Getting Started

LangChain Integration

LangChain provides a standard interface for building applications with LLMs.

Python

Installation

pip install langchain langchain-openai

Usage

from langchain_openai import ChatOpenAI

chat = ChatOpenAI(
    model="anthropic/claude-opus-4.5",
    temperature=0.7,
    openai_api_key="your-langmart-api-key",
    openai_api_base="https://api.langmart.ai/v1",
)

response = chat.invoke("Tell me a fun fact about space.")
print(response.content)

With Message Types

from langchain_core.messages import HumanMessage, SystemMessage

messages = [
    SystemMessage(content="You are a helpful assistant."),
    HumanMessage(content="What is the capital of France?"),
]

response = chat.invoke(messages)
print(response.content)

JavaScript / TypeScript

Installation

npm install @langchain/openai @langchain/core

Usage

import { ChatOpenAI } from "@langchain/openai";
import { HumanMessage, SystemMessage } from "@langchain/core/messages";

const chat = new ChatOpenAI(
  {
    model: "openai/gpt-5.2",
    temperature: 0.8,
    apiKey: "your-langmart-api-key",
  },
  {
    baseURL: "https://api.langmart.ai/v1",
  }
);

const response = await chat.invoke([
  new SystemMessage("You are a helpful assistant."),
  new HumanMessage("Hello, how are you?"),
]);

console.log(response.content);

Streaming

from langchain_openai import ChatOpenAI

chat = ChatOpenAI(
    model="openai/gpt-5.2",
    streaming=True,
    openai_api_key="your-langmart-api-key",
    openai_api_base="https://api.langmart.ai/v1",
)

for chunk in chat.stream("Write a haiku about coding"):
    print(chunk.content, end="", flush=True)

With Chains

from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate

chat = ChatOpenAI(
    model="anthropic/claude-opus-4.5",
    openai_api_key="your-langmart-api-key",
    openai_api_base="https://api.langmart.ai/v1",
)

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a {role}."),
    ("human", "{input}"),
])

chain = prompt | chat
response = chain.invoke({"role": "poet", "input": "Write about the moon"})
print(response.content)

Learn More