LangChain

Connect your LangChain-powered application to Latitude for observability.

Work in progress: Telemetry documentation is still being updated. Integration steps and APIs may be incomplete or out of date. Verify against your SDK versions and check back for revisions.

Overview

This guide shows you how to integrate Latitude Telemetry into an application that uses LangChain.

You’ll keep calling LangChain exactly as you do today. Telemetry simply observes and enriches those calls.

---

Requirements

• A Latitude account and API key
• A Latitude project slug
• A project that uses LangChain

---

Steps

1. Install

   TypeScript

   npm

   npm install @latitude-data/telemetry
   

   Python

   pip

   pip install latitude-telemetry
   
2. Initialize and use

   TypeScript

   import { initLatitude, capture } from "@latitude-data/telemetry"
   import { ChatOpenAI } from "@langchain/openai"
   import { HumanMessage } from "@langchain/core/messages"
   
   const latitude = initLatitude({
     apiKey: process.env.LATITUDE_API_KEY!,
     projectSlug: process.env.LATITUDE_PROJECT_SLUG!,
     instrumentations: ["langchain"],
   })
   
   await latitude.ready
   
   const llm = new ChatOpenAI({ modelName: "gpt-4o" })
   
   await capture("langchain-query", async () => {
     const response = await llm.invoke([new HumanMessage("Hello")])
     return response.content
   })
   
   await latitude.shutdown()
   

   Python

   from latitude_telemetry import init_latitude, capture
   from langchain_openai import ChatOpenAI
   from langchain_core.messages import HumanMessage
   
   latitude = init_latitude(
       api_key="your-api-key",
       project_slug="your-project-slug",
       instrumentations=["langchain"],
   )
   
   llm = ChatOpenAI(model="gpt-4o")
   
   def langchain_query():
       response = llm.invoke([HumanMessage(content="Hello")])
       return response.content
   
   capture("langchain-query", langchain_query)
   
   latitude.shutdown()
   

---

Seeing Your Traces

Once connected, traces appear automatically in Latitude:

1. Open your project in the Latitude dashboard
2. Each execution shows input/output messages, model, token usage, latency, and errors
3. LangChain chain steps appear as child spans

---

That’s It

No changes to your LangChain calls: just initialize Latitude and your LLM calls are traced.