@anvia/langfuse

Langfuse tracing adapter for Anvia.

Use this package to attach Langfuse tracing to Anvia agents and to publish evaluation scores from Anvia eval reporters.

Installation

pnpm add @anvia/langfuse @anvia/core

In this monorepo, the package is available through the workspace:

pnpm --filter @anvia/langfuse build

Usage

import { AgentBuilder } from "@anvia/core";
import { OpenAIClient } from "@anvia/openai";
import { langfuse } from "@anvia/langfuse";

const tracing = langfuse.create({
  publicKey,
  secretKey,
  baseUrl,
  environment,
  release,
});

const client = new OpenAIClient({
  apiKey,
});

const agent = new AgentBuilder("support", client.completionModel())
  .instructions("Answer support questions clearly.")
  .observe(tracing)
  .build();

const response = await agent.prompt("How do I reset my password?").send();

console.log(response.output);

await tracing.flush();

Use flush() after short-lived jobs. Use shutdown() when the process is exiting.

Eval Scores

import { createLangfuseEvalReporter } from "@anvia/langfuse";

const reporter = createLangfuseEvalReporter(tracing);

The reporter reads trace information from eval output when available, then publishes metric scores to Langfuse.

Exports

• langfuse
• createLangfuseEvalReporter
• LangfuseTracing
• LangfuseTracingOptions
• LangfuseScoreArgs
• LangfuseEvalReporterOptions

Development

pnpm --filter @anvia/langfuse typecheck
pnpm --filter @anvia/langfuse test
pnpm --filter @anvia/langfuse build