Use Meridian with LlamaIndex

Installation

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

Quick start

from llama_index.llms.openai import OpenAI

llm = OpenAI(
    api_key="nim_live_***",
    api_base="https://meridian.getnimbus.net/api/v1",
    model="gpt-5-codex"
)

resp = llm.complete("hello")

With agents

from llama_index.core.agent import ReActAgent

agent = ReActAgent.from_tools([t1, t2], llm=llm)

Embeddings

Currently embeddings via Meridian are gpt-3.5-turbo only. Use OpenAI directly for embeddings.