Getting Started

LlamaIndex Integration

LlamaIndex is a data framework for building RAG (Retrieval-Augmented Generation) applications.

Python

Installation

pip install llama-index llama-index-llms-openai-like

Basic Usage

from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    model="openai/gpt-5.2",
    api_key="your-langmart-api-key",
    api_base="https://api.langmart.ai/v1",
)

response = llm.complete("What is the capital of France?")
print(response.text)

Chat Interface

from llama_index.core.llms import ChatMessage

messages = [
    ChatMessage(role="system", content="You are a helpful assistant."),
    ChatMessage(role="user", content="Explain quantum computing in simple terms."),
]

response = llm.chat(messages)
print(response.message.content)

Using with Index

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.core import Settings

Settings.llm = OpenAILike(
    model="anthropic/claude-opus-4.5",
    api_key="your-langmart-api-key",
    api_base="https://api.langmart.ai/v1",
)

documents = SimpleDirectoryReader("./data").load_data()
index = VectorStoreIndex.from_documents(documents)

query_engine = index.as_query_engine()
response = query_engine.query("What is the main topic?")
print(response)

Streaming

response = llm.stream_complete("Write a poem about coding")

for chunk in response:
    print(chunk.delta, end="", flush=True)

TypeScript

Installation

npm install llamaindex

Usage

import { OpenAI } from "llamaindex";

const llm = new OpenAI({
  model: "openai/gpt-5.2",
  apiKey: "your-langmart-api-key",
  additionalSessionOptions: {
    baseURL: "https://api.langmart.ai/v1",
  },
});

const response = await llm.complete({ prompt: "Hello, world!" });
console.log(response.text);

Learn More