@fiddler-ai/langchain

LangChain JS instrumentation for Fiddler observability. Auto-traces LangChain applications via OpenTelemetry.

Note: If you're using LangGraph, see @fiddler-ai/langgraph instead. Both packages use the same callback handler under the hood — this package provides a clean import path for LangChain-only users.

Installation

npm install @fiddler-ai/langchain @fiddler-ai/otel @opentelemetry/api @langchain/core

Quick Start

import { FiddlerClient } from "@fiddler-ai/otel";
import { LangChainInstrumentor, setConversationId } from "@fiddler-ai/langchain";

// 1. Create a Fiddler client
const client = new FiddlerClient({
  url: "https://app.fiddler.ai",
  apiKey: process.env.FIDDLER_API_KEY!,
  applicationId: "your-app-uuid",
});

// 2. Auto-instrument LangChain
const instrumentor = new LangChainInstrumentor(client);
await instrumentor.instrument();

// 3. Set conversation context
setConversationId("session-123");

// 4. Use LangChain normally — traces are auto-captured
const chain = prompt.pipe(model).pipe(outputParser);
const result = await chain.invoke({ input: "Hello" });

// 5. Flush before exit
await client.flush();

Manual Callback Handler

import { FiddlerClient } from "@fiddler-ai/otel";
import { FiddlerCallbackHandler } from "@fiddler-ai/langchain";

const client = new FiddlerClient({ /* ... */ });
const handler = new FiddlerCallbackHandler(client);

const result = await chain.invoke(
  { input: "Hello" },
  { callbacks: [handler] },
);

Context Utilities

import {
  setConversationId,
  addSessionAttributes,
  setLlmContext,
} from "@fiddler-ai/langchain";

setConversationId("thread-abc");
addSessionAttributes({ userId: "user-123" });
setLlmContext(chatModel, "Retrieved context: ...");

Requirements

• Node.js >= 20
• @langchain/core >= 0.3.0
• @fiddler-ai/otel >= 0.1.0
• @opentelemetry/api >= 1.9.0