LangChain

LangChain works with Glitch by configuring the OpenAI client before passing it to LangChain. This secures all LLM calls made through LangChain chains, agents, and tools.

Configuration

Python

import os
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-4",
    api_key=os.environ["GLITCH_API_KEY"],  # Your Glitch API key
    base_url="https://api.golabrat.ai/v1",
)

response = llm.invoke("Hello, world!")
print(response.content)

JavaScript

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

const llm = new ChatOpenAI({
  model: "gpt-4",
  apiKey: process.env.GLITCH_API_KEY!,
  configuration: {
    baseURL: "https://api.golabrat.ai/v1",
  }
});

const response = await llm.invoke("Hello, world!");
console.log(response.content);

Basic Example

Python

import os
from langchain_openai import ChatOpenAI
from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate

# Configure LangChain with Glitch
llm = ChatOpenAI(
    model="gpt-4",
    api_key=os.environ["GLITCH_API_KEY"],
    base_url="https://api.golabrat.ai/v1",
)

# Use in a chain - all LLM calls are secured
prompt = PromptTemplate(
    input_variables=["topic"],
    template="Write a short poem about {topic}",
)
chain = LLMChain(llm=llm, prompt=prompt)
result = chain.run("AI")
print(result)

JavaScript

import { ChatOpenAI } from "@langchain/openai";
import { PromptTemplate } from "@langchain/core/prompts";
import { LLMChain } from "langchain/chains";

const llm = new ChatOpenAI({
  model: "gpt-4",
  apiKey: process.env.GLITCH_API_KEY!,
  configuration: {
    baseURL: "https://api.golabrat.ai/v1",
  }
});

const prompt = PromptTemplate.fromTemplate("Write a short poem about {topic}");
const chain = new LLMChain({ llm, prompt });
const result = await chain.call({ topic: "AI" });
console.log(result.text);

---

Next Steps

• Frameworks Overview — Other framework integrations
• Quick Start — Get running in 5 minutes
• API Reference — Full endpoint documentation