Implementation:FlowiseAI Flowise GetEvaluation

Property	Value
Implementation Name	GetEvaluation
Implements	Principle:FlowiseAI_Flowise_Evaluation_Results_Analysis
Source	packages/ui/src/api/evaluations.js, packages/ui/src/views/evaluations/EvaluationResult.jsx
Repository	FlowiseAI/Flowise
Domain	API Client, Results Visualization
Last Updated	2026-02-12 14:00 GMT

Code Reference

Source Location

The evaluation retrieval API function is defined in packages/ui/src/api/evaluations.js at line 6. The results are rendered by the EvaluationResult.jsx component located at packages/ui/src/views/evaluations/EvaluationResult.jsx (approximately 1050 lines).

Signature

// packages/ui/src/api/evaluations.js:L6
const getEvaluation = (id) => client.get(`/evaluations/${id}`)

The API client is configured at packages/ui/src/api/client.js with a base URL of ${baseURL}/api/v1, making the full endpoint:

• GET /api/v1/evaluations/{id}

Import

import evaluationApi from '@/api/evaluations'

UI Components

The results page imports and uses several visualization components:

// packages/ui/src/views/evaluations/EvaluationResult.jsx
import MetricsItemCard from '@/views/evaluations/MetricsItemCard'
import { ChartLatency } from '@/views/evaluations/ChartLatency'
import { ChartPassPrnt } from '@/views/evaluations/ChartPassPrnt'
import { ChartTokens } from '@/views/evaluations/ChartTokens'
import EvaluationResultSideDrawer from '@/views/evaluations/EvaluationResultSideDrawer'
import EvaluationResultVersionsSideDrawer from '@/views/evaluations/EvaluationResultVersionsSideDrawer'
import EvalsResultDialog from '@/views/evaluations/EvalsResultDialog'

Charts are rendered using the recharts library for interactive data visualization.

I/O Contract

getEvaluation

Inputs:

• id (string, required): The unique identifier of the evaluation run to retrieve

Outputs:

• Promise<{data: EvaluationDetail}>: Resolves with the full evaluation detail object containing:
  • rows (Array): Per-row evaluation results, each containing:
    • input (string): The original input prompt from the dataset
    • expectedOutput (string): The expected output from the dataset
    • actualOutput (Object): The actual chatflow response(s), keyed by chatflow ID
    • evaluatorResults (Object): Pass/fail results for each evaluator
    • latency (number): API response time in milliseconds
    • tokenUsage (Object): Token consumption details (promptTokens, completionTokens, totalTokens)
    • cost (number): Estimated cost for the row
  • summary (Object): Aggregate metrics including pass count, fail count, error count, average latency, and average cost

Usage Examples

Fetching Evaluation Results

import evaluationApi from '@/api/evaluations'

// Retrieve the full evaluation results
const response = await evaluationApi.getEvaluation('eval-run-123')
const evaluationDetail = response.data

// Access summary metrics
const { passCount, failCount, errorCount, avgLatency, avgCost } = evaluationDetail.summary

// Iterate per-row results
evaluationDetail.rows.forEach((row) => {
    console.log('Input:', row.input)
    console.log('Expected:', row.expectedOutput)
    console.log('Actual:', row.actualOutput)
    console.log('Evaluators:', row.evaluatorResults)
})

Using with the useApi Hook in React

import React, { useEffect } from 'react'
import useApi from '@/hooks/useApi'
import evaluationApi from '@/api/evaluations'

const EvaluationResultPage = ({ evaluationId }) => {
    const getEvaluationApi = useApi(evaluationApi.getEvaluation)

    useEffect(() => {
        getEvaluationApi.request(evaluationId)
    }, [evaluationId])

    if (getEvaluationApi.data) {
        const evaluation = getEvaluationApi.data
        // Render MetricsItemCard, ChartPassPrnt, ChartLatency, ChartTokens
        // Render per-row results table
    }
}

Related Pages

• Principle:FlowiseAI_Flowise_Evaluation_Results_Analysis
• Implementation:FlowiseAI_Flowise_CreateEvaluation
• Implementation:FlowiseAI_Flowise_RunAgain
• Implementation:FlowiseAI_Flowise_GetVersions