Langchain

Before you begin

Follow the Setting up guide to make sure that you have access to the Hamming dashboard and you have created a secret key.

Quickstart - Node.js

Learn how to monitor your AI application with our Hamming TypeScript SDK.

1. Install Hamming SDK TypeScript libraries

2. Create a script for a simple Langchain application

Make sure to replace the placeholders with your actual keys and dataset ID created in the previous step.

Create a file named langchain-app.js and add the following code:

langchain-app.js

const { Hamming } = require("@hamming/hamming-sdk");
const { OpenAI } = require("openai");

// Setup OpenAI API Key to be used by the Langchain LLM call 
process.env.OPENAI_API_KEY = "<your-openai-key>";
const HAMMING_API_KEY = "<your-secret-key>";
const hamming = new Hamming({ apiKey: HAMMING_API_KEY });

// Setup Hamming callback to be used by the Langchain chain
const cb = new HammingCallbackHandler(hamming);

async function run() {
  const model = new ChatOpenAI({ model: "gpt-4-turbo" });
  const systemTemplate = "Translate the following into {language}:";
  const promptTemplate = ChatPromptTemplate.fromMessages([
    ["system", systemTemplate],
    ["user", "{text}"],
  ]);
  const chain = promptTemplate.pipe(model);
  const result = await chain.invoke(
    { language: "italian", text: "hi" },
    { callbacks: [cb] } // Pass the Hamming callback into the chain
  );
  console.log(result.content);
}

run().catch(console.error);

3. Run the Langchain application script

Install dependencies:

npm install langchain @langchain/openai

Run the script by executing the following command in your terminal:

node langchain-app.js

This will create a monitoring item in Hamming with the corresponding LLM trace. You can view the item on the Monitoring page.

Quickstart - Python

Learn how to monitor your AI application with our Hamming Python SDK.

1. Install Hamming SDK Python library

2. Create a script for a simple Langchain application

Create a file named langchain-app.py and add the following code:

langchain-app.py

import os
from hamming import (
    ClientOptions,
    Hamming,
    LangchainCallbackHandler
)
from operator import itemgetter
from langchain_openai import ChatOpenAI
from langchain.prompts import ChatPromptTemplate
from langchain.schema import StrOutputParser

HAMMING_API_KEY = "<your-secret-key>"
# Setup OpenAI API Key to be used by the Langchain LLM call 
os.environ["OPENAI_API_KEY"] = "<your-openai-key>"

hamming = Hamming(ClientOptions(api_key=HAMMING_API_KEY))
# Setup Hamming callback to be used by the Langchain chain
callback_handler = LangchainCallbackHandler(hamming)

def run():
    prompt1 = ChatPromptTemplate.from_template("what is the city {person} is from?")
    prompt2 = ChatPromptTemplate.from_template(
        "what country is the city {city} in? respond in {language}"
    )
    model = ChatOpenAI()
    chain1 = prompt1 | model | StrOutputParser()
    chain2 = (
        {"city": chain1, "language": itemgetter("language")}
        | prompt2
        | model
        | StrOutputParser()
    )

    chain2.invoke(
        {"person": "trudeau", "language": "french"}, 
        config={"callbacks":[callback_handler]} # Pass the Hamming callback into the chain
    )

if __name__ == "__main__":
    run()

3. Run the Langchain application script

Install dependencies:

pip install langchain langchain_openai

Run the script by executing the following command in your terminal:

python langchain-app.py

This will create a monitoring item in Hamming with the corresponding LLM trace. You can view the item in the Monitoring dashboard.

Get Started

Voice Agent Testing

Call Monitoring

Other Guides

Before you begin

Quickstart - Node.js

Quickstart - Python

Get Started

Voice Agent Testing

Call Monitoring

Other Guides

​Before you begin

​Quickstart - Node.js

​Quickstart - Python

Before you begin

Quickstart - Node.js

Quickstart - Python