LangChain Integration - Pezzo

Pezzo supports integration with LangChain for observability and monitoring. Integration is as easy as configuring the LLM to proxy requests to Pezzo.

If you want to learn more about the Pezzo Proxy, click here.

Example: LangChain with OpenAI

Below is an example using ChatOpenAI. The same can be applied to chains and agents.

LangChain + Node.js
LangChain + Python

import { ChatOpenAI } from "langchain/chat_models/openai";

const llm = new ChatOpenAI({
  openAIApiKey: process.env.OPENAI_API_KEY,
  temperature: 0,
  configuration: {
    baseURL: "https://proxy.pezzo.ai/openai/v1",
    defaultHeaders: {
      "X-Pezzo-Api-Key": "<Your API Key>",
      "X-Pezzo-Project-Id": "<Your Project ID>",
      "X-Pezzo-Environment": "Production",
    },
  },
});

const llmResult = await llm.predict("Tell me 5 fun facts about yourself!");

from langchain.chat_models import ChatOpenAI

llm = ChatOpenAI(
    openai_api_key='<>',
    openai_api_base="https://proxy.pezzo.ai/openai/v1",
    default_headers={
      "X-Pezzo-Api-Key": "<Your API Key>",
      "X-Pezzo-Project-Id": "<Your Project ID>",
      "X-Pezzo-Environment": "Production",
    }
)

llm_result = llm.predict("Tell me 5 fun facts about yourself!")