Langgraph

LangGraph Example with Reflight

This example demonstrates how to integrate Reflight with LangGraph workflows to track and observe your AI operations.

Installation

Install the Reflight SDK for LangChain:

# Using npm
npm install @reflight/langchain
 
# Using pnpm
pnpm add @reflight/langchain
 
# Using yarn
yarn add @reflight/langchain
 
# Using bun
bun add @reflight/langchain

Setup

  1. Get your Reflight API key from your Reflight dashboard
  2. Set it as an environment variable:
export REFLIGHT_API_KEY="your-api-key-here"

Usage

The Reflight SDK provides three main functions for LangGraph:

1. Initialize Reflight

Call init() at the start of your application to set up Reflight tracking:

import { init } from "@reflight/langchain";
 
init(process.env.REFLIGHT_API_KEY);

2. Use the Tracer Callback

Add the Tracer callback to your LangGraph workflow's RunnableConfig to automatically track all operations:

import { Tracer } from "@reflight/langchain";
import { runPublishingWorkflow } from "./workflows/publishing-workflow";
 
const result = await runPublishingWorkflow(
  {
    topic: "New feature launch",
    audience: "developers",
    channel: "email",
  },
  {
    callbacks: [new Tracer()], // Add Reflight tracer
  }
);

The Tracer automatically captures:

  • All LLM calls
  • Tool invocations
  • Workflow state transitions
  • Message flow

3. Shutdown (Optional)

Call shutdown() when your application is done to ensure all traces are flushed:

import { shutdown } from "@reflight/langchain";
 
// At the end of your script
await shutdown();

Complete Example

Here's a complete example showing all three steps:

import { init, shutdown, Tracer } from "@reflight/langchain";
import { runPublishingWorkflow, type PublishingRequest } from "./workflows/publishing-workflow";
 
// 1. Initialize Reflight
init(process.env.REFLIGHT_API_KEY);
 
// 2. Run your workflow with Tracer
const request: PublishingRequest = {
  topic: "New feature launch: AI-powered content generation",
  audience: "product managers and marketing teams",
  tone: "professional",
  channel: "email",
  length: 150,
  ctaUrl: "https://example.com/learn-more",
};
 
const result = await runPublishingWorkflow(request, {
  callbacks: [new Tracer()], // Reflight automatically tracks everything
});
 
// 3. Shutdown when done
await shutdown();

What Gets Tracked

With the Tracer callback, Reflight automatically tracks:

  • LLM Calls: Every model invocation with inputs, outputs, and metadata
  • Tool Usage: All tool calls with parameters and results
  • Workflow Execution: State transitions and message flow
  • Performance Metrics: Latency, token usage, and costs

All of this data appears in your Reflight dashboard for analysis and debugging.

Running the Example

# Make sure you have your API keys set
export OPENAI_API_KEY="your-openai-key"
export REFLIGHT_API_KEY="your-reflight-key"
 
# Run the workflow
bun run scripts/run-workflow.ts
Index