Skip to main content

Overview

Evaluations run one or more evaluators against samples in a dataset. Each evaluation produces scores and detailed results that you can use to measure AI performance. Base URL: https://api.akhara.ai/v1/evaluations

Create Evaluation

Create and start a new evaluation run.

Request Body

Evaluator Configuration

Example Request

Response


List Evaluations

List evaluations with optional filtering.

Query Parameters

Example Request


Get Evaluation

Retrieve a specific evaluation with full results.

Example Request

Response (Completed)


Get Evaluation Results

Retrieve detailed per-sample results.

Query Parameters

Example Request

Response


Cancel Evaluation

Cancel a running evaluation.

Example Request

Response


Compare Evaluations

Compare results between two or more evaluations.

Request Body

Example Request

Response


Built-in Evaluators

Triage Accuracy

Evaluates correctness of urgency level classification.

Red Flag Detection

Checks if critical symptoms were identified.

Guideline Compliance

Measures adherence to clinical protocols.

Symptom Extraction

Evaluates completeness of symptom identification.

Custom Evaluator

Use your own evaluation logic via webhook.

Scoring & Metrics APIs

Detailed scoring and metrics endpoints

Human Review APIs

Route flagged samples for clinician review