Langfuse SDKs

The Langfuse SDKs are the recommended way to integrate with Langfuse.

Properties:

• Fully async requests, using Langfuse adds almost no latency
• Accurate latency tracking using synchronous timestamps
• IDs available for downstream use
• Great DX when nesting observations
• Cannot break your application, all errors are caught and logged
• Interoperable with Langfuse integrations

JS/TS

npm install langfuse
 
# Node.js < 18
npm install langfuse-node

pnpm add langfuse
 
# Node.js < 18
pnpm add langfuse-node

yarn add langfuse
 
# Node.js < 18
yarn add langfuse-node

bun add langfuse
 
# Node.js < 18
bun add langfuse-node

• Fully typed
• Edge-ready, e.g., Vercel, Cloudflare, Deno
• Works client-side to report user feedback (with only the public_key)
• Interfaces
  • Server-side
  • Client-side, meant to be used in the browser to report scores

Python

pip install langfuse

• Based on OpenTelemetry, so you can use any OTEL-based instrumentation library for your LLM. See our docs for more details.
• Uses Pydantic for typing and validation
• Interfaces
  • @observe() decorator
  • Context Managers
  • Manual instrumentation