evals

Overview ¶

Package evals provides evaluation capabilities for Phoenix.

This package implements the llmops.Evaluator interface, enabling evaluation of LLM outputs with metrics and recording results to Phoenix.

Usage ¶

import (
    "github.com/agentplexus/go-phoenix"
    "github.com/agentplexus/go-phoenix/evals"
    "github.com/agentplexus/omniobserve/llmops"
    "github.com/agentplexus/omniobserve/llmops/metrics"
)

// Create Phoenix client
client, _ := phoenix.NewClient()

// Create evaluator
evaluator := evals.NewEvaluator(client)

// Run evaluation
result, _ := evaluator.Evaluate(ctx, llmops.EvalInput{
    Input:   "What is the capital of France?",
    Output:  "The capital of France is Paris.",
    SpanID:  "span-123",
}, metrics.NewExactMatchMetric())