Skip to main content

BeeAI has native integration with Arize Phoenix


NPM Version This module provides automatic instrumentation for BeeAI framework. It integrates seamlessly with the @opentelemetry/sdk-trace-node package to collect and export telemetry data.

​
Install

npm install --save beeai-framework \
  @arizeai/openinference-instrumentation-beeai \
  @arizeai/openinference-semantic-conventions \
  @opentelemetry/sdk-trace-node \
  @opentelemetry/resources \
  @opentelemetry/exporter-trace-otlp-proto \
  @opentelemetry/semantic-conventions \
  @opentelemetry/instrumentation

​
Setup

To instrument your application, import and enable BeeAIInstrumentation. Create the instrumentation.js file: 
import {
  NodeTracerProvider,
  SimpleSpanProcessor,
  ConsoleSpanExporter,
} from "@opentelemetry/sdk-trace-node";
import { diag, DiagConsoleLogger, DiagLogLevel } from "@opentelemetry/api";
import { resourceFromAttributes } from "@opentelemetry/resources";
import { OTLPTraceExporter } from "@opentelemetry/exporter-trace-otlp-proto";
import { ATTR_SERVICE_NAME } from "@opentelemetry/semantic-conventions";
import { SEMRESATTRS_PROJECT_NAME } from "@arizeai/openinference-semantic-conventions";
import * as beeaiFramework from "beeai-framework";
import { registerInstrumentations } from "@opentelemetry/instrumentation";
import { BeeAIInstrumentation } from "@arizeai/openinference-instrumentation-beeai";

const COLLECTOR_ENDPOINT = "your-phoenix-collector-endpoint";

const provider = new NodeTracerProvider({
  resource: resourceFromAttributes({
    [ATTR_SERVICE_NAME]: "beeai-project",
    [SEMRESATTRS_PROJECT_NAME]: "beeai-project",
  }),
  spanProcessors: [
    new SimpleSpanProcessor(new ConsoleSpanExporter()),
    new SimpleSpanProcessor(
      new OTLPTraceExporter({
        url: `${COLLECTOR_ENDPOINT}/v1/traces`,
        // (optional) if connecting to Phoenix with Authentication enabled
        headers: { Authorization: `Bearer ${process.env.PHOENIX_API_KEY}` },
      }),
    ),
  ],
});

provider.register();

const beeAIInstrumentation = new BeeAIInstrumentation();
beeAIInstrumentation.manuallyInstrument(beeaiFramework);

registerInstrumentations({
  instrumentations: [beeAIInstrumentation],
});

console.log("👀 OpenInference initialized");

​
Run BeeAI

Sample agent built using BeeAI with automatic tracing: 
import "./instrumentation.js";
import { ToolCallingAgent } from "beeai-framework/agents/toolCalling/agent";
import { TokenMemory } from "beeai-framework/memory/tokenMemory";
import { DuckDuckGoSearchTool } from "beeai-framework/tools/search/duckDuckGoSearch";
import { OpenMeteoTool } from "beeai-framework/tools/weather/openMeteo";
import { OpenAIChatModel } from "beeai-framework/adapters/openai/backend/chat";

const llm = new OpenAIChatModel(
  "gpt-4o",
  {},
  { apiKey: 'your-openai-api-key' }
);

const agent = new ToolCallingAgent({
  llm,
  memory: new TokenMemory(),
  tools: [
    new DuckDuckGoSearchTool(),
    new OpenMeteoTool(), // weather tool
  ],
});

async function main() {
  const response = await agent.run({ prompt: "What's the current weather in Berlin?" });
  console.log(`Agent 🤖 : `, response.result.text);
}

main();

​
Observe

Phoenix provides visibility into your BeeAI agent operations by automatically tracing all interactions.

​
Troubleshooting

Add the following at the top of your instrumentation.js to see OpenTelemetry diagnostic logs in your console while debugging: 
import { diag, DiagConsoleLogger, DiagLogLevel } from "@opentelemetry/api";

// Enable OpenTelemetry diagnostic logging
diag.setLogger(new DiagConsoleLogger(), DiagLogLevel.INFO);
If traces aren’t appearing, a common cause is an outdated beeai-framework package. Check the diagnostic logs for version or initialization errors and update your package as needed.

​
Custom Tracer Provider

You can specify a custom tracer provider for BeeAI instrumentation in multiple ways:

​
Method 1: Pass tracerProvider on instantiation

const beeAIInstrumentation = new BeeAIInstrumentation({
  tracerProvider: customTracerProvider,
});
beeAIInstrumentation.manuallyInstrument(beeaiFramework);

​
Method 2: Set tracerProvider after instantiation

const beeAIInstrumentation = new BeeAIInstrumentation();
beeAIInstrumentation.setTracerProvider(customTracerProvider);
beeAIInstrumentation.manuallyInstrument(beeaiFramework);

​
Method 3: Pass tracerProvider to registerInstrumentations

const beeAIInstrumentation = new BeeAIInstrumentation();
beeAIInstrumentation.manuallyInstrument(beeaiFramework);

registerInstrumentations({
  instrumentations: [beeAIInstrumentation],
  tracerProvider: customTracerProvider,
});

​
Resources