LLM evaluation
    platform. The API grades supplied LLM input / output / context rows against
    a list of named checks (context relevance, factual accuracy, response
    completeness, conciseness, tonality, prompt injection, hallucination and
    more), logs results to a named project for dashboard monitoring, and
    performs root cause analysis on failures. These paths correspond to the
    public endpoints called by the uptrain Python package's APIClient
    (uptrain/framework/remote.py), rooted at {server_url}/api/public. The
    default managed server is https://demo.uptrain.ai. Requests are
    authenticated with an uptrain-access-token header.
  termsOfService: https://uptrain.ai/
  contact:
    name: UpTrain
    url: https://uptrain.ai/
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0.html
  version: '0.7.1'
servers:
  - url: https://demo.uptrain.ai/api/public
    description: Default UpTrain managed evaluation service
security:
  - UptrainAccessToken: []
paths:
  /auth:
    get:
      operationId: checkAuth
      tags:
        - Auth
      summary: Validate the UpTrain access token.
      description: >-
        Checks that the supplied uptrain-access-token is valid. Called by the
        APIClient.check_auth() method on initialization.
      responses:
        '200':
          description: Token is valid.
          content:
            application/json:
              schema:
                type: object
                properties:
                  message:
                    type: string
        '401':
          description: Invalid or missing access token.
  /evaluate:
    post:
      operationId: evaluate
      tags:
        - Evaluation
      summary: Run evaluations on a set of LLM responses.
      description: >-
        Evaluates each row of input data against the supplied list of checks and
        returns the original rows enriched with per-check scores and
        explanations. Grading LLM calls are run server-side by UpTrain.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/EvaluateRequest'
      responses:
        '200':
          description: Evaluation results, one object per input row.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EvaluationResults'
        '401':
          description: Invalid or missing access token.
        '422':
          description: Invalid request payload.
  /log_and_evaluate:
    post:
      operationId: logAndEvaluate
      tags:
        - Evaluation
      summary: Log data to a project and evaluate it.
      description: >-
        Logs the supplied data under a named project and runs the requested
        checks, persisting results so they are visible on the UpTrain dashboard
        with real-time monitoring. This endpoint also backs the SDK's
        evaluate_experiments method, which adds experiment column names for A/B
        comparison of prompt or model variants.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/LogAndEvaluateRequest'
      responses:
        '200':
          description: Evaluation results, one object per input row.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EvaluationResults'
        '401':
          description: Invalid or missing access token.
        '422':
          description: Invalid request payload.
  /perform_root_cause_analysis:
    post:
      operationId: performRootCauseAnalysis
      tags:
        - Root Cause Analysis
      summary: Perform root cause analysis on failing responses.
      description: >-
        Analyzes failing RAG or LLM responses and classifies why each response
        was poor (for example incomplete context, poor retrieval, or
        hallucination) to guide remediation.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RootCauseAnalysisRequest'
      responses:
        '200':
          description: Root cause analysis results, one object per input row.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EvaluationResults'
        '401':
          description: Invalid or missing access token.
        '422':
          description: Invalid request payload.
  /run:
    post:
      operationId: addRun
      tags:
        - Runs
      summary: Create an evaluation run.
      description: >-
        Creates a run that pairs a previously uploaded dataset with a checkset
        and executes the checks asynchronously. Returns a run identifier that
        can be polled for status and results.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RunRequest'
      responses:
        '200':
          description: The created run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Run'
        '401':
          description: Invalid or missing access token.
  /run/{run_id}:
    get:
      operationId: getRun
      tags:
        - Runs
      summary: Get the status of a run.
      parameters:
        - name: run_id
          in: path
          required: true
          schema:
            type: string
      responses:
        '200':
          description: The run object with its current status.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Run'
        '404':
          description: Run not found.
  /run/{run_id}/results:
    get:
      operationId: getRunResults
      tags:
        - Runs
      summary: Download the results of a completed run.
      parameters:
        - name: run_id
          in: path
          required: true
          schema:
            type: string
      responses:
        '200':
          description: Evaluation results for the run.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EvaluationResults'
        '404':
          description: Run not found.
  /dataset:
    post:
      operationId: addDataset
      tags:
        - Datasets
      summary: Upload an evaluation dataset.
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                name:
                  type: string
                  description: Name to register the dataset under.
                file:
                  type: string
                  format: binary
                  description: JSONL / CSV file of evaluation rows.
      responses:
        '200':
          description: The registered dataset.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Dataset'
        '401':
          description: Invalid or missing access token.
    get:
      operationId: getDataset
      tags:
        - Datasets
      summary: Get a dataset by name.
      parameters:
        - name: name
          in: query
          required: true
          schema:
            type: string
      responses:
        '200':
          description: The dataset.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Dataset'
        '404':
          description: Dataset not found.
  /checkset:
    post:
      operationId: addCheckset
      tags:
        - Checksets
      summary: Create a reusable checkset.
      description: >-
        Registers a named bundle of checks that can be paired with a dataset in
        a run. This endpoint also backs add_experiment in the SDK.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/Checkset'
      responses:
        '200':
          description: The registered checkset.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Checkset'
        '401':
          description: Invalid or missing access token.
  /evaluation_results/{project_name}:
    get:
      operationId: downloadProjectEvalResults
      tags:
        - Evaluation
      summary: Download evaluation results for a project.
      parameters:
        - name: project_name
          in: path
          required: true
          schema:
            type: string
      responses:
        '200':
          description: All evaluation results logged under the project.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EvaluationResults'
        '404':
          description: Project not found.
components:
  securitySchemes:
    UptrainAccessToken:
      type: apiKey
      in: header
      name: uptrain-access-token
      description: >-
        UpTrain managed-service access token. Obtained from the UpTrain
        dashboard and supplied on every request as the uptrain-access-token
        header.
  schemas:
    EvalRow:
      type: object
      description: >-
        A single evaluation row. The exact keys depend on the checks requested;
        common keys are question, response and context.
      properties:
        question:
          type: string
          description: The user query / prompt sent to the LLM.
        response:
          type: string
          description: The LLM-generated response to grade.
        context:
          type: string
          description: Retrieved context provided to the LLM (for RAG checks).
        ground_truth:
          type: string
          description: Optional reference answer for accuracy checks.
      additionalProperties: true
    EvaluateRequest:
      type: object
      required:
        - data
        - checks
      properties:
        data:
          type: array
          description: List of rows to evaluate.
          items:
            $ref: '#/components/schemas/EvalRow'
        checks:
          type: array
          description: >-
            List of checks to run. Each item is a preconfigured check name (for
            example context_relevance, factual_accuracy, response_completeness,
            response_conciseness, response_relevance, valid_response, tonality,
            prompt_injection, jailbreak_detection) or a check object.
          items:
            type: string
          example:
            - context_relevance
            - factual_accuracy
            - response_completeness
        metadata:
          type: object
          description: Optional metadata to attach to the evaluation.
          additionalProperties: true
    LogAndEvaluateRequest:
      type: object
      required:
        - project_name
        - data
        - checks
      properties:
        project_name:
          type: string
          description: Project to log the data and results under.
        data:
          type: array
          items:
            $ref: '#/components/schemas/EvalRow'
        checks:
          type: array
          items:
            type: string
          example:
            - context_relevance
            - factual_accuracy
        metadata:
          type: object
          additionalProperties: true
    RootCauseAnalysisRequest:
      type: object
      required:
        - project_name
        - data
        - rca_template
      properties:
        project_name:
          type: string
        data:
          type: array
          items:
            $ref: '#/components/schemas/EvalRow'
        rca_template:
          type: string
          description: >-
            Root cause analysis template to apply, for example
            rag_with_citation.
          example: rag_with_citation
    EvaluationResults:
      type: array
      description: >-
        The input rows echoed back, each enriched with score_<check> and
        explanation_<check> fields for every requested check.
      items:
        type: object
        additionalProperties: true
    RunRequest:
      type: object
      required:
        - dataset
        - checkset
      properties:
        name:
          type: string
        dataset:
          type: string
          description: Name of a previously uploaded dataset.
        checkset:
          type: string
          description: Name of a previously created checkset.
    Run:
      type: object
      properties:
        run_id:
          type: string
        status:
          type: string
          description: Run status, for example queued, running, or done.
        created_at:
          type: string
          format: date-time
    Dataset:
      type: object
      properties:
        name:
          type: string
        rows:
          type: integer
        created_at:
          type: string
          format: date-time
    Checkset:
      type: object
      required:
        - name
        - checks
      properties:
        name:
          type: string
        checks:
          type: array
          items:
            type: string