Skip to content

Latest commit

 

History

History
44 lines (28 loc) · 1.41 KB

README.md

File metadata and controls

44 lines (28 loc) · 1.41 KB
Raw

Overview

This is a very simple example of how to setup LangChain.js auto instrumentation in a node application.

Instrumentation

Checkout the instrumentation.ts file to see how to auto-instrument LangChain.js and export spans to a locally running (Phoenix)[https://github.com/Arize-ai/phoenix] server.

Chat

Checkout the chat.ts file to see how to send a simple message to OpenAI with langchain.

Instructions

Please use node version >= 18 to run this example.

  1. (Optional) In order to see spans in Phoenix, begin running a Phoenix server. This can be done in one command using docker.
docker run -p 6006:6006 -i -t arizephoenix/phoenix
  1. Make sure you have and OpenAI API key set in your environment variables as OPENAI_API_KEY.
  2. Go to the root of the JS directory of this repo and run the following commands to install dependencies and build the latest packages in the repo. This ensures any dependencies within the repo are at their latest versions.
pnpm -r install
pnpm -r prebuild
pnpm -r build
  1. Run the following command from the openinference-instrumentation-langchain package directory
node dist/examples/chat.js

You should see your spans exported in your console. If you've set up a locally running Phoenix server, head over to localhost:6006 to see your spans.